Upload 107 files

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+deploy/triton-inference-server/data/dog_result.jpg filter=lfs diff=lfs merge=lfs -text
+deploy/triton-inference-server/data/dog.jpg filter=lfs diff=lfs merge=lfs -text
+models/__pycache__/common.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text
+tools/YOLOv7-Dynamic-Batch-TENSORRT.ipynb filter=lfs diff=lfs merge=lfs -text

LICENSE.md

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<https://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<https://www.gnu.org/licenses/why-not-lgpl.html>.

README.md

@@ -1,12 +1,310 @@
----
-title: Newcustomyolo
-emoji: 📚
-colorFrom: yellow
-colorTo: pink
-sdk: gradio
-sdk_version: 5.24.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Official YOLOv7
+
+Implementation of paper - [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://arxiv.org/abs/2207.02696)
+
+[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/yolov7-trainable-bag-of-freebies-sets-new/real-time-object-detection-on-coco)](https://paperswithcode.com/sota/real-time-object-detection-on-coco?p=yolov7-trainable-bag-of-freebies-sets-new)
+[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/akhaliq/yolov7)
+<a href="https://colab.research.google.com/gist/AlexeyAB/b769f5795e65fdab80086f6cb7940dae/yolov7detection.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+[![arxiv.org](http://img.shields.io/badge/cs.CV-arXiv%3A2207.02696-B31B1B.svg)](https://arxiv.org/abs/2207.02696)
+
+<div align="center">
+    <a href="./">
+        <img src="./figure/performance.png" width="79%"/>
+    </a>
+</div>
+
+## Web Demo
+
+- Integrated into [Huggingface Spaces 🤗](https://huggingface.co/spaces/akhaliq/yolov7) using Gradio. Try out the Web Demo [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/akhaliq/yolov7)
+
+## Performance 
+
+MS COCO
+
+| Model | Test Size | AP<sup>test</sup> | AP<sub>50</sub><sup>test</sup> | AP<sub>75</sub><sup>test</sup> | batch 1 fps | batch 32 average time |
+| :-- | :-: | :-: | :-: | :-: | :-: | :-: |
+| [**YOLOv7**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt) | 640 | **51.4%** | **69.7%** | **55.9%** | 161 *fps* | 2.8 *ms* |
+| [**YOLOv7-X**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x.pt) | 640 | **53.1%** | **71.2%** | **57.8%** | 114 *fps* | 4.3 *ms* |
+|  |  |  |  |  |  |  |
+| [**YOLOv7-W6**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6.pt) | 1280 | **54.9%** | **72.6%** | **60.1%** | 84 *fps* | 7.6 *ms* |
+| [**YOLOv7-E6**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt) | 1280 | **56.0%** | **73.5%** | **61.2%** | 56 *fps* | 12.3 *ms* |
+| [**YOLOv7-D6**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6.pt) | 1280 | **56.6%** | **74.0%** | **61.8%** | 44 *fps* | 15.0 *ms* |
+| [**YOLOv7-E6E**](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e.pt) | 1280 | **56.8%** | **74.4%** | **62.1%** | 36 *fps* | 18.7 *ms* |
+
+## Installation
+
+Docker environment (recommended)
+<details><summary> <b>Expand</b> </summary>
+
+``` shell
+# create the docker container, you can change the share memory size if you have more.
+nvidia-docker run --name yolov7 -it -v your_coco_path/:/coco/ -v your_code_path/:/yolov7 --shm-size=64g nvcr.io/nvidia/pytorch:21.08-py3
+
+# apt install required packages
+apt update
+apt install -y zip htop screen libgl1-mesa-glx
+
+# pip install required packages
+pip install seaborn thop
+
+# go to code folder
+cd /yolov7
+```
+
+</details>
+
+## Testing
+
+[`yolov7.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt) [`yolov7x.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x.pt) [`yolov7-w6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6.pt) [`yolov7-e6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt) [`yolov7-d6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6.pt) [`yolov7-e6e.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e.pt)
+
+``` shell
+python test.py --data data/coco.yaml --img 640 --batch 32 --conf 0.001 --iou 0.65 --device 0 --weights yolov7.pt --name yolov7_640_val
+```
+
+You will get the results:
+
+```
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.51206
+ Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.69730
+ Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.55521
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.35247
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.55937
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.66693
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.38453
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.63765
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.68772
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.53766
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.73549
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.83868
+```
+
+To measure accuracy, download [COCO-annotations for Pycocotools](http://images.cocodataset.org/annotations/annotations_trainval2017.zip) to the `./coco/annotations/instances_val2017.json`
+
+## Training
+
+Data preparation
+
+``` shell
+bash scripts/get_coco.sh
+```
+
+* Download MS COCO dataset images ([train](http://images.cocodataset.org/zips/train2017.zip), [val](http://images.cocodataset.org/zips/val2017.zip), [test](http://images.cocodataset.org/zips/test2017.zip)) and [labels](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/coco2017labels-segments.zip). If you have previously used a different version of YOLO, we strongly recommend that you delete `train2017.cache` and `val2017.cache` files, and redownload [labels](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/coco2017labels-segments.zip) 
+
+Single GPU training
+
+``` shell
+# train p5 models
+python train.py --workers 8 --device 0 --batch-size 32 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml
+
+# train p6 models
+python train_aux.py --workers 8 --device 0 --batch-size 16 --data data/coco.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights '' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml
+```
+
+Multiple GPU training
+
+``` shell
+# train p5 models
+python -m torch.distributed.launch --nproc_per_node 4 --master_port 9527 train.py --workers 8 --device 0,1,2,3 --sync-bn --batch-size 128 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml
+
+# train p6 models
+python -m torch.distributed.launch --nproc_per_node 8 --master_port 9527 train_aux.py --workers 8 --device 0,1,2,3,4,5,6,7 --sync-bn --batch-size 128 --data data/coco.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights '' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml
+```
+
+## Transfer learning
+
+[`yolov7_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7_training.pt) [`yolov7x_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x_training.pt) [`yolov7-w6_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6_training.pt) [`yolov7-e6_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6_training.pt) [`yolov7-d6_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6_training.pt) [`yolov7-e6e_training.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e_training.pt)
+
+Single GPU finetuning for custom dataset
+
+``` shell
+# finetune p5 models
+python train.py --workers 8 --device 0 --batch-size 32 --data data/custom.yaml --img 640 640 --cfg cfg/training/yolov7-custom.yaml --weights 'yolov7_training.pt' --name yolov7-custom --hyp data/hyp.scratch.custom.yaml
+
+# finetune p6 models
+python train_aux.py --workers 8 --device 0 --batch-size 16 --data data/custom.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6-custom.yaml --weights 'yolov7-w6_training.pt' --name yolov7-w6-custom --hyp data/hyp.scratch.custom.yaml
+```
+
+## Re-parameterization
+
+See [reparameterization.ipynb](tools/reparameterization.ipynb)
+
+## Inference
+
+On video:
+``` shell
+python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source yourvideo.mp4
+```
+
+On image:
+``` shell
+python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source inference/images/horses.jpg
+```
+
+<div align="center">
+    <a href="./">
+        <img src="./figure/horses_prediction.jpg" width="59%"/>
+    </a>
+</div>
+
+
+## Export
+
+**Pytorch to CoreML (and inference on MacOS/iOS)** <a href="https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/YOLOv7CoreML.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+
+**Pytorch to ONNX with NMS (and inference)** <a href="https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/YOLOv7onnx.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+```shell
+python export.py --weights yolov7-tiny.pt --grid --end2end --simplify \
+        --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640 --max-wh 640
+```
+
+**Pytorch to TensorRT with NMS (and inference)** <a href="https://colab.research.google.com/github/WongKinYiu/yolov7/blob/main/tools/YOLOv7trt.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+
+```shell
+wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-tiny.pt
+python export.py --weights ./yolov7-tiny.pt --grid --end2end --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640
+git clone https://github.com/Linaom1214/tensorrt-python.git
+python ./tensorrt-python/export.py -o yolov7-tiny.onnx -e yolov7-tiny-nms.trt -p fp16
+```
+
+**Pytorch to TensorRT another way** <a href="https://colab.research.google.com/gist/AlexeyAB/fcb47ae544cf284eb24d8ad8e880d45c/yolov7trtlinaom.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> <details><summary> <b>Expand</b> </summary>
+
+
+```shell
+wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-tiny.pt
+python export.py --weights yolov7-tiny.pt --grid --include-nms
+git clone https://github.com/Linaom1214/tensorrt-python.git
+python ./tensorrt-python/export.py -o yolov7-tiny.onnx -e yolov7-tiny-nms.trt -p fp16
+
+# Or use trtexec to convert ONNX to TensorRT engine
+/usr/src/tensorrt/bin/trtexec --onnx=yolov7-tiny.onnx --saveEngine=yolov7-tiny-nms.trt --fp16
+```
+
+</details>
+
+Tested with: Python 3.7.13, Pytorch 1.12.0+cu113
+
+## Pose estimation
+
+[`code`](https://github.com/WongKinYiu/yolov7/tree/pose) [`yolov7-w6-pose.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6-pose.pt)
+
+See [keypoint.ipynb](https://github.com/WongKinYiu/yolov7/blob/main/tools/keypoint.ipynb).
+
+<div align="center">
+    <a href="./">
+        <img src="./figure/pose.png" width="39%"/>
+    </a>
+</div>
+
+
+## Instance segmentation (with NTU)
+
+[`code`](https://github.com/WongKinYiu/yolov7/tree/mask) [`yolov7-mask.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-mask.pt)
+
+See [instance.ipynb](https://github.com/WongKinYiu/yolov7/blob/main/tools/instance.ipynb).
+
+<div align="center">
+    <a href="./">
+        <img src="./figure/mask.png" width="59%"/>
+    </a>
+</div>
+
+## Instance segmentation
+
+[`code`](https://github.com/WongKinYiu/yolov7/tree/u7/seg) [`yolov7-seg.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-seg.pt)
+
+YOLOv7 for instance segmentation (YOLOR + YOLOv5 + YOLACT)
+
+| Model | Test Size | AP<sup>box</sup> | AP<sub>50</sub><sup>box</sup> | AP<sub>75</sub><sup>box</sup> | AP<sup>mask</sup> | AP<sub>50</sub><sup>mask</sup> | AP<sub>75</sub><sup>mask</sup> |
+| :-- | :-: | :-: | :-: | :-: | :-: | :-: | :-: |
+| **YOLOv7-seg** | 640 | **51.4%** | **69.4%** | **55.8%** | **41.5%** | **65.5%** | **43.7%** |
+
+## Anchor free detection head
+
+[`code`](https://github.com/WongKinYiu/yolov7/tree/u6) [`yolov7-u6.pt`](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-u6.pt)
+
+YOLOv7 with decoupled TAL head (YOLOR + YOLOv5 + YOLOv6)
+
+| Model | Test Size | AP<sup>val</sup> | AP<sub>50</sub><sup>val</sup> | AP<sub>75</sub><sup>val</sup> |
+| :-- | :-: | :-: | :-: | :-: |
+| **YOLOv7-u6** | 640 | **52.6%** | **69.7%** | **57.3%** |
+
+
+## Citation
+
+```
+@inproceedings{wang2023yolov7,
+  title={{YOLOv7}: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors},
+  author={Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year={2023}
+}
+```
+
+```
+@article{wang2023designing,
+  title={Designing Network Design Strategies Through Gradient Path Analysis},
+  author={Wang, Chien-Yao and Liao, Hong-Yuan Mark and Yeh, I-Hau},
+  journal={Journal of Information Science and Engineering},
+  year={2023}
+}
+```
+
+
+## Teaser
+
+YOLOv7-semantic & YOLOv7-panoptic & YOLOv7-caption
+
+<div align="center">
+    <a href="./">
+        <img src="./figure/tennis.jpg" width="24%"/>
+    </a>
+    <a href="./">
+        <img src="./figure/tennis_semantic.jpg" width="24%"/>
+    </a>
+    <a href="./">
+        <img src="./figure/tennis_panoptic.png" width="24%"/>
+    </a>
+    <a href="./">
+        <img src="./figure/tennis_caption.png" width="24%"/>
+    </a>
+</div>
+
+YOLOv7-semantic & YOLOv7-detection & YOLOv7-depth (with NTUT)
+
+<div align="center">
+    <a href="./">
+        <img src="./figure/yolov7_city.jpg" width="80%"/>
+    </a>
+</div>
+
+YOLOv7-3d-detection & YOLOv7-lidar & YOLOv7-road (with NTUT)
+
+<div align="center">
+    <a href="./">
+        <img src="./figure/yolov7_3d.jpg" width="30%"/>
+    </a>
+    <a href="./">
+        <img src="./figure/yolov7_lidar.jpg" width="30%"/>
+    </a>
+    <a href="./">
+        <img src="./figure/yolov7_road.jpg" width="30%"/>
+    </a>
+</div>
+
+
+## Acknowledgements
+
+<details><summary> <b>Expand</b> </summary>
+
+* [https://github.com/AlexeyAB/darknet](https://github.com/AlexeyAB/darknet)
+* [https://github.com/WongKinYiu/yolor](https://github.com/WongKinYiu/yolor)
+* [https://github.com/WongKinYiu/PyTorch_YOLOv4](https://github.com/WongKinYiu/PyTorch_YOLOv4)
+* [https://github.com/WongKinYiu/ScaledYOLOv4](https://github.com/WongKinYiu/ScaledYOLOv4)
+* [https://github.com/Megvii-BaseDetection/YOLOX](https://github.com/Megvii-BaseDetection/YOLOX)
+* [https://github.com/ultralytics/yolov3](https://github.com/ultralytics/yolov3)
+* [https://github.com/ultralytics/yolov5](https://github.com/ultralytics/yolov5)
+* [https://github.com/DingXiaoH/RepVGG](https://github.com/DingXiaoH/RepVGG)
+* [https://github.com/JUGGHM/OREPA_CVPR2022](https://github.com/JUGGHM/OREPA_CVPR2022)
+* [https://github.com/TexasInstruments/edgeai-yolov5/tree/yolo-pose](https://github.com/TexasInstruments/edgeai-yolov5/tree/yolo-pose)
+
+</details>

app.py

@@ -0,0 +1,190 @@
+import argparse
+import time
+from pathlib import Path
+import os
+import cv2
+import torch
+import torch.backends.cudnn as cudnn
+from numpy import random
+import sys
+import numpy as np
+from models.experimental import attempt_load
+from utils.datasets import LoadImages
+from utils.general import check_img_size, non_max_suppression, scale_coords, set_logging, increment_path
+from utils.plots import plot_one_box
+from utils.torch_utils import select_device, time_synchronized
+import gradio as gr
+import ffmpeg
+
+# IoU and scanner movement functions (unchanged)
+def compute_iou(box1, box2):
+    x1, y1, x2, y2 = box1
+    x1_, y1_, x2_, y2_ = box2
+    xi1 = max(x1, x1_)
+    yi1 = max(y1, y1_)
+    xi2 = min(x2, x2_)
+    yi2 = min(y2, y2_)
+    inter_width = max(0, xi2 - xi1)
+    inter_height = max(0, yi2 - yi1)
+    inter_area = inter_width * inter_height
+    box1_area = (x2 - x1) * (y2 - y1)
+    box2_area = (x2_ - x1_) * (y2_ - y1_)
+    union_area = box1_area + box2_area - inter_area
+    return inter_area / union_area if union_area != 0 else 0.0
+
+def is_scanner_moving(prev_centroids, curr_box, scanner_id, threshold=5.0):
+    x1, y1, x2, y2 = curr_box
+    curr_centroid = ((x1 + x2) / 2, (y1 + y2) / 2)
+    if scanner_id in prev_centroids:
+        prev_x, prev_y = prev_centroids[scanner_id]
+        distance = np.sqrt((curr_centroid[0] - prev_x)**2 + (curr_centroid[1] - prev_y)**2)
+        return distance > threshold
+    return False
+
+def detect_video(video_path, weights, conf_thres=0.25, iou_thres=0.45, img_size=640, device='', save_dir='runs/detect/exp'):
+    save_dir = Path(increment_path(Path(save_dir), exist_ok=True))
+    save_dir.mkdir(parents=True, exist_ok=True)
+    
+    set_logging()
+    device = select_device(device)
+    half = device.type != 'cpu'
+    model = attempt_load(weights, map_location=device)
+    stride = int(model.stride.max())
+    imgsz = check_img_size(img_size, s=stride)
+    if half:
+        model.half()
+
+    dataset = LoadImages(video_path, img_size=imgsz, stride=stride)
+    names = model.module.names if hasattr(model, 'module') else model.names
+    colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
+
+    vid_path, vid_writer = None, None
+    prev_centroids = {}
+    scanner_id_counter = 0
+
+    for path, img, im0s, vid_cap in dataset:
+        img = torch.from_numpy(img).to(device)
+        img = img.half() if half else img.float()
+        img /= 255.0
+        if img.ndimension() == 3:
+            img = img.unsqueeze(0)
+
+        with torch.no_grad():
+            pred = model(img)[0]
+        pred = non_max_suppression(pred, conf_thres, iou_thres)
+
+        for i, det in enumerate(pred):
+            p = Path(path)
+            save_path = str(save_dir / p.name.replace('.mp4', '_output.mp4'))
+            im0 = im0s
+
+            if len(det):
+                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
+                item_boxes, scanner_data, phone_boxes = [], [], []
+                curr_scanner_boxes = []
+
+                for *xyxy, conf, cls in det:
+                    x1, y1, x2, y2 = map(int, xyxy)
+                    class_name = names[int(cls)]
+                    color = colors[int(cls)]
+                    if class_name.lower() == "item":
+                        item_boxes.append([x1, y1, x2, y2])
+                    elif class_name.lower() == "phone":
+                        phone_boxes.append([x1, y1, x2, y2])
+                    elif class_name.lower() == "scanner":
+                        curr_scanner_boxes.append([x1, y1, x2, y2])
+                    plot_one_box(xyxy, im0, label=class_name, color=color, line_thickness=2)
+
+                new_prev_centroids = {}
+                if prev_centroids and curr_scanner_boxes:
+                    for curr_box in curr_scanner_boxes:
+                        curr_centroid = ((curr_box[0] + curr_box[2]) / 2, (curr_box[1] + curr_box[3]) / 2)
+                        best_match_id = min(prev_centroids.keys(), 
+                                          key=lambda k: np.sqrt((curr_centroid[0] - prev_centroids[k][0])**2 + 
+                                                                (curr_centroid[1] - prev_centroids[k][1])**2), 
+                                          default=None)
+                        if best_match_id is not None and np.sqrt((curr_centroid[0] - prev_centroids[best_match_id][0])**2 + 
+                                                                 (curr_centroid[1] - prev_centroids[best_match_id][1])**2) < 50:
+                            scanner_id = best_match_id
+                        else:
+                            scanner_id = scanner_id_counter
+                            scanner_id_counter += 1
+                        is_moving = is_scanner_moving(prev_centroids, curr_box, scanner_id)
+                        movement_status = "Scanning" if is_moving else "Idle"
+                        scanner_data.append([curr_box, movement_status, scanner_id])
+                        new_prev_centroids[scanner_id] = curr_centroid
+                elif curr_scanner_boxes:
+                    for curr_box in curr_scanner_boxes:
+                        scanner_id = scanner_id_counter
+                        scanner_id_counter += 1
+                        movement_status = "Idle"
+                        curr_centroid = ((curr_box[0] + curr_box[2]) / 2, (curr_box[1] + curr_box[3]) / 2)
+                        scanner_data.append([curr_box, movement_status, scanner_id])
+                        new_prev_centroids[scanner_id] = curr_centroid
+
+                prev_centroids = new_prev_centroids
+
+                for scanner_box, movement_status, scanner_id in scanner_data:
+                    x1, y1, x2, y2 = scanner_box
+                    label = f"scanner {movement_status} (ID: {scanner_id})"
+                    plot_one_box([x1, y1, x2, y2], im0, label=label, color=colors[names.index("scanner")], line_thickness=2)
+
+                product_scanning_status = ""
+                payment_scanning_status = ""
+                for scanner_box, movement_status, _ in scanner_data:
+                    for item_box in item_boxes:
+                        if movement_status == "Scanning" and compute_iou(scanner_box, item_box) > 0.1:
+                            product_scanning_status = "Product scanning is finished"
+                    for phone_box in phone_boxes:
+                        if movement_status == "Scanning" and compute_iou(scanner_box, phone_box) > 0.1:
+                            payment_scanning_status = "Payment scanning is finished"
+
+                if product_scanning_status:
+                    cv2.putText(im0, product_scanning_status, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.9, colors[names.index("scanner")], 2)
+                if payment_scanning_status:
+                    cv2.putText(im0, payment_scanning_status, (10, 60), cv2.FONT_HERSHEY_SIMPLEX, 0.9, colors[names.index("scanner")], 2)
+
+            if vid_path != save_path:
+                vid_path = save_path
+                if isinstance(vid_writer, cv2.VideoWriter):
+                    vid_writer.release()
+                fps = vid_cap.get(cv2.CAP_PROP_FPS) if vid_cap else 30
+                w, h = im0.shape[1], im0.shape[0]
+                vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+            vid_writer.write(im0)
+
+    if isinstance(vid_writer, cv2.VideoWriter):
+        vid_writer.release()
+
+    # Convert to H.264 for browser compatibility
+    output_h264 = str(Path(save_path).with_name(f"{Path(save_path).stem}_h264.mp4"))
+    try:
+        stream = ffmpeg.input(save_path)
+        stream = ffmpeg.output(stream, output_h264, vcodec='libx264', acodec='aac', format='mp4', pix_fmt='yuv420p')
+        ffmpeg.run(stream, overwrite_output=True)
+        os.remove(save_path)  # Remove original
+        return output_h264
+    except ffmpeg.Error as e:
+        print(f"FFmpeg error: {e.stderr.decode()}")
+        return save_path
+
+def gradio_interface(video, conf_thres, iou_thres):
+    weights = "/home/myominhtet/Desktop/deepsortfromscratch/yolov7/best.pt"
+    img_size = 640
+    output_video = detect_video(video, weights, conf_thres, iou_thres, img_size)
+    return output_video if output_video else "Error processing video."
+
+interface = gr.Interface(
+    fn=gradio_interface,
+    inputs=[
+        gr.Video(label="Upload Video"),
+        gr.Slider(0, 1, value=0.25, step=0.05, label="Confidence Threshold"),
+        gr.Slider(0, 1, value=0.45, step=0.05, label="IoU Threshold"),
+    ],
+    outputs=gr.Video(label="Processed Video"),
+    title="YOLO Video Detection",
+    description="Upload a video to run YOLO detection with custom parameters."
+)
+
+if __name__ == "__main__":
+    interface.launch(share=True)

cfg/baseline/r50-csp.yaml

@@ -0,0 +1,49 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# CSP-ResNet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Stem, [128]],  # 0-P1/2
+   [-1, 3, ResCSPC, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 2-P3/8
+   [-1, 4, ResCSPC, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 4-P3/8
+   [-1, 6, ResCSPC, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 6-P3/8
+   [-1, 3, ResCSPC, [1024]],  # 7
+  ]
+
+# CSP-Res-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 8
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [5, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, ResCSPB, [256]], # 13
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [3, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, ResCSPB, [128]], # 18
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 13], 1, Concat, [1]],  # cat
+   [-1, 2, ResCSPB, [256]], # 22
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [512, 3, 2]],
+   [[-1, 8], 1, Concat, [1]],  # cat
+   [-1, 2, ResCSPB, [512]], # 26
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[19,23,27], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/baseline/x50-csp.yaml

@@ -0,0 +1,49 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# CSP-ResNeXt backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Stem, [128]],  # 0-P1/2
+   [-1, 3, ResXCSPC, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 2-P3/8
+   [-1, 4, ResXCSPC, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 4-P3/8
+   [-1, 6, ResXCSPC, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 6-P3/8
+   [-1, 3, ResXCSPC, [1024]],  # 7
+  ]
+
+# CSP-ResX-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 8
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [5, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, ResXCSPB, [256]], # 13
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [3, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, ResXCSPB, [128]], # 18
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 13], 1, Concat, [1]],  # cat
+   [-1, 2, ResXCSPB, [256]], # 22
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [512, 3, 2]],
+   [[-1, 8], 1, Concat, [1]],  # cat
+   [-1, 2, ResXCSPB, [512]], # 26
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[19,23,27], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/baseline/yolor-csp-x.yaml

@@ -0,0 +1,52 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.33  # model depth multiple
+width_multiple: 1.25  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, BottleneckCSPC, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, BottleneckCSPC, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, BottleneckCSPC, [512]],
+   [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
+   [-1, 4, BottleneckCSPC, [1024]],  # 10
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 11
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [8, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, BottleneckCSPB, [256]], # 16 
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [6, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, BottleneckCSPB, [128]], # 21
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat
+   [-1, 2, BottleneckCSPB, [256]], # 25
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [512, 3, 2]],
+   [[-1, 11], 1, Concat, [1]],  # cat
+   [-1, 2, BottleneckCSPB, [512]], # 29
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[22,26,30], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/baseline/yolor-csp.yaml

@@ -0,0 +1,52 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, BottleneckCSPC, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, BottleneckCSPC, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, BottleneckCSPC, [512]],
+   [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
+   [-1, 4, BottleneckCSPC, [1024]],  # 10
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 11
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [8, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, BottleneckCSPB, [256]], # 16 
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [6, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, BottleneckCSPB, [128]], # 21
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat
+   [-1, 2, BottleneckCSPB, [256]], # 25
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [512, 3, 2]],
+   [[-1, 11], 1, Concat, [1]],  # cat
+   [-1, 2, BottleneckCSPB, [512]], # 29
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[22,26,30], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/baseline/yolor-d6.yaml

@@ -0,0 +1,63 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # expand model depth
+width_multiple: 1.25  # expand layer channels
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [64, 3, 1]],  # 1-P1/2
+   [-1, 1, DownC, [128]],  # 2-P2/4
+   [-1, 3, BottleneckCSPA, [128]],
+   [-1, 1, DownC, [256]],  # 4-P3/8
+   [-1, 15, BottleneckCSPA, [256]],
+   [-1, 1, DownC, [512]],  # 6-P4/16
+   [-1, 15, BottleneckCSPA, [512]],
+   [-1, 1, DownC, [768]], # 8-P5/32
+   [-1, 7, BottleneckCSPA, [768]],
+   [-1, 1, DownC, [1024]], # 10-P6/64
+   [-1, 7, BottleneckCSPA, [1024]],  # 11
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 12
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-6, 1, Conv, [384, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [384]], # 17
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-13, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [256]], # 22
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-20, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [128]], # 27
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, DownC, [256]],
+   [[-1, 22], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [256]], # 31
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, DownC, [384]],
+   [[-1, 17], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [384]], # 35
+   [-1, 1, Conv, [768, 3, 1]],
+   [-2, 1, DownC, [512]],
+   [[-1, 12], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [512]], # 39
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[28,32,36,40], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

cfg/baseline/yolor-e6.yaml

@@ -0,0 +1,63 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # expand model depth
+width_multiple: 1.25  # expand layer channels
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [64, 3, 1]],  # 1-P1/2
+   [-1, 1, DownC, [128]],  # 2-P2/4
+   [-1, 3, BottleneckCSPA, [128]],
+   [-1, 1, DownC, [256]],  # 4-P3/8
+   [-1, 7, BottleneckCSPA, [256]],
+   [-1, 1, DownC, [512]],  # 6-P4/16
+   [-1, 7, BottleneckCSPA, [512]],
+   [-1, 1, DownC, [768]], # 8-P5/32
+   [-1, 3, BottleneckCSPA, [768]],
+   [-1, 1, DownC, [1024]], # 10-P6/64
+   [-1, 3, BottleneckCSPA, [1024]],  # 11
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 12
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-6, 1, Conv, [384, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [384]], # 17
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-13, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [256]], # 22
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-20, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [128]], # 27
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, DownC, [256]],
+   [[-1, 22], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [256]], # 31
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, DownC, [384]],
+   [[-1, 17], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [384]], # 35
+   [-1, 1, Conv, [768, 3, 1]],
+   [-2, 1, DownC, [512]],
+   [[-1, 12], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [512]], # 39
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[28,32,36,40], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

cfg/baseline/yolor-p6.yaml

@@ -0,0 +1,63 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # expand model depth
+width_multiple: 1.0  # expand layer channels
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [64, 3, 1]],  # 1-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
+   [-1, 3, BottleneckCSPA, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 4-P3/8
+   [-1, 7, BottleneckCSPA, [256]],
+   [-1, 1, Conv, [384, 3, 2]],  # 6-P4/16
+   [-1, 7, BottleneckCSPA, [384]],
+   [-1, 1, Conv, [512, 3, 2]], # 8-P5/32
+   [-1, 3, BottleneckCSPA, [512]],
+   [-1, 1, Conv, [640, 3, 2]], # 10-P6/64
+   [-1, 3, BottleneckCSPA, [640]],  # 11
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [320]], # 12
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-6, 1, Conv, [256, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [256]], # 17
+   [-1, 1, Conv, [192, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-13, 1, Conv, [192, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [192]], # 22
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-20, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [128]], # 27
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [192, 3, 2]],
+   [[-1, 22], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [192]], # 31
+   [-1, 1, Conv, [384, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 17], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [256]], # 35
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [320, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [320]], # 39
+   [-1, 1, Conv, [640, 3, 1]],
+
+   [[28,32,36,40], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

cfg/baseline/yolor-w6.yaml

@@ -0,0 +1,63 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # expand model depth
+width_multiple: 1.0  # expand layer channels
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [64, 3, 1]],  # 1-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
+   [-1, 3, BottleneckCSPA, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 4-P3/8
+   [-1, 7, BottleneckCSPA, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 6-P4/16
+   [-1, 7, BottleneckCSPA, [512]],
+   [-1, 1, Conv, [768, 3, 2]], # 8-P5/32
+   [-1, 3, BottleneckCSPA, [768]],
+   [-1, 1, Conv, [1024, 3, 2]], # 10-P6/64
+   [-1, 3, BottleneckCSPA, [1024]],  # 11
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 12
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-6, 1, Conv, [384, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [384]], # 17
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-13, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [256]], # 22
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-20, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [128]], # 27
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 22], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [256]], # 31
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [384, 3, 2]],
+   [[-1, 17], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [384]], # 35
+   [-1, 1, Conv, [768, 3, 1]],
+   [-2, 1, Conv, [512, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [512]], # 39
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[28,32,36,40], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

cfg/baseline/yolov3-spp.yaml

@@ -0,0 +1,51 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3-SPP head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, SPP, [512, [5, 9, 13]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/baseline/yolov3.yaml

@@ -0,0 +1,51 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3 head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, Conv, [512, [1, 1]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/baseline/yolov4-csp.yaml

@@ -0,0 +1,52 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, BottleneckCSPC, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, BottleneckCSPC, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, BottleneckCSPC, [512]],
+   [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
+   [-1, 4, BottleneckCSPC, [1024]],  # 10
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 11
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [8, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, BottleneckCSPB, [256]], # 16 
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [6, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, BottleneckCSPB, [128]], # 21
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat
+   [-1, 2, BottleneckCSPB, [256]], # 25
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [512, 3, 2]],
+   [[-1, 11], 1, Concat, [1]],  # cat
+   [-1, 2, BottleneckCSPB, [512]], # 29
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[22,26,30], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/deploy/yolov7-d6.yaml

@@ -0,0 +1,202 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7-d6 backbone
+backbone:
+  # [from, number, module, args],
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [96, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, DownC, [192]],  # 2-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [192, 1, 1]],  # 14
+         
+   [-1, 1, DownC, [384]],  # 15-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]],  # 27
+         
+   [-1, 1, DownC, [768]],  # 28-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [768, 1, 1]],  # 40
+         
+   [-1, 1, DownC, [1152]],  # 41-P5/32  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [1152, 1, 1]],  # 53
+         
+   [-1, 1, DownC, [1536]],  # 54-P6/64  
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [1536, 1, 1]],  # 66
+  ]
+
+# yolov7-d6 head
+head:
+  [[-1, 1, SPPCSPC, [768]], # 67
+  
+   [-1, 1, Conv, [576, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [53, 1, Conv, [576, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [576, 1, 1]], # 83
+  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [40, 1, Conv, [384, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 99
+   
+   [-1, 1, Conv, [192, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [27, 1, Conv, [192, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [192, 1, 1]], # 115
+      
+   [-1, 1, DownC, [384]],
+   [[-1, 99], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 129
+      
+   [-1, 1, DownC, [576]],
+   [[-1, 83], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [576, 1, 1]], # 143
+      
+   [-1, 1, DownC, [768]],
+   [[-1, 67], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [768, 1, 1]], # 157
+   
+   [115, 1, Conv, [384, 3, 1]],
+   [129, 1, Conv, [768, 3, 1]],
+   [143, 1, Conv, [1152, 3, 1]],
+   [157, 1, Conv, [1536, 3, 1]],
+
+   [[158,159,160,161], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

cfg/deploy/yolov7-e6.yaml

@@ -0,0 +1,180 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7-e6 backbone
+backbone:
+  # [from, number, module, args],
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [80, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, DownC, [160]],  # 2-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]],  # 12
+         
+   [-1, 1, DownC, [320]],  # 13-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 23
+         
+   [-1, 1, DownC, [640]],  # 24-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 34
+         
+   [-1, 1, DownC, [960]],  # 35-P5/32  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [960, 1, 1]],  # 45
+         
+   [-1, 1, DownC, [1280]],  # 46-P6/64  
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 56
+  ]
+
+# yolov7-e6 head
+head:
+  [[-1, 1, SPPCSPC, [640]], # 57
+  
+   [-1, 1, Conv, [480, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [45, 1, Conv, [480, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 71
+  
+   [-1, 1, Conv, [320, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [34, 1, Conv, [320, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 85
+   
+   [-1, 1, Conv, [160, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [23, 1, Conv, [160, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 99
+      
+   [-1, 1, DownC, [320]],
+   [[-1, 85], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 111
+      
+   [-1, 1, DownC, [480]],
+   [[-1, 71], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 123
+      
+   [-1, 1, DownC, [640]],
+   [[-1, 57], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 135
+   
+   [99, 1, Conv, [320, 3, 1]],
+   [111, 1, Conv, [640, 3, 1]],
+   [123, 1, Conv, [960, 3, 1]],
+   [135, 1, Conv, [1280, 3, 1]],
+
+   [[136,137,138,139], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

cfg/deploy/yolov7-e6e.yaml

@@ -0,0 +1,301 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7-e6e backbone
+backbone:
+  # [from, number, module, args],
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [80, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, DownC, [160]],  # 2-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]],  # 12
+   [-11, 1, Conv, [64, 1, 1]],
+   [-12, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]],  # 22
+   [[-1, -11], 1, Shortcut, [1]],  # 23
+         
+   [-1, 1, DownC, [320]],  # 24-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 34
+   [-11, 1, Conv, [128, 1, 1]],
+   [-12, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 44
+   [[-1, -11], 1, Shortcut, [1]],  # 45
+         
+   [-1, 1, DownC, [640]],  # 46-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 56
+   [-11, 1, Conv, [256, 1, 1]],
+   [-12, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 66
+   [[-1, -11], 1, Shortcut, [1]],  # 67
+         
+   [-1, 1, DownC, [960]],  # 68-P5/32  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [960, 1, 1]],  # 78
+   [-11, 1, Conv, [384, 1, 1]],
+   [-12, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [960, 1, 1]],  # 88
+   [[-1, -11], 1, Shortcut, [1]],  # 89
+         
+   [-1, 1, DownC, [1280]],  # 90-P6/64  
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 100 
+   [-11, 1, Conv, [512, 1, 1]],
+   [-12, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 110
+   [[-1, -11], 1, Shortcut, [1]],  # 111 
+  ]
+
+# yolov7-e6e head
+head:
+  [[-1, 1, SPPCSPC, [640]], # 112
+  
+   [-1, 1, Conv, [480, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [89, 1, Conv, [480, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 126
+   [-11, 1, Conv, [384, 1, 1]],
+   [-12, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 136
+   [[-1, -11], 1, Shortcut, [1]],  # 137
+  
+   [-1, 1, Conv, [320, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [67, 1, Conv, [320, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 151
+   [-11, 1, Conv, [256, 1, 1]],
+   [-12, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 161
+   [[-1, -11], 1, Shortcut, [1]],  # 162
+   
+   [-1, 1, Conv, [160, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [45, 1, Conv, [160, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 176
+   [-11, 1, Conv, [128, 1, 1]],
+   [-12, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 186
+   [[-1, -11], 1, Shortcut, [1]],  # 187
+      
+   [-1, 1, DownC, [320]],
+   [[-1, 162], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 199
+   [-11, 1, Conv, [256, 1, 1]],
+   [-12, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 209
+   [[-1, -11], 1, Shortcut, [1]],  # 210
+      
+   [-1, 1, DownC, [480]],
+   [[-1, 137], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 222
+   [-11, 1, Conv, [384, 1, 1]],
+   [-12, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 232
+   [[-1, -11], 1, Shortcut, [1]],  # 233
+      
+   [-1, 1, DownC, [640]],
+   [[-1, 112], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 245
+   [-11, 1, Conv, [512, 1, 1]],
+   [-12, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 255
+   [[-1, -11], 1, Shortcut, [1]],  # 256
+   
+   [187, 1, Conv, [320, 3, 1]],
+   [210, 1, Conv, [640, 3, 1]],
+   [233, 1, Conv, [960, 3, 1]],
+   [256, 1, Conv, [1280, 3, 1]],
+
+   [[257,258,259,260], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

cfg/deploy/yolov7-tiny-silu.yaml

@@ -0,0 +1,112 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv7-tiny backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 2]],  # 0-P1/2  
+  
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P2/4    
+   
+   [-1, 1, Conv, [32, 1, 1]],
+   [-2, 1, Conv, [32, 1, 1]],
+   [-1, 1, Conv, [32, 3, 1]],
+   [-1, 1, Conv, [32, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [64, 1, 1]],  # 7
+   
+   [-1, 1, MP, []],  # 8-P3/8
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]],  # 14
+   
+   [-1, 1, MP, []],  # 15-P4/16
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 21
+   
+   [-1, 1, MP, []],  # 22-P5/32
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]],  # 28
+  ]
+
+# YOLOv7-tiny head
+head:
+  [[-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, SP, [5]],
+   [-2, 1, SP, [9]],
+   [-3, 1, SP, [13]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [[-1, -7], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 37
+  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [21, 1, Conv, [128, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]],  # 47
+  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [14, 1, Conv, [64, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [32, 1, 1]],
+   [-2, 1, Conv, [32, 1, 1]],
+   [-1, 1, Conv, [32, 3, 1]],
+   [-1, 1, Conv, [32, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [64, 1, 1]],  # 57
+   
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, 47], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]],  # 65
+   
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 37], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 73
+      
+   [57, 1, Conv, [128, 3, 1]],
+   [65, 1, Conv, [256, 3, 1]],
+   [73, 1, Conv, [512, 3, 1]],
+
+   [[74,75,76], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/deploy/yolov7-tiny.yaml

@@ -0,0 +1,112 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# yolov7-tiny backbone
+backbone:
+  # [from, number, module, args] c2, k=1, s=1, p=None, g=1, act=True
+  [[-1, 1, Conv, [32, 3, 2, None, 1, nn.LeakyReLU(0.1)]],  # 0-P1/2  
+  
+   [-1, 1, Conv, [64, 3, 2, None, 1, nn.LeakyReLU(0.1)]],  # 1-P2/4    
+   
+   [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 7
+   
+   [-1, 1, MP, []],  # 8-P3/8
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 14
+   
+   [-1, 1, MP, []],  # 15-P4/16
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 21
+   
+   [-1, 1, MP, []],  # 22-P5/32
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 28
+  ]
+
+# yolov7-tiny head
+head:
+  [[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, SP, [5]],
+   [-2, 1, SP, [9]],
+   [-3, 1, SP, [13]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -7], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 37
+  
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [21, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 47
+  
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [14, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 57
+   
+   [-1, 1, Conv, [128, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, 47], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 65
+   
+   [-1, 1, Conv, [256, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, 37], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 73
+      
+   [57, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [65, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [73, 1, Conv, [512, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+
+   [[74,75,76], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/deploy/yolov7-w6.yaml

@@ -0,0 +1,158 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7-w6 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [64, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]],  # 10
+         
+   [-1, 1, Conv, [256, 3, 2]],  # 11-P3/8
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 19
+         
+   [-1, 1, Conv, [512, 3, 2]],  # 20-P4/16
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]],  # 28
+         
+   [-1, 1, Conv, [768, 3, 2]],  # 29-P5/32
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [768, 1, 1]],  # 37
+         
+   [-1, 1, Conv, [1024, 3, 2]],  # 38-P6/64
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [1024, 1, 1]],  # 46
+  ]
+
+# yolov7-w6 head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 47
+  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [37, 1, Conv, [384, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 59
+  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [28, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 71
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [19, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]], # 83
+      
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 71], 1, Concat, [1]],  # cat
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 93
+      
+   [-1, 1, Conv, [384, 3, 2]],
+   [[-1, 59], 1, Concat, [1]],  # cat
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 103
+      
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 47], 1, Concat, [1]],  # cat
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]], # 113
+   
+   [83, 1, Conv, [256, 3, 1]],
+   [93, 1, Conv, [512, 3, 1]],
+   [103, 1, Conv, [768, 3, 1]],
+   [113, 1, Conv, [1024, 3, 1]],
+
+   [[114,115,116,117], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

cfg/deploy/yolov7.yaml

@@ -0,0 +1,140 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+  
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2      
+   [-1, 1, Conv, [64, 3, 1]],
+   
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 11
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [128, 1, 1]],
+   [-3, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 16-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]],  # 24
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-3, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 29-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [1024, 1, 1]],  # 37
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-3, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 42-P5/32  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [1024, 1, 1]],  # 50
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 51
+  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [37, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 63
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [24, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]], # 75
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [128, 1, 1]],
+   [-3, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, -3, 63], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 88
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-3, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, -3, 51], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]], # 101
+   
+   [75, 1, RepConv, [256, 3, 1]],
+   [88, 1, RepConv, [512, 3, 1]],
+   [101, 1, RepConv, [1024, 3, 1]],
+
+   [[102,103,104], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/deploy/yolov7x.yaml

@@ -0,0 +1,156 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# yolov7x backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [40, 3, 1]],  # 0
+  
+   [-1, 1, Conv, [80, 3, 2]],  # 1-P1/2      
+   [-1, 1, Conv, [80, 3, 1]],
+   
+   [-1, 1, Conv, [160, 3, 2]],  # 3-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 13
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [160, 1, 1]],
+   [-3, 1, Conv, [160, 1, 1]],
+   [-1, 1, Conv, [160, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 18-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 28
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [320, 1, 1]],
+   [-3, 1, Conv, [320, 1, 1]],
+   [-1, 1, Conv, [320, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 33-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 43
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [640, 1, 1]],
+   [-3, 1, Conv, [640, 1, 1]],
+   [-1, 1, Conv, [640, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 48-P5/32  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 58
+  ]
+
+# yolov7x head
+head:
+  [[-1, 1, SPPCSPC, [640]], # 59
+  
+   [-1, 1, Conv, [320, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [43, 1, Conv, [320, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 73
+   
+   [-1, 1, Conv, [160, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [28, 1, Conv, [160, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 87
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [160, 1, 1]],
+   [-3, 1, Conv, [160, 1, 1]],
+   [-1, 1, Conv, [160, 3, 2]],
+   [[-1, -3, 73], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 102
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [320, 1, 1]],
+   [-3, 1, Conv, [320, 1, 1]],
+   [-1, 1, Conv, [320, 3, 2]],
+   [[-1, -3, 59], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 117
+   
+   [87, 1, Conv, [320, 3, 1]],
+   [102, 1, Conv, [640, 3, 1]],
+   [117, 1, Conv, [1280, 3, 1]],
+
+   [[118,119,120], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/training/yolov7-d6.yaml

@@ -0,0 +1,207 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args],
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [96, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, DownC, [192]],  # 2-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [192, 1, 1]],  # 14
+         
+   [-1, 1, DownC, [384]],  # 15-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]],  # 27
+         
+   [-1, 1, DownC, [768]],  # 28-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [768, 1, 1]],  # 40
+         
+   [-1, 1, DownC, [1152]],  # 41-P5/32  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [1152, 1, 1]],  # 53
+         
+   [-1, 1, DownC, [1536]],  # 54-P6/64  
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [1536, 1, 1]],  # 66
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [768]], # 67
+  
+   [-1, 1, Conv, [576, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [53, 1, Conv, [576, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [576, 1, 1]], # 83
+  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [40, 1, Conv, [384, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 99
+   
+   [-1, 1, Conv, [192, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [27, 1, Conv, [192, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [192, 1, 1]], # 115
+      
+   [-1, 1, DownC, [384]],
+   [[-1, 99], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 129
+      
+   [-1, 1, DownC, [576]],
+   [[-1, 83], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [576, 1, 1]], # 143
+      
+   [-1, 1, DownC, [768]],
+   [[-1, 67], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [768, 1, 1]], # 157
+   
+   [115, 1, Conv, [384, 3, 1]],
+   [129, 1, Conv, [768, 3, 1]],
+   [143, 1, Conv, [1152, 3, 1]],
+   [157, 1, Conv, [1536, 3, 1]],
+   
+   [115, 1, Conv, [384, 3, 1]],
+   [99, 1, Conv, [768, 3, 1]],
+   [83, 1, Conv, [1152, 3, 1]],
+   [67, 1, Conv, [1536, 3, 1]],
+
+   [[158,159,160,161,162,163,164,165], 1, IAuxDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

cfg/training/yolov7-e6.yaml

@@ -0,0 +1,185 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args],
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [80, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, DownC, [160]],  # 2-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]],  # 12
+         
+   [-1, 1, DownC, [320]],  # 13-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 23
+         
+   [-1, 1, DownC, [640]],  # 24-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 34
+         
+   [-1, 1, DownC, [960]],  # 35-P5/32  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [960, 1, 1]],  # 45
+         
+   [-1, 1, DownC, [1280]],  # 46-P6/64  
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 56
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [640]], # 57
+  
+   [-1, 1, Conv, [480, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [45, 1, Conv, [480, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 71
+  
+   [-1, 1, Conv, [320, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [34, 1, Conv, [320, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 85
+   
+   [-1, 1, Conv, [160, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [23, 1, Conv, [160, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 99
+      
+   [-1, 1, DownC, [320]],
+   [[-1, 85], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 111
+      
+   [-1, 1, DownC, [480]],
+   [[-1, 71], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 123
+      
+   [-1, 1, DownC, [640]],
+   [[-1, 57], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 135
+   
+   [99, 1, Conv, [320, 3, 1]],
+   [111, 1, Conv, [640, 3, 1]],
+   [123, 1, Conv, [960, 3, 1]],
+   [135, 1, Conv, [1280, 3, 1]],
+   
+   [99, 1, Conv, [320, 3, 1]],
+   [85, 1, Conv, [640, 3, 1]],
+   [71, 1, Conv, [960, 3, 1]],
+   [57, 1, Conv, [1280, 3, 1]],
+
+   [[136,137,138,139,140,141,142,143], 1, IAuxDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

cfg/training/yolov7-e6e.yaml

@@ -0,0 +1,306 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args],
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [80, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, DownC, [160]],  # 2-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]],  # 12
+   [-11, 1, Conv, [64, 1, 1]],
+   [-12, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]],  # 22
+   [[-1, -11], 1, Shortcut, [1]],  # 23
+         
+   [-1, 1, DownC, [320]],  # 24-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 34
+   [-11, 1, Conv, [128, 1, 1]],
+   [-12, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 44
+   [[-1, -11], 1, Shortcut, [1]],  # 45
+         
+   [-1, 1, DownC, [640]],  # 46-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 56
+   [-11, 1, Conv, [256, 1, 1]],
+   [-12, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 66
+   [[-1, -11], 1, Shortcut, [1]],  # 67
+         
+   [-1, 1, DownC, [960]],  # 68-P5/32  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [960, 1, 1]],  # 78
+   [-11, 1, Conv, [384, 1, 1]],
+   [-12, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [960, 1, 1]],  # 88
+   [[-1, -11], 1, Shortcut, [1]],  # 89
+         
+   [-1, 1, DownC, [1280]],  # 90-P6/64  
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 100 
+   [-11, 1, Conv, [512, 1, 1]],
+   [-12, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 110
+   [[-1, -11], 1, Shortcut, [1]],  # 111 
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [640]], # 112
+  
+   [-1, 1, Conv, [480, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [89, 1, Conv, [480, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 126
+   [-11, 1, Conv, [384, 1, 1]],
+   [-12, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 136
+   [[-1, -11], 1, Shortcut, [1]],  # 137
+  
+   [-1, 1, Conv, [320, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [67, 1, Conv, [320, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 151
+   [-11, 1, Conv, [256, 1, 1]],
+   [-12, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 161
+   [[-1, -11], 1, Shortcut, [1]],  # 162
+   
+   [-1, 1, Conv, [160, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [45, 1, Conv, [160, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 176
+   [-11, 1, Conv, [128, 1, 1]],
+   [-12, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 186
+   [[-1, -11], 1, Shortcut, [1]],  # 187
+      
+   [-1, 1, DownC, [320]],
+   [[-1, 162], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 199
+   [-11, 1, Conv, [256, 1, 1]],
+   [-12, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 209
+   [[-1, -11], 1, Shortcut, [1]],  # 210
+      
+   [-1, 1, DownC, [480]],
+   [[-1, 137], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 222
+   [-11, 1, Conv, [384, 1, 1]],
+   [-12, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 232
+   [[-1, -11], 1, Shortcut, [1]],  # 233
+      
+   [-1, 1, DownC, [640]],
+   [[-1, 112], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 245
+   [-11, 1, Conv, [512, 1, 1]],
+   [-12, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 255
+   [[-1, -11], 1, Shortcut, [1]],  # 256
+   
+   [187, 1, Conv, [320, 3, 1]],
+   [210, 1, Conv, [640, 3, 1]],
+   [233, 1, Conv, [960, 3, 1]],
+   [256, 1, Conv, [1280, 3, 1]],
+   
+   [186, 1, Conv, [320, 3, 1]],
+   [161, 1, Conv, [640, 3, 1]],
+   [136, 1, Conv, [960, 3, 1]],
+   [112, 1, Conv, [1280, 3, 1]],
+
+   [[257,258,259,260,261,262,263,264], 1, IAuxDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

cfg/training/yolov7-tiny.yaml

@@ -0,0 +1,112 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# yolov7-tiny backbone
+backbone:
+  # [from, number, module, args] c2, k=1, s=1, p=None, g=1, act=True
+  [[-1, 1, Conv, [32, 3, 2, None, 1, nn.LeakyReLU(0.1)]],  # 0-P1/2  
+  
+   [-1, 1, Conv, [64, 3, 2, None, 1, nn.LeakyReLU(0.1)]],  # 1-P2/4    
+   
+   [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 7
+   
+   [-1, 1, MP, []],  # 8-P3/8
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 14
+   
+   [-1, 1, MP, []],  # 15-P4/16
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 21
+   
+   [-1, 1, MP, []],  # 22-P5/32
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 28
+  ]
+
+# yolov7-tiny head
+head:
+  [[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, SP, [5]],
+   [-2, 1, SP, [9]],
+   [-3, 1, SP, [13]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -7], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 37
+  
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [21, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 47
+  
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [14, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 57
+   
+   [-1, 1, Conv, [128, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, 47], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 65
+   
+   [-1, 1, Conv, [256, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, 37], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 73
+      
+   [57, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [65, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [73, 1, Conv, [512, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+
+   [[74,75,76], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/training/yolov7-w6.yaml

@@ -0,0 +1,163 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [64, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]],  # 10
+         
+   [-1, 1, Conv, [256, 3, 2]],  # 11-P3/8
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 19
+         
+   [-1, 1, Conv, [512, 3, 2]],  # 20-P4/16
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]],  # 28
+         
+   [-1, 1, Conv, [768, 3, 2]],  # 29-P5/32
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [768, 1, 1]],  # 37
+         
+   [-1, 1, Conv, [1024, 3, 2]],  # 38-P6/64
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [1024, 1, 1]],  # 46
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 47
+  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [37, 1, Conv, [384, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 59
+  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [28, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 71
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [19, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]], # 83
+      
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 71], 1, Concat, [1]],  # cat
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 93
+      
+   [-1, 1, Conv, [384, 3, 2]],
+   [[-1, 59], 1, Concat, [1]],  # cat
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 103
+      
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 47], 1, Concat, [1]],  # cat
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]], # 113
+   
+   [83, 1, Conv, [256, 3, 1]],
+   [93, 1, Conv, [512, 3, 1]],
+   [103, 1, Conv, [768, 3, 1]],
+   [113, 1, Conv, [1024, 3, 1]],
+   
+   [83, 1, Conv, [320, 3, 1]],
+   [71, 1, Conv, [640, 3, 1]],
+   [59, 1, Conv, [960, 3, 1]],
+   [47, 1, Conv, [1280, 3, 1]],
+
+   [[114,115,116,117,118,119,120,121], 1, IAuxDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

cfg/training/yolov7.yaml

@@ -0,0 +1,140 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+  
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2      
+   [-1, 1, Conv, [64, 3, 1]],
+   
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 11
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [128, 1, 1]],
+   [-3, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 16-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]],  # 24
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-3, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 29-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [1024, 1, 1]],  # 37
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-3, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 42-P5/32  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [1024, 1, 1]],  # 50
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 51
+  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [37, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 63
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [24, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]], # 75
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [128, 1, 1]],
+   [-3, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, -3, 63], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 88
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-3, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, -3, 51], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]], # 101
+   
+   [75, 1, RepConv, [256, 3, 1]],
+   [88, 1, RepConv, [512, 3, 1]],
+   [101, 1, RepConv, [1024, 3, 1]],
+
+   [[102,103,104], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

cfg/training/yolov7x.yaml

@@ -0,0 +1,156 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [40, 3, 1]],  # 0
+  
+   [-1, 1, Conv, [80, 3, 2]],  # 1-P1/2      
+   [-1, 1, Conv, [80, 3, 1]],
+   
+   [-1, 1, Conv, [160, 3, 2]],  # 3-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 13
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [160, 1, 1]],
+   [-3, 1, Conv, [160, 1, 1]],
+   [-1, 1, Conv, [160, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 18-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 28
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [320, 1, 1]],
+   [-3, 1, Conv, [320, 1, 1]],
+   [-1, 1, Conv, [320, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 33-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 43
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [640, 1, 1]],
+   [-3, 1, Conv, [640, 1, 1]],
+   [-1, 1, Conv, [640, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 48-P5/32  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 58
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [640]], # 59
+  
+   [-1, 1, Conv, [320, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [43, 1, Conv, [320, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 73
+   
+   [-1, 1, Conv, [160, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [28, 1, Conv, [160, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 87
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [160, 1, 1]],
+   [-3, 1, Conv, [160, 1, 1]],
+   [-1, 1, Conv, [160, 3, 2]],
+   [[-1, -3, 73], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 102
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [320, 1, 1]],
+   [-3, 1, Conv, [320, 1, 1]],
+   [-1, 1, Conv, [320, 3, 2]],
+   [[-1, -3, 59], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 117
+   
+   [87, 1, Conv, [320, 3, 1]],
+   [102, 1, Conv, [640, 3, 1]],
+   [117, 1, Conv, [1280, 3, 1]],
+
+   [[118,119,120], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

data/coco.yaml

@@ -0,0 +1,23 @@
+# COCO 2017 dataset http://cocodataset.org
+
+# download command/URL (optional)
+download: bash ./scripts/get_coco.sh
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ./coco/train2017.txt  # 118287 images
+val: ./coco/val2017.txt  # 5000 images
+test: ./coco/test-dev2017.txt  # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
+
+# number of classes
+nc: 80
+
+# class names
+names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
+         'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
+         'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+         'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
+         'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
+         'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+         'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
+         'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
+         'hair drier', 'toothbrush' ]

data/hyp.scratch.custom.yaml

@@ -0,0 +1,31 @@
+lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.1  # final OneCycleLR learning rate (lr0 * lrf)
+momentum: 0.937  # SGD momentum/Adam beta1
+weight_decay: 0.0005  # optimizer weight decay 5e-4
+warmup_epochs: 3.0  # warmup epochs (fractions ok)
+warmup_momentum: 0.8  # warmup initial momentum
+warmup_bias_lr: 0.1  # warmup initial bias lr
+box: 0.05  # box loss gain
+cls: 0.3  # cls loss gain
+cls_pw: 1.0  # cls BCELoss positive_weight
+obj: 0.7  # obj loss gain (scale with pixels)
+obj_pw: 1.0  # obj BCELoss positive_weight
+iou_t: 0.20  # IoU training threshold
+anchor_t: 4.0  # anchor-multiple threshold
+# anchors: 3  # anchors per output layer (0 to ignore)
+fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
+hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
+hsv_v: 0.4  # image HSV-Value augmentation (fraction)
+degrees: 0.0  # image rotation (+/- deg)
+translate: 0.2  # image translation (+/- fraction)
+scale: 0.5  # image scale (+/- gain)
+shear: 0.0  # image shear (+/- deg)
+perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0  # image flip up-down (probability)
+fliplr: 0.5  # image flip left-right (probability)
+mosaic: 1.0  # image mosaic (probability)
+mixup: 0.0  # image mixup (probability)
+copy_paste: 0.0  # image copy paste (probability)
+paste_in: 0.0  # image copy paste (probability), use 0 for faster training
+loss_ota: 1 # use ComputeLossOTA, use 0 for faster training

data/hyp.scratch.p5.yaml

@@ -0,0 +1,31 @@
+lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.1  # final OneCycleLR learning rate (lr0 * lrf)
+momentum: 0.937  # SGD momentum/Adam beta1
+weight_decay: 0.0005  # optimizer weight decay 5e-4
+warmup_epochs: 3.0  # warmup epochs (fractions ok)
+warmup_momentum: 0.8  # warmup initial momentum
+warmup_bias_lr: 0.1  # warmup initial bias lr
+box: 0.05  # box loss gain
+cls: 0.3  # cls loss gain
+cls_pw: 1.0  # cls BCELoss positive_weight
+obj: 0.7  # obj loss gain (scale with pixels)
+obj_pw: 1.0  # obj BCELoss positive_weight
+iou_t: 0.20  # IoU training threshold
+anchor_t: 4.0  # anchor-multiple threshold
+# anchors: 3  # anchors per output layer (0 to ignore)
+fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
+hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
+hsv_v: 0.4  # image HSV-Value augmentation (fraction)
+degrees: 0.0  # image rotation (+/- deg)
+translate: 0.2  # image translation (+/- fraction)
+scale: 0.9  # image scale (+/- gain)
+shear: 0.0  # image shear (+/- deg)
+perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0  # image flip up-down (probability)
+fliplr: 0.5  # image flip left-right (probability)
+mosaic: 1.0  # image mosaic (probability)
+mixup: 0.15  # image mixup (probability)
+copy_paste: 0.0  # image copy paste (probability)
+paste_in: 0.15  # image copy paste (probability), use 0 for faster training
+loss_ota: 1 # use ComputeLossOTA, use 0 for faster training

data/hyp.scratch.p6.yaml

@@ -0,0 +1,31 @@
+lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.2  # final OneCycleLR learning rate (lr0 * lrf)
+momentum: 0.937  # SGD momentum/Adam beta1
+weight_decay: 0.0005  # optimizer weight decay 5e-4
+warmup_epochs: 3.0  # warmup epochs (fractions ok)
+warmup_momentum: 0.8  # warmup initial momentum
+warmup_bias_lr: 0.1  # warmup initial bias lr
+box: 0.05  # box loss gain
+cls: 0.3  # cls loss gain
+cls_pw: 1.0  # cls BCELoss positive_weight
+obj: 0.7  # obj loss gain (scale with pixels)
+obj_pw: 1.0  # obj BCELoss positive_weight
+iou_t: 0.20  # IoU training threshold
+anchor_t: 4.0  # anchor-multiple threshold
+# anchors: 3  # anchors per output layer (0 to ignore)
+fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
+hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
+hsv_v: 0.4  # image HSV-Value augmentation (fraction)
+degrees: 0.0  # image rotation (+/- deg)
+translate: 0.2  # image translation (+/- fraction)
+scale: 0.9  # image scale (+/- gain)
+shear: 0.0  # image shear (+/- deg)
+perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0  # image flip up-down (probability)
+fliplr: 0.5  # image flip left-right (probability)
+mosaic: 1.0  # image mosaic (probability)
+mixup: 0.15  # image mixup (probability)
+copy_paste: 0.0  # image copy paste (probability)
+paste_in: 0.15  # image copy paste (probability), use 0 for faster training
+loss_ota: 1 # use ComputeLossOTA, use 0 for faster training

data/hyp.scratch.tiny.yaml

@@ -0,0 +1,31 @@
+lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.01  # final OneCycleLR learning rate (lr0 * lrf)
+momentum: 0.937  # SGD momentum/Adam beta1
+weight_decay: 0.0005  # optimizer weight decay 5e-4
+warmup_epochs: 3.0  # warmup epochs (fractions ok)
+warmup_momentum: 0.8  # warmup initial momentum
+warmup_bias_lr: 0.1  # warmup initial bias lr
+box: 0.05  # box loss gain
+cls: 0.5  # cls loss gain
+cls_pw: 1.0  # cls BCELoss positive_weight
+obj: 1.0  # obj loss gain (scale with pixels)
+obj_pw: 1.0  # obj BCELoss positive_weight
+iou_t: 0.20  # IoU training threshold
+anchor_t: 4.0  # anchor-multiple threshold
+# anchors: 3  # anchors per output layer (0 to ignore)
+fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
+hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
+hsv_v: 0.4  # image HSV-Value augmentation (fraction)
+degrees: 0.0  # image rotation (+/- deg)
+translate: 0.1  # image translation (+/- fraction)
+scale: 0.5  # image scale (+/- gain)
+shear: 0.0  # image shear (+/- deg)
+perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0  # image flip up-down (probability)
+fliplr: 0.5  # image flip left-right (probability)
+mosaic: 1.0  # image mosaic (probability)
+mixup: 0.05  # image mixup (probability)
+copy_paste: 0.0  # image copy paste (probability)
+paste_in: 0.05  # image copy paste (probability), use 0 for faster training
+loss_ota: 1 # use ComputeLossOTA, use 0 for faster training

deploy/triton-inference-server/README.md

@@ -0,0 +1,164 @@
+# YOLOv7 on Triton Inference Server
+
+Instructions to deploy YOLOv7 as TensorRT engine to [Triton Inference Server](https://github.com/NVIDIA/triton-inference-server).
+
+Triton Inference Server takes care of model deployment with many out-of-the-box benefits, like a GRPC and HTTP interface, automatic scheduling on multiple GPUs, shared memory (even on GPU), dynamic server-side batching, health metrics and memory resource management.
+
+There are no additional dependencies needed to run this deployment, except a working docker daemon with GPU support.
+
+## Export TensorRT
+
+See https://github.com/WongKinYiu/yolov7#export for more info.
+
+```bash
+#install onnx-simplifier not listed in general yolov7 requirements.txt
+pip3 install onnx-simplifier 
+
+# Pytorch Yolov7 -> ONNX with grid, EfficientNMS plugin and dynamic batch size
+python export.py --weights ./yolov7.pt --grid --end2end --dynamic-batch --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640
+# ONNX -> TensorRT with trtexec and docker
+docker run -it --rm --gpus=all nvcr.io/nvidia/tensorrt:22.06-py3
+# Copy onnx -> container: docker cp yolov7.onnx <container-id>:/workspace/
+# Export with FP16 precision, min batch 1, opt batch 8 and max batch 8
+./tensorrt/bin/trtexec --onnx=yolov7.onnx --minShapes=images:1x3x640x640 --optShapes=images:8x3x640x640 --maxShapes=images:8x3x640x640 --fp16 --workspace=4096 --saveEngine=yolov7-fp16-1x8x8.engine --timingCacheFile=timing.cache
+# Test engine
+./tensorrt/bin/trtexec --loadEngine=yolov7-fp16-1x8x8.engine
+# Copy engine -> host: docker cp <container-id>:/workspace/yolov7-fp16-1x8x8.engine .
+```
+
+Example output of test with RTX 3090.
+
+```
+[I] === Performance summary ===
+[I] Throughput: 73.4985 qps
+[I] Latency: min = 14.8578 ms, max = 15.8344 ms, mean = 15.07 ms, median = 15.0422 ms, percentile(99%) = 15.7443 ms
+[I] End-to-End Host Latency: min = 25.8715 ms, max = 28.4102 ms, mean = 26.672 ms, median = 26.6082 ms, percentile(99%) = 27.8314 ms
+[I] Enqueue Time: min = 0.793701 ms, max = 1.47144 ms, mean = 1.2008 ms, median = 1.28644 ms, percentile(99%) = 1.38965 ms
+[I] H2D Latency: min = 1.50073 ms, max = 1.52454 ms, mean = 1.51225 ms, median = 1.51404 ms, percentile(99%) = 1.51941 ms
+[I] GPU Compute Time: min = 13.3386 ms, max = 14.3186 ms, mean = 13.5448 ms, median = 13.5178 ms, percentile(99%) = 14.2151 ms
+[I] D2H Latency: min = 0.00878906 ms, max = 0.0172729 ms, mean = 0.0128844 ms, median = 0.0125732 ms, percentile(99%) = 0.0166016 ms
+[I] Total Host Walltime: 3.04768 s
+[I] Total GPU Compute Time: 3.03404 s
+[I] Explanations of the performance metrics are printed in the verbose logs.
+```
+Note: 73.5 qps x batch 8 = 588 fps @ ~15ms latency.
+
+## Model Repository
+
+See [Triton Model Repository Documentation](https://github.com/triton-inference-server/server/blob/main/docs/model_repository.md#model-repository) for more info.
+
+```bash
+# Create folder structure
+mkdir -p triton-deploy/models/yolov7/1/
+touch triton-deploy/models/yolov7/config.pbtxt
+# Place model
+mv yolov7-fp16-1x8x8.engine triton-deploy/models/yolov7/1/model.plan
+```
+
+## Model Configuration
+
+See [Triton Model Configuration Documentation](https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#model-configuration) for more info.
+
+Minimal configuration for `triton-deploy/models/yolov7/config.pbtxt`:
+
+```
+name: "yolov7"
+platform: "tensorrt_plan"
+max_batch_size: 8
+dynamic_batching { }
+```
+
+Example repository:
+
+```bash
+$ tree triton-deploy/
+triton-deploy/
+└── models
+    └── yolov7
+        ├── 1
+        │   └── model.plan
+        └── config.pbtxt
+
+3 directories, 2 files
+```
+
+## Start Triton Inference Server
+
+```
+docker run --gpus all --rm --ipc=host --shm-size=1g --ulimit memlock=-1 --ulimit stack=67108864 -p8000:8000 -p8001:8001 -p8002:8002 -v$(pwd)/triton-deploy/models:/models nvcr.io/nvidia/tritonserver:22.06-py3 tritonserver --model-repository=/models --strict-model-config=false --log-verbose 1
+```
+
+In the log you should see:
+
+```
++--------+---------+--------+
+| Model  | Version | Status |
++--------+---------+--------+
+| yolov7 | 1       | READY  |
++--------+---------+--------+
+```
+
+## Performance with Model Analyzer
+
+See [Triton Model Analyzer Documentation](https://github.com/triton-inference-server/server/blob/main/docs/model_analyzer.md#model-analyzer) for more info.
+
+Performance numbers @ RTX 3090 + AMD Ryzen 9 5950X
+
+Example test for 16 concurrent clients using shared memory, each with batch size 1 requests:
+
+```bash
+docker run -it --ipc=host --net=host nvcr.io/nvidia/tritonserver:22.06-py3-sdk /bin/bash
+
+./install/bin/perf_analyzer -m yolov7 -u 127.0.0.1:8001 -i grpc --shared-memory system --concurrency-range 16
+
+# Result (truncated)
+Concurrency: 16, throughput: 590.119 infer/sec, latency 27080 usec
+```
+
+Throughput for 16 clients with batch size 1 is the same as for a single thread running the engine at 16 batch size locally thanks to Triton [Dynamic Batching Strategy](https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#dynamic-batcher). Result without dynamic batching (disable in model configuration) considerably worse:
+
+```bash
+# Result (truncated)
+Concurrency: 16, throughput: 335.587 infer/sec, latency 47616 usec
+```
+
+## How to run model in your code
+
+Example client can be found in client.py. It can run dummy input, images and videos.
+
+```bash
+pip3 install tritonclient[all] opencv-python
+python3 client.py image data/dog.jpg
+```
+
+![exemplary output result](data/dog_result.jpg)
+
+```
+$ python3 client.py --help
+usage: client.py [-h] [-m MODEL] [--width WIDTH] [--height HEIGHT] [-u URL] [-o OUT] [-f FPS] [-i] [-v] [-t CLIENT_TIMEOUT] [-s] [-r ROOT_CERTIFICATES] [-p PRIVATE_KEY] [-x CERTIFICATE_CHAIN] {dummy,image,video} [input]
+
+positional arguments:
+  {dummy,image,video}   Run mode. 'dummy' will send an emtpy buffer to the server to test if inference works. 'image' will process an image. 'video' will process a video.
+  input                 Input file to load from in image or video mode
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -m MODEL, --model MODEL
+                        Inference model name, default yolov7
+  --width WIDTH         Inference model input width, default 640
+  --height HEIGHT       Inference model input height, default 640
+  -u URL, --url URL     Inference server URL, default localhost:8001
+  -o OUT, --out OUT     Write output into file instead of displaying it
+  -f FPS, --fps FPS     Video output fps, default 24.0 FPS
+  -i, --model-info      Print model status, configuration and statistics
+  -v, --verbose         Enable verbose client output
+  -t CLIENT_TIMEOUT, --client-timeout CLIENT_TIMEOUT
+                        Client timeout in seconds, default no timeout
+  -s, --ssl             Enable SSL encrypted channel to the server
+  -r ROOT_CERTIFICATES, --root-certificates ROOT_CERTIFICATES
+                        File holding PEM-encoded root certificates, default none
+  -p PRIVATE_KEY, --private-key PRIVATE_KEY
+                        File holding PEM-encoded private key, default is none
+  -x CERTIFICATE_CHAIN, --certificate-chain CERTIFICATE_CHAIN
+                        File holding PEM-encoded certicate chain default is none
+```

deploy/triton-inference-server/boundingbox.py

@@ -0,0 +1,33 @@
+class BoundingBox:
+    def __init__(self, classID, confidence, x1, x2, y1, y2, image_width, image_height):
+        self.classID = classID
+        self.confidence = confidence
+        self.x1 = x1
+        self.x2 = x2
+        self.y1 = y1
+        self.y2 = y2
+        self.u1 = x1 / image_width
+        self.u2 = x2 / image_width
+        self.v1 = y1 / image_height
+        self.v2 = y2 / image_height
+
+    def box(self):
+        return (self.x1, self.y1, self.x2, self.y2)
+
+    def width(self):
+        return self.x2 - self.x1
+
+    def height(self):
+        return self.y2 - self.y1
+
+    def center_absolute(self):
+        return (0.5 * (self.x1 + self.x2), 0.5 * (self.y1 + self.y2))
+
+    def center_normalized(self):
+        return (0.5 * (self.u1 + self.u2), 0.5 * (self.v1 + self.v2))
+
+    def size_absolute(self):
+        return (self.x2 - self.x1, self.y2 - self.y1)
+
+    def size_normalized(self):
+        return (self.u2 - self.u1, self.v2 - self.v1)

deploy/triton-inference-server/client.py

@@ -0,0 +1,334 @@
+#!/usr/bin/env python
+
+import argparse
+import numpy as np
+import sys
+import cv2
+
+import tritonclient.grpc as grpcclient
+from tritonclient.utils import InferenceServerException
+
+from processing import preprocess, postprocess
+from render import render_box, render_filled_box, get_text_size, render_text, RAND_COLORS
+from labels import COCOLabels
+
+INPUT_NAMES = ["images"]
+OUTPUT_NAMES = ["num_dets", "det_boxes", "det_scores", "det_classes"]
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('mode',
+                        choices=['dummy', 'image', 'video'],
+                        default='dummy',
+                        help='Run mode. \'dummy\' will send an emtpy buffer to the server to test if inference works. \'image\' will process an image. \'video\' will process a video.')
+    parser.add_argument('input',
+                        type=str,
+                        nargs='?',
+                        help='Input file to load from in image or video mode')
+    parser.add_argument('-m',
+                        '--model',
+                        type=str,
+                        required=False,
+                        default='yolov7',
+                        help='Inference model name, default yolov7')
+    parser.add_argument('--width',
+                        type=int,
+                        required=False,
+                        default=640,
+                        help='Inference model input width, default 640')
+    parser.add_argument('--height',
+                        type=int,
+                        required=False,
+                        default=640,
+                        help='Inference model input height, default 640')
+    parser.add_argument('-u',
+                        '--url',
+                        type=str,
+                        required=False,
+                        default='localhost:8001',
+                        help='Inference server URL, default localhost:8001')
+    parser.add_argument('-o',
+                        '--out',
+                        type=str,
+                        required=False,
+                        default='',
+                        help='Write output into file instead of displaying it')
+    parser.add_argument('-f',
+                        '--fps',
+                        type=float,
+                        required=False,
+                        default=24.0,
+                        help='Video output fps, default 24.0 FPS')
+    parser.add_argument('-i',
+                        '--model-info',
+                        action="store_true",
+                        required=False,
+                        default=False,
+                        help='Print model status, configuration and statistics')
+    parser.add_argument('-v',
+                        '--verbose',
+                        action="store_true",
+                        required=False,
+                        default=False,
+                        help='Enable verbose client output')
+    parser.add_argument('-t',
+                        '--client-timeout',
+                        type=float,
+                        required=False,
+                        default=None,
+                        help='Client timeout in seconds, default no timeout')
+    parser.add_argument('-s',
+                        '--ssl',
+                        action="store_true",
+                        required=False,
+                        default=False,
+                        help='Enable SSL encrypted channel to the server')
+    parser.add_argument('-r',
+                        '--root-certificates',
+                        type=str,
+                        required=False,
+                        default=None,
+                        help='File holding PEM-encoded root certificates, default none')
+    parser.add_argument('-p',
+                        '--private-key',
+                        type=str,
+                        required=False,
+                        default=None,
+                        help='File holding PEM-encoded private key, default is none')
+    parser.add_argument('-x',
+                        '--certificate-chain',
+                        type=str,
+                        required=False,
+                        default=None,
+                        help='File holding PEM-encoded certicate chain default is none')
+
+    FLAGS = parser.parse_args()
+
+    # Create server context
+    try:
+        triton_client = grpcclient.InferenceServerClient(
+            url=FLAGS.url,
+            verbose=FLAGS.verbose,
+            ssl=FLAGS.ssl,
+            root_certificates=FLAGS.root_certificates,
+            private_key=FLAGS.private_key,
+            certificate_chain=FLAGS.certificate_chain)
+    except Exception as e:
+        print("context creation failed: " + str(e))
+        sys.exit()
+
+    # Health check
+    if not triton_client.is_server_live():
+        print("FAILED : is_server_live")
+        sys.exit(1)
+
+    if not triton_client.is_server_ready():
+        print("FAILED : is_server_ready")
+        sys.exit(1)
+
+    if not triton_client.is_model_ready(FLAGS.model):
+        print("FAILED : is_model_ready")
+        sys.exit(1)
+
+    if FLAGS.model_info:
+        # Model metadata
+        try:
+            metadata = triton_client.get_model_metadata(FLAGS.model)
+            print(metadata)
+        except InferenceServerException as ex:
+            if "Request for unknown model" not in ex.message():
+                print("FAILED : get_model_metadata")
+                print("Got: {}".format(ex.message()))
+                sys.exit(1)
+            else:
+                print("FAILED : get_model_metadata")
+                sys.exit(1)
+
+        # Model configuration
+        try:
+            config = triton_client.get_model_config(FLAGS.model)
+            if not (config.config.name == FLAGS.model):
+                print("FAILED: get_model_config")
+                sys.exit(1)
+            print(config)
+        except InferenceServerException as ex:
+            print("FAILED : get_model_config")
+            print("Got: {}".format(ex.message()))
+            sys.exit(1)
+
+    # DUMMY MODE
+    if FLAGS.mode == 'dummy':
+        print("Running in 'dummy' mode")
+        print("Creating emtpy buffer filled with ones...")
+        inputs = []
+        outputs = []
+        inputs.append(grpcclient.InferInput(INPUT_NAMES[0], [1, 3, FLAGS.width, FLAGS.height], "FP32"))
+        inputs[0].set_data_from_numpy(np.ones(shape=(1, 3, FLAGS.width, FLAGS.height), dtype=np.float32))
+        outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[0]))
+        outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[1]))
+        outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[2]))
+        outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[3]))
+
+        print("Invoking inference...")
+        results = triton_client.infer(model_name=FLAGS.model,
+                                      inputs=inputs,
+                                      outputs=outputs,
+                                      client_timeout=FLAGS.client_timeout)
+        if FLAGS.model_info:
+            statistics = triton_client.get_inference_statistics(model_name=FLAGS.model)
+            if len(statistics.model_stats) != 1:
+                print("FAILED: get_inference_statistics")
+                sys.exit(1)
+            print(statistics)
+        print("Done")
+
+        for output in OUTPUT_NAMES:
+            result = results.as_numpy(output)
+            print(f"Received result buffer \"{output}\" of size {result.shape}")
+            print(f"Naive buffer sum: {np.sum(result)}")
+
+    # IMAGE MODE
+    if FLAGS.mode == 'image':
+        print("Running in 'image' mode")
+        if not FLAGS.input:
+            print("FAILED: no input image")
+            sys.exit(1)
+
+        inputs = []
+        outputs = []
+        inputs.append(grpcclient.InferInput(INPUT_NAMES[0], [1, 3, FLAGS.width, FLAGS.height], "FP32"))
+        outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[0]))
+        outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[1]))
+        outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[2]))
+        outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[3]))
+
+        print("Creating buffer from image file...")
+        input_image = cv2.imread(str(FLAGS.input))
+        if input_image is None:
+            print(f"FAILED: could not load input image {str(FLAGS.input)}")
+            sys.exit(1)
+        input_image_buffer = preprocess(input_image, [FLAGS.width, FLAGS.height])
+        input_image_buffer = np.expand_dims(input_image_buffer, axis=0)
+
+        inputs[0].set_data_from_numpy(input_image_buffer)
+
+        print("Invoking inference...")
+        results = triton_client.infer(model_name=FLAGS.model,
+                                      inputs=inputs,
+                                      outputs=outputs,
+                                      client_timeout=FLAGS.client_timeout)
+        if FLAGS.model_info:
+            statistics = triton_client.get_inference_statistics(model_name=FLAGS.model)
+            if len(statistics.model_stats) != 1:
+                print("FAILED: get_inference_statistics")
+                sys.exit(1)
+            print(statistics)
+        print("Done")
+
+        for output in OUTPUT_NAMES:
+            result = results.as_numpy(output)
+            print(f"Received result buffer \"{output}\" of size {result.shape}")
+            print(f"Naive buffer sum: {np.sum(result)}")
+
+        num_dets = results.as_numpy(OUTPUT_NAMES[0])
+        det_boxes = results.as_numpy(OUTPUT_NAMES[1])
+        det_scores = results.as_numpy(OUTPUT_NAMES[2])
+        det_classes = results.as_numpy(OUTPUT_NAMES[3])
+        detected_objects = postprocess(num_dets, det_boxes, det_scores, det_classes, input_image.shape[1], input_image.shape[0], [FLAGS.width, FLAGS.height])
+        print(f"Detected objects: {len(detected_objects)}")
+
+        for box in detected_objects:
+            print(f"{COCOLabels(box.classID).name}: {box.confidence}")
+            input_image = render_box(input_image, box.box(), color=tuple(RAND_COLORS[box.classID % 64].tolist()))
+            size = get_text_size(input_image, f"{COCOLabels(box.classID).name}: {box.confidence:.2f}", normalised_scaling=0.6)
+            input_image = render_filled_box(input_image, (box.x1 - 3, box.y1 - 3, box.x1 + size[0], box.y1 + size[1]), color=(220, 220, 220))
+            input_image = render_text(input_image, f"{COCOLabels(box.classID).name}: {box.confidence:.2f}", (box.x1, box.y1), color=(30, 30, 30), normalised_scaling=0.5)
+
+        if FLAGS.out:
+            cv2.imwrite(FLAGS.out, input_image)
+            print(f"Saved result to {FLAGS.out}")
+        else:
+            cv2.imshow('image', input_image)
+            cv2.waitKey(0)
+            cv2.destroyAllWindows()
+
+    # VIDEO MODE
+    if FLAGS.mode == 'video':
+        print("Running in 'video' mode")
+        if not FLAGS.input:
+            print("FAILED: no input video")
+            sys.exit(1)
+
+        inputs = []
+        outputs = []
+        inputs.append(grpcclient.InferInput(INPUT_NAMES[0], [1, 3, FLAGS.width, FLAGS.height], "FP32"))
+        outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[0]))
+        outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[1]))
+        outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[2]))
+        outputs.append(grpcclient.InferRequestedOutput(OUTPUT_NAMES[3]))
+
+        print("Opening input video stream...")
+        cap = cv2.VideoCapture(FLAGS.input)
+        if not cap.isOpened():
+            print(f"FAILED: cannot open video {FLAGS.input}")
+            sys.exit(1)
+
+        counter = 0
+        out = None
+        print("Invoking inference...")
+        while True:
+            ret, frame = cap.read()
+            if not ret:
+                print("failed to fetch next frame")
+                break
+
+            if counter == 0 and FLAGS.out:
+                print("Opening output video stream...")
+                fourcc = cv2.VideoWriter_fourcc('M', 'P', '4', 'V')
+                out = cv2.VideoWriter(FLAGS.out, fourcc, FLAGS.fps, (frame.shape[1], frame.shape[0]))
+
+            input_image_buffer = preprocess(frame, [FLAGS.width, FLAGS.height])
+            input_image_buffer = np.expand_dims(input_image_buffer, axis=0)
+
+            inputs[0].set_data_from_numpy(input_image_buffer)
+
+            results = triton_client.infer(model_name=FLAGS.model,
+                                          inputs=inputs,
+                                          outputs=outputs,
+                                          client_timeout=FLAGS.client_timeout)
+
+            num_dets = results.as_numpy("num_dets")
+            det_boxes = results.as_numpy("det_boxes")
+            det_scores = results.as_numpy("det_scores")
+            det_classes = results.as_numpy("det_classes")
+            detected_objects = postprocess(num_dets, det_boxes, det_scores, det_classes, frame.shape[1], frame.shape[0], [FLAGS.width, FLAGS.height])
+            print(f"Frame {counter}: {len(detected_objects)} objects")
+            counter += 1
+
+            for box in detected_objects:
+                print(f"{COCOLabels(box.classID).name}: {box.confidence}")
+                frame = render_box(frame, box.box(), color=tuple(RAND_COLORS[box.classID % 64].tolist()))
+                size = get_text_size(frame, f"{COCOLabels(box.classID).name}: {box.confidence:.2f}", normalised_scaling=0.6)
+                frame = render_filled_box(frame, (box.x1 - 3, box.y1 - 3, box.x1 + size[0], box.y1 + size[1]), color=(220, 220, 220))
+                frame = render_text(frame, f"{COCOLabels(box.classID).name}: {box.confidence:.2f}", (box.x1, box.y1), color=(30, 30, 30), normalised_scaling=0.5)
+
+            if FLAGS.out:
+                out.write(frame)
+            else:
+                cv2.imshow('image', frame)
+                if cv2.waitKey(1) == ord('q'):
+                    break
+
+        if FLAGS.model_info:
+            statistics = triton_client.get_inference_statistics(model_name=FLAGS.model)
+            if len(statistics.model_stats) != 1:
+                print("FAILED: get_inference_statistics")
+                sys.exit(1)
+            print(statistics)
+        print("Done")
+
+        cap.release()
+        if FLAGS.out:
+            out.release()
+        else:
+            cv2.destroyAllWindows()

deploy/triton-inference-server/labels.py

@@ -0,0 +1,83 @@
+from enum import Enum
+
+class COCOLabels(Enum):
+    PERSON = 0
+    BICYCLE = 1
+    CAR = 2
+    MOTORBIKE = 3
+    AEROPLANE = 4
+    BUS = 5
+    TRAIN = 6
+    TRUCK = 7
+    BOAT = 8
+    TRAFFIC_LIGHT = 9
+    FIRE_HYDRANT = 10
+    STOP_SIGN = 11
+    PARKING_METER = 12
+    BENCH = 13
+    BIRD = 14
+    CAT = 15
+    DOG = 16
+    HORSE = 17
+    SHEEP = 18
+    COW = 19
+    ELEPHANT = 20
+    BEAR = 21
+    ZEBRA = 22
+    GIRAFFE = 23
+    BACKPACK = 24
+    UMBRELLA = 25
+    HANDBAG = 26
+    TIE = 27
+    SUITCASE = 28
+    FRISBEE = 29
+    SKIS = 30
+    SNOWBOARD = 31
+    SPORTS_BALL = 32
+    KITE = 33
+    BASEBALL_BAT = 34
+    BASEBALL_GLOVE = 35
+    SKATEBOARD = 36
+    SURFBOARD = 37
+    TENNIS_RACKET = 38
+    BOTTLE = 39
+    WINE_GLASS = 40
+    CUP = 41
+    FORK = 42
+    KNIFE = 43
+    SPOON = 44
+    BOWL = 45
+    BANANA = 46
+    APPLE = 47
+    SANDWICH = 48
+    ORANGE = 49
+    BROCCOLI = 50
+    CARROT = 51
+    HOT_DOG = 52
+    PIZZA = 53
+    DONUT = 54
+    CAKE = 55
+    CHAIR = 56
+    SOFA = 57
+    POTTEDPLANT = 58
+    BED = 59
+    DININGTABLE = 60
+    TOILET = 61
+    TVMONITOR = 62
+    LAPTOP = 63
+    MOUSE = 64
+    REMOTE = 65
+    KEYBOARD = 66
+    CELL_PHONE = 67
+    MICROWAVE = 68
+    OVEN = 69
+    TOASTER = 70
+    SINK = 71
+    REFRIGERATOR = 72
+    BOOK = 73
+    CLOCK = 74
+    VASE = 75
+    SCISSORS = 76
+    TEDDY_BEAR = 77
+    HAIR_DRIER = 78
+    TOOTHBRUSH = 79

deploy/triton-inference-server/processing.py

@@ -0,0 +1,51 @@
+from boundingbox import BoundingBox
+
+import cv2
+import numpy as np
+
+def preprocess(img, input_shape, letter_box=True):
+    if letter_box:
+        img_h, img_w, _ = img.shape
+        new_h, new_w = input_shape[0], input_shape[1]
+        offset_h, offset_w = 0, 0
+        if (new_w / img_w) <= (new_h / img_h):
+            new_h = int(img_h * new_w / img_w)
+            offset_h = (input_shape[0] - new_h) // 2
+        else:
+            new_w = int(img_w * new_h / img_h)
+            offset_w = (input_shape[1] - new_w) // 2
+        resized = cv2.resize(img, (new_w, new_h))
+        img = np.full((input_shape[0], input_shape[1], 3), 127, dtype=np.uint8)
+        img[offset_h:(offset_h + new_h), offset_w:(offset_w + new_w), :] = resized
+    else:
+        img = cv2.resize(img, (input_shape[1], input_shape[0]))
+
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+    img = img.transpose((2, 0, 1)).astype(np.float32)
+    img /= 255.0
+    return img
+
+def postprocess(num_dets, det_boxes, det_scores, det_classes, img_w, img_h, input_shape, letter_box=True):
+    boxes = det_boxes[0, :num_dets[0][0]] / np.array([input_shape[0], input_shape[1], input_shape[0], input_shape[1]], dtype=np.float32)
+    scores = det_scores[0, :num_dets[0][0]]
+    classes = det_classes[0, :num_dets[0][0]].astype(np.int)
+
+    old_h, old_w = img_h, img_w
+    offset_h, offset_w = 0, 0
+    if letter_box:
+        if (img_w / input_shape[1]) >= (img_h / input_shape[0]):
+            old_h = int(input_shape[0] * img_w / input_shape[1])
+            offset_h = (old_h - img_h) // 2
+        else:
+            old_w = int(input_shape[1] * img_h / input_shape[0])
+            offset_w = (old_w - img_w) // 2
+
+    boxes = boxes * np.array([old_w, old_h, old_w, old_h], dtype=np.float32)
+    if letter_box:
+        boxes -= np.array([offset_w, offset_h, offset_w, offset_h], dtype=np.float32)
+    boxes = boxes.astype(np.int)
+
+    detected_objects = []
+    for box, score, label in zip(boxes, scores, classes):
+        detected_objects.append(BoundingBox(label, score, box[0], box[2], box[1], box[3], img_w, img_h))
+    return detected_objects

deploy/triton-inference-server/render.py

@@ -0,0 +1,110 @@
+import numpy as np
+
+import cv2
+
+from math import sqrt
+
+_LINE_THICKNESS_SCALING = 500.0
+
+np.random.seed(0)
+RAND_COLORS = np.random.randint(50, 255, (64, 3), "int")  # used for class visu
+RAND_COLORS[0] = [220, 220, 220]
+
+def render_box(img, box, color=(200, 200, 200)):
+    """
+    Render a box. Calculates scaling and thickness automatically.
+    :param img: image to render into
+    :param box: (x1, y1, x2, y2) - box coordinates
+    :param color: (b, g, r) - box color
+    :return: updated image
+    """
+    x1, y1, x2, y2 = box
+    thickness = int(
+        round(
+            (img.shape[0] * img.shape[1])
+            / (_LINE_THICKNESS_SCALING * _LINE_THICKNESS_SCALING)
+        )
+    )
+    thickness = max(1, thickness)
+    img = cv2.rectangle(
+        img,
+        (int(x1), int(y1)),
+        (int(x2), int(y2)),
+        color,
+        thickness=thickness
+    )
+    return img
+
+def render_filled_box(img, box, color=(200, 200, 200)):
+    """
+    Render a box. Calculates scaling and thickness automatically.
+    :param img: image to render into
+    :param box: (x1, y1, x2, y2) - box coordinates
+    :param color: (b, g, r) - box color
+    :return: updated image
+    """
+    x1, y1, x2, y2 = box
+    img = cv2.rectangle(
+        img,
+        (int(x1), int(y1)),
+        (int(x2), int(y2)),
+        color,
+        thickness=cv2.FILLED
+    )
+    return img
+
+_TEXT_THICKNESS_SCALING = 700.0
+_TEXT_SCALING = 520.0
+
+
+def get_text_size(img, text, normalised_scaling=1.0):
+    """
+    Get calculated text size (as box width and height)
+    :param img: image reference, used to determine appropriate text scaling
+    :param text: text to display
+    :param normalised_scaling: additional normalised scaling. Default 1.0.
+    :return: (width, height) - width and height of text box
+    """
+    thickness = int(
+        round(
+            (img.shape[0] * img.shape[1])
+            / (_TEXT_THICKNESS_SCALING * _TEXT_THICKNESS_SCALING)
+        )
+        * normalised_scaling
+    )
+    thickness = max(1, thickness)
+    scaling = img.shape[0] / _TEXT_SCALING * normalised_scaling
+    return cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, scaling, thickness)[0]
+
+
+def render_text(img, text, pos, color=(200, 200, 200), normalised_scaling=1.0):
+    """
+    Render a text into the image. Calculates scaling and thickness automatically.
+    :param img: image to render into
+    :param text: text to display
+    :param pos: (x, y) - upper left coordinates of render position
+    :param color: (b, g, r) - text color
+    :param normalised_scaling: additional normalised scaling. Default 1.0.
+    :return: updated image
+    """
+    x, y = pos
+    thickness = int(
+        round(
+            (img.shape[0] * img.shape[1])
+            / (_TEXT_THICKNESS_SCALING * _TEXT_THICKNESS_SCALING)
+        )
+        * normalised_scaling
+    )
+    thickness = max(1, thickness)
+    scaling = img.shape[0] / _TEXT_SCALING * normalised_scaling
+    size = get_text_size(img, text, normalised_scaling)
+    cv2.putText(
+        img,
+        text,
+        (int(x), int(y + size[1])),
+        cv2.FONT_HERSHEY_SIMPLEX,
+        scaling,
+        color,
+        thickness=thickness,
+    )
+    return img

environment.yml

@@ -0,0 +1,469 @@
+name: myominhtet
+channels:
+  - conda-forge
+  - pytorch
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - asttokens=3.0.0=py311h06a4308_0
+  - blas=1.0=mkl
+  - brotli-python=1.0.9=py311h6a678d5_9
+  - bzip2=1.0.8=h5eee18b_6
+  - ca-certificates=2025.2.25=h06a4308_0
+  - certifi=2025.1.31=py311h06a4308_0
+  - comm=0.2.1=py311h06a4308_0
+  - cpuonly=2.0=0
+  - debugpy=1.8.11=py311h6a678d5_0
+  - decorator=5.1.1=pyhd3eb1b0_0
+  - executing=0.8.3=pyhd3eb1b0_0
+  - filelock=3.13.1=py311h06a4308_0
+  - gmp=6.3.0=h6a678d5_0
+  - gmpy2=2.2.1=py311h5eee18b_0
+  - intel-openmp=2023.1.0=hdb19cb5_46306
+  - ipykernel=6.29.0=pyhd33586a_0
+  - ipython=8.30.0=py311h06a4308_0
+  - jedi=0.19.2=py311h06a4308_0
+  - jinja2=3.1.6=py311h06a4308_0
+  - jupyter_client=8.6.3=py311h06a4308_0
+  - jupyter_core=5.7.2=py311h06a4308_0
+  - ld_impl_linux-64=2.40=h12ee557_0
+  - libffi=3.4.4=h6a678d5_1
+  - libgcc-ng=11.2.0=h1234567_1
+  - libgomp=11.2.0=h1234567_1
+  - libllvm14=14.0.6=hecde1de_4
+  - libsodium=1.0.18=h7b6447c_0
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - libuuid=1.41.5=h5eee18b_0
+  - llvm-openmp=14.0.6=h9e868ea_0
+  - llvmlite=0.41.0=py311he621ea3_0
+  - markupsafe=3.0.2=py311h5eee18b_0
+  - matplotlib-inline=0.1.6=py311h06a4308_0
+  - mkl=2023.1.0=h213fc3f_46344
+  - mkl-service=2.4.0=py311h5eee18b_2
+  - mkl_fft=1.3.11=py311h5eee18b_0
+  - mkl_random=1.2.8=py311ha02d727_0
+  - mpc=1.3.1=h5eee18b_0
+  - mpfr=4.2.1=h5eee18b_0
+  - mpmath=1.3.0=py311h06a4308_0
+  - ncurses=6.4=h6a678d5_0
+  - nest-asyncio=1.6.0=py311h06a4308_0
+  - networkx=3.4.2=py311h06a4308_0
+  - numba=0.58.1=py311ha02d727_0
+  - numpy=1.26.4=py311h08b1b3b_0
+  - numpy-base=1.26.4=py311hf175353_0
+  - openssl=3.0.16=h5eee18b_0
+  - packaging=24.2=py311h06a4308_0
+  - parso=0.8.4=py311h06a4308_0
+  - pexpect=4.8.0=pyhd3eb1b0_3
+  - pip=25.0=py311h06a4308_0
+  - platformdirs=3.10.0=py311h06a4308_0
+  - prompt-toolkit=3.0.43=py311h06a4308_0
+  - prompt_toolkit=3.0.43=hd3eb1b0_0
+  - psutil=5.9.0=py311h5eee18b_1
+  - ptyprocess=0.7.0=pyhd3eb1b0_2
+  - pure_eval=0.2.2=pyhd3eb1b0_0
+  - pygments=2.15.1=py311h06a4308_1
+  - pysocks=1.7.1=py311h06a4308_0
+  - python=3.11.11=he870216_0
+  - python-dateutil=2.9.0post0=py311h06a4308_2
+  - pytorch-mutex=1.0=cpu
+  - pyyaml=6.0.2=py311h5eee18b_0
+  - pyzmq=26.2.0=py311h6a678d5_0
+  - readline=8.2=h5eee18b_0
+  - setuptools=75.8.0=py311h06a4308_0
+  - six=1.16.0=pyhd3eb1b0_1
+  - sqlite=3.45.3=h5eee18b_0
+  - stack_data=0.2.0=pyhd3eb1b0_0
+  - tbb=2021.8.0=hdb19cb5_0
+  - tk=8.6.14=h39e8969_0
+  - torchaudio=2.1.2=py311_cpu
+  - tornado=6.4.2=py311h5eee18b_0
+  - traitlets=5.14.3=py311h06a4308_0
+  - typing_extensions=4.12.2=py311h06a4308_0
+  - urllib3=2.3.0=py311h06a4308_0
+  - wcwidth=0.2.5=pyhd3eb1b0_0
+  - wheel=0.45.1=py311h06a4308_0
+  - xz=5.6.4=h5eee18b_1
+  - yaml=0.2.5=h7b6447c_0
+  - zeromq=4.3.5=h6a678d5_0
+  - zlib=1.2.13=h5eee18b_1
+  - pip:
+      - absl-py==2.1.0
+      - accelerate==0.28.0
+      - aiofiles==23.2.1
+      - aiohttp==3.9.3
+      - aiosignal==1.3.1
+      - albumentations==1.4.0
+      - alembic==1.13.1
+      - amqp==5.2.0
+      - annotated-types==0.6.0
+      - antlr4-python3-runtime==4.9.3
+      - anyio==4.3.0
+      - appdirs==1.4.4
+      - attrs==23.2.0
+      - basemap==1.4.0
+      - basemap-data==1.3.2
+      - bcrypt==4.1.3
+      - beautifulsoup4==4.12.3
+      - black==24.3.0
+      - blinker==1.7.0
+      - blis==0.7.11
+      - bs4==0.0.2
+      - cachetools==5.3.3
+      - catalogue==2.0.10
+      - catboost==1.2.2
+      - charset-normalizer==3.4.1
+      - click==8.1.7
+      - click-plugins==1.1.1
+      - cligj==0.7.2
+      - cloudpathlib==0.18.1
+      - cloudpickle==3.0.0
+      - colorama==0.4.6
+      - coloredlogs==15.0.1
+      - colorlog==6.8.2
+      - confection==0.1.5
+      - configparser==6.0.1
+      - contourpy==1.2.0
+      - crayons==0.4.0
+      - croniter==2.0.5
+      - cssselect==1.2.0
+      - cycler==0.12.1
+      - cymem==2.0.8
+      - dataclasses-json==0.6.4
+      - datasets==2.18.0
+      - dateparser==1.2.0
+      - debtcollector==3.0.0
+      - demjson3==3.0.6
+      - detectron2==0.6
+      - dill==0.3.8
+      - distlib==0.3.8
+      - distro==1.9.0
+      - dnspython==2.6.1
+      - dogpile-cache==1.3.3
+      - efficientnet-pytorch==0.7.1
+      - emoji==2.11.1
+      - en-core-web-sm==3.7.1
+      - et-xmlfile==1.1.0
+      - evdev==1.7.0
+      - eventlet==0.36.1
+      - facebook-page-scraper==5.0.2
+      - facebook-scraper==0.2.59
+      - facebook-sdk==3.1.0
+      - fake-useragent==1.4.0
+      - fastapi==0.115.4
+      - fasteners==0.19
+      - fastjsonschema==2.19.1
+      - fasttext==0.9.2
+      - ffmpeg-python==0.2.0
+      - ffmpy==0.4.0
+      - fiona==1.9.5
+      - fire==0.6.0
+      - flatbuffers==24.3.25
+      - fonttools==4.47.2
+      - frozenlist==1.4.1
+      - fsspec==2023.12.2
+      - future==1.0.0
+      - futurist==3.0.0
+      - fvcore==0.1.5.post20221221
+      - gdown==5.2.0
+      - gensim==4.3.2
+      - geographiclib==2.0
+      - geopandas==0.14.3
+      - geopy==2.4.1
+      - gkeepapi==0.16.0
+      - gmplot==1.4.1
+      - google-api-core==2.22.0
+      - google-auth==2.35.0
+      - google-auth-oauthlib==1.2.1
+      - google-cloud-vision==3.8.0
+      - google-images-download==2.8.0
+      - googleapis-common-protos==1.65.0
+      - gpsoauth==1.1.1
+      - gradio==4.44.0
+      - gradio-client==1.3.0
+      - greenlet==3.0.3
+      - grpcio==1.67.1
+      - grpcio-status==1.67.1
+      - h11==0.14.0
+      - h2==4.1.0
+      - h5py==3.10.0
+      - hpack==4.0.0
+      - httpcore==1.0.5
+      - httptools==0.6.1
+      - httpx==0.27.0
+      - huggingface-hub==0.24.7
+      - humanfriendly==10.0
+      - hydra-core==1.3.2
+      - hyperframe==6.0.1
+      - idna==3.10
+      - imagecodecs==2024.12.30
+      - imageio==2.34.0
+      - imbalanced-learn==0.12.2
+      - imblearn==0.0
+      - imgviz==1.7.5
+      - importlib-resources==6.4.5
+      - iopath==0.1.9
+      - iso8601==2.1.0
+      - jax==0.5.2
+      - jaxlib==0.5.1
+      - joblib==1.3.2
+      - jsonpatch==1.33
+      - jsonpointer==2.4
+      - jsonschema==4.21.1
+      - jsonschema-specifications==2023.12.1
+      - kaitaistruct==0.10
+      - keyboard==0.13.5
+      - keystoneauth1==5.6.0
+      - keystonemiddleware==10.7.0
+      - kiwisolver==1.4.5
+      - kombu==5.3.7
+      - labelme==5.5.0
+      - labelme2coco==0.2.6
+      - langchain==0.1.12
+      - langchain-community==0.0.28
+      - langchain-core==0.1.32
+      - langchain-text-splitters==0.0.1
+      - langcodes==3.4.0
+      - langdetect==1.0.9
+      - langsmith==0.1.27
+      - language-data==1.2.0
+      - lazy-loader==0.3
+      - lightgbm==4.2.0
+      - logutils==0.3.5
+      - lxml==5.1.0
+      - mako==1.3.5
+      - marisa-trie==1.2.0
+      - markdown==3.6
+      - markdown-it-py==3.0.0
+      - marshmallow==3.21.1
+      - matplotlib==3.8.2
+      - mdurl==0.1.2
+      - mediapipe==0.10.21
+      - mistral==18.0.1
+      - mistral-lib==3.0.0
+      - mistralai==0.4.1
+      - ml-dtypes==0.5.1
+      - msgpack==1.0.8
+      - multidict==6.0.5
+      - multiprocess==0.70.16
+      - munch==4.0.0
+      - murmurhash==1.0.10
+      - myanmartools==1.2.1
+      - mypy-extensions==1.0.0
+      - natsort==8.4.0
+      - nbformat==5.9.2
+      - netaddr==1.3.0
+      - netifaces==0.11.0
+      - nltk==3.8.1
+      - nvidia-cublas-cu12==12.4.5.8
+      - nvidia-cuda-cupti-cu12==12.4.127
+      - nvidia-cuda-nvrtc-cu12==12.4.127
+      - nvidia-cuda-runtime-cu12==12.4.127
+      - nvidia-cudnn-cu12==9.1.0.70
+      - nvidia-cufft-cu12==11.2.1.3
+      - nvidia-curand-cu12==10.3.5.147
+      - nvidia-cusolver-cu12==11.6.1.9
+      - nvidia-cusparse-cu12==12.3.1.170
+      - nvidia-cusparselt-cu12==0.6.2
+      - nvidia-nccl-cu12==2.21.5
+      - nvidia-nvjitlink-cu12==12.4.127
+      - nvidia-nvtx-cu12==12.4.127
+      - oauthlib==3.2.2
+      - omegaconf==2.3.0
+      - onnxruntime==1.19.0
+      - openai==0.28.0
+      - opencv-contrib-python==4.11.0.86
+      - opencv-python==4.9.0.80
+      - openpyxl==3.1.2
+      - opt-einsum==3.4.0
+      - optuna==3.6.1
+      - orjson==3.9.15
+      - os-service-types==1.7.0
+      - oslo-cache==3.7.0
+      - oslo-concurrency==6.0.0
+      - oslo-config==9.4.0
+      - oslo-context==5.5.0
+      - oslo-db==15.1.0
+      - oslo-i18n==6.3.0
+      - oslo-log==6.0.0
+      - oslo-messaging==14.8.0
+      - oslo-metrics==0.8.0
+      - oslo-middleware==6.1.0
+      - oslo-policy==4.3.0
+      - oslo-serialization==5.4.0
+      - oslo-service==3.5.0
+      - oslo-utils==7.1.0
+      - osprofiler==4.1.0
+      - outcome==1.3.0.post0
+      - pandas==2.2.0
+      - paramiko==3.4.0
+      - parse==1.20.1
+      - paste==3.10.1
+      - pastedeploy==3.1.0
+      - pathspec==0.12.1
+      - pbr==6.0.0
+      - pdf2image==1.17.0
+      - pecan==1.5.1
+      - pillow==11.1.0
+      - plotly==5.18.0
+      - pluggy==0.3.1
+      - plum-dispatch==1.7.4
+      - ply==3.11
+      - polars==0.20.23
+      - portalocker==2.8.2
+      - preshed==3.0.9
+      - pretrainedmodels==0.7.4
+      - prettytable==3.10.0
+      - prometheus-client==0.20.0
+      - proto-plus==1.25.0
+      - protobuf==4.25.6
+      - py==1.11.0
+      - pyarrow==15.0.1
+      - pyarrow-hotfix==0.6
+      - pyasn1==0.5.1
+      - pyasn1-modules==0.4.1
+      - pybboxes==0.1.6
+      - pybind11==2.12.0
+      - pycadf==3.1.1
+      - pycocotools==2.0.7
+      - pycryptodomex==3.21.0
+      - pydantic==2.6.3
+      - pydantic-core==2.16.3
+      - pydub==0.25.1
+      - pyee==8.2.2
+      - pyheif==0.7.1
+      - pyicu==2.13.1
+      - pyidaungsu==0.1.4
+      - pyjwt==2.8.0
+      - pymupdf==1.24.5
+      - pymupdfb==1.24.3
+      - pynacl==1.5.0
+      - pynput==1.7.6
+      - pyparsing==3.1.1
+      - pypdf==4.1.0
+      - pypdf2==3.0.1
+      - pyppeteer==1.0.2
+      - pyproj==3.6.1
+      - pyqt5==5.15.11
+      - pyqt5-qt5==5.15.14
+      - pyqt5-sip==12.15.0
+      - pyquery==2.0.0
+      - pyshark==0.6
+      - pyshp==2.3.1
+      - pytesseract==0.3.10
+      - python-crfsuite==0.9.10
+      - python-docx==1.1.2
+      - python-dotenv==1.0.1
+      - python-graphviz==0.20.1
+      - python-keystoneclient==5.4.0
+      - python-multipart==0.0.12
+      - python-xlib==0.33
+      - pytz==2023.3.post1
+      - qtpy==2.4.1
+      - qudida==0.0.4
+      - rabbit==1.2.0
+      - referencing==0.33.0
+      - regex==2023.12.25
+      - repoze-lru==0.7
+      - requests==2.32.3
+      - requests-html==0.10.0
+      - requests-oauthlib==1.3.1
+      - rfc3986==2.0.0
+      - rich==13.7.1
+      - routes==2.5.1
+      - rpds-py==0.18.0
+      - rsa==4.9
+      - ruff==0.6.5
+      - safehttpx==0.1.1
+      - safetensors==0.4.1
+      - sahi==0.11.18
+      - scikit-image==0.22.0
+      - scikit-learn==1.4.0
+      - scipy==1.11.4
+      - seaborn==0.13.1
+      - segmentation-models-pytorch==0.3.3
+      - selenium==4.24.0
+      - selenium-wire==5.1.0
+      - semantic-version==2.10.0
+      - sentence-transformers==3.0.1
+      - sentencepiece==0.2.0
+      - shapely==2.0.2
+      - shellingham==1.5.4
+      - simplegeneric==0.8.1
+      - smart-open==7.0.4
+      - sniffio==1.3.0
+      - sortedcontainers==2.4.0
+      - sounddevice==0.5.1
+      - soupsieve==2.5
+      - spacy==3.7.5
+      - spacy-legacy==3.0.12
+      - spacy-loggers==1.0.5
+      - spire-doc==12.4.0
+      - sqlalchemy==2.0.28
+      - srsly==2.4.8
+      - starlette==0.41.2
+      - statsd==4.0.1
+      - stevedore==5.2.0
+      - super-image==0.1.7
+      - sympy==1.13.1
+      - tabpfn==0.1.10
+      - tabulate==0.9.0
+      - tenacity==8.2.3
+      - tensorboard==2.16.2
+      - tensorboard-data-server==0.7.2
+      - termcolor==2.4.0
+      - terminaltables==3.1.10
+      - testresources==2.0.1
+      - testscenarios==0.5.0
+      - testtools==2.7.2
+      - thinc==8.2.5
+      - thop==0.1.1-2209072238
+      - threadpoolctl==3.2.0
+      - tifffile==2024.2.12
+      - tika==2.6.0
+      - timm==0.9.2
+      - tokenizers==0.20.1
+      - tomlkit==0.12.0
+      - tooz==6.2.0
+      - torch==2.6.0
+      - torchvision==0.21.0
+      - tox==2.2.1
+      - tqdm==4.66.1
+      - transformers==4.46.1
+      - trio==0.24.0
+      - trio-websocket==0.11.1
+      - triton==3.2.0
+      - tweepy==4.14.0
+      - typer==0.12.3
+      - typing-inspect==0.9.0
+      - tzdata==2023.4
+      - tzlocal==5.2
+      - urllib3-secure-extra==0.1.0
+      - uvicorn==0.27.1
+      - uvloop==0.19.0
+      - vine==5.1.0
+      - virtualenv==20.26.1
+      - voluptuous==0.15.1
+      - w3lib==2.1.2
+      - warcio==1.7.4
+      - wasabi==1.1.3
+      - watchfiles==0.21.0
+      - weasel==0.4.1
+      - webdriver-manager==3.2.2
+      - webob==1.8.7
+      - websocket-client==1.8.0
+      - websockets==10.4
+      - werkzeug==3.0.1
+      - wikipedia==1.4.0
+      - wrapt==1.16.0
+      - wsme==0.12.1
+      - wsproto==1.2.0
+      - xgboost==2.0.3
+      - xxhash==3.4.1
+      - yacs==0.1.8
+      - yappi==1.6.0
+      - yaql==3.0.0
+      - yarl==1.9.4
+      - zstandard==0.22.0
+prefix: /home/myominhtet/anaconda3/envs/myominhtet

export.py

@@ -0,0 +1,205 @@
+import argparse
+import sys
+import time
+import warnings
+
+sys.path.append('./')  # to run '$ python *.py' files in subdirectories
+
+import torch
+import torch.nn as nn
+from torch.utils.mobile_optimizer import optimize_for_mobile
+
+import models
+from models.experimental import attempt_load, End2End
+from utils.activations import Hardswish, SiLU
+from utils.general import set_logging, check_img_size
+from utils.torch_utils import select_device
+from utils.add_nms import RegisterNMS
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default='./yolor-csp-c.pt', help='weights path')
+    parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size')  # height, width
+    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+    parser.add_argument('--dynamic', action='store_true', help='dynamic ONNX axes')
+    parser.add_argument('--dynamic-batch', action='store_true', help='dynamic batch onnx for tensorrt and onnx-runtime')
+    parser.add_argument('--grid', action='store_true', help='export Detect() layer grid')
+    parser.add_argument('--end2end', action='store_true', help='export end2end onnx')
+    parser.add_argument('--max-wh', type=int, default=None, help='None for tensorrt nms, int value for onnx-runtime nms')
+    parser.add_argument('--topk-all', type=int, default=100, help='topk objects for every images')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='iou threshold for NMS')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='conf threshold for NMS')
+    parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--simplify', action='store_true', help='simplify onnx model')
+    parser.add_argument('--include-nms', action='store_true', help='export end2end onnx')
+    parser.add_argument('--fp16', action='store_true', help='CoreML FP16 half-precision export')
+    parser.add_argument('--int8', action='store_true', help='CoreML INT8 quantization')
+    opt = parser.parse_args()
+    opt.img_size *= 2 if len(opt.img_size) == 1 else 1  # expand
+    opt.dynamic = opt.dynamic and not opt.end2end
+    opt.dynamic = False if opt.dynamic_batch else opt.dynamic
+    print(opt)
+    set_logging()
+    t = time.time()
+
+    # Load PyTorch model
+    device = select_device(opt.device)
+    model = attempt_load(opt.weights, map_location=device)  # load FP32 model
+    labels = model.names
+
+    # Checks
+    gs = int(max(model.stride))  # grid size (max stride)
+    opt.img_size = [check_img_size(x, gs) for x in opt.img_size]  # verify img_size are gs-multiples
+
+    # Input
+    img = torch.zeros(opt.batch_size, 3, *opt.img_size).to(device)  # image size(1,3,320,192) iDetection
+
+    # Update model
+    for k, m in model.named_modules():
+        m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatibility
+        if isinstance(m, models.common.Conv):  # assign export-friendly activations
+            if isinstance(m.act, nn.Hardswish):
+                m.act = Hardswish()
+            elif isinstance(m.act, nn.SiLU):
+                m.act = SiLU()
+        # elif isinstance(m, models.yolo.Detect):
+        #     m.forward = m.forward_export  # assign forward (optional)
+    model.model[-1].export = not opt.grid  # set Detect() layer grid export
+    y = model(img)  # dry run
+    if opt.include_nms:
+        model.model[-1].include_nms = True
+        y = None
+
+    # TorchScript export
+    try:
+        print('\nStarting TorchScript export with torch %s...' % torch.__version__)
+        f = opt.weights.replace('.pt', '.torchscript.pt')  # filename
+        ts = torch.jit.trace(model, img, strict=False)
+        ts.save(f)
+        print('TorchScript export success, saved as %s' % f)
+    except Exception as e:
+        print('TorchScript export failure: %s' % e)
+
+    # CoreML export
+    try:
+        import coremltools as ct
+
+        print('\nStarting CoreML export with coremltools %s...' % ct.__version__)
+        # convert model from torchscript and apply pixel scaling as per detect.py
+        ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
+        bits, mode = (8, 'kmeans_lut') if opt.int8 else (16, 'linear') if opt.fp16 else (32, None)
+        if bits < 32:
+            if sys.platform.lower() == 'darwin':  # quantization only supported on macOS
+                with warnings.catch_warnings():
+                    warnings.filterwarnings("ignore", category=DeprecationWarning)  # suppress numpy==1.20 float warning
+                    ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode)
+            else:
+                print('quantization only supported on macOS, skipping...')
+
+        f = opt.weights.replace('.pt', '.mlmodel')  # filename
+        ct_model.save(f)
+        print('CoreML export success, saved as %s' % f)
+    except Exception as e:
+        print('CoreML export failure: %s' % e)
+                     
+    # TorchScript-Lite export
+    try:
+        print('\nStarting TorchScript-Lite export with torch %s...' % torch.__version__)
+        f = opt.weights.replace('.pt', '.torchscript.ptl')  # filename
+        tsl = torch.jit.trace(model, img, strict=False)
+        tsl = optimize_for_mobile(tsl)
+        tsl._save_for_lite_interpreter(f)
+        print('TorchScript-Lite export success, saved as %s' % f)
+    except Exception as e:
+        print('TorchScript-Lite export failure: %s' % e)
+
+    # ONNX export
+    try:
+        import onnx
+
+        print('\nStarting ONNX export with onnx %s...' % onnx.__version__)
+        f = opt.weights.replace('.pt', '.onnx')  # filename
+        model.eval()
+        output_names = ['classes', 'boxes'] if y is None else ['output']
+        dynamic_axes = None
+        if opt.dynamic:
+            dynamic_axes = {'images': {0: 'batch', 2: 'height', 3: 'width'},  # size(1,3,640,640)
+             'output': {0: 'batch', 2: 'y', 3: 'x'}}
+        if opt.dynamic_batch:
+            opt.batch_size = 'batch'
+            dynamic_axes = {
+                'images': {
+                    0: 'batch',
+                }, }
+            if opt.end2end and opt.max_wh is None:
+                output_axes = {
+                    'num_dets': {0: 'batch'},
+                    'det_boxes': {0: 'batch'},
+                    'det_scores': {0: 'batch'},
+                    'det_classes': {0: 'batch'},
+                }
+            else:
+                output_axes = {
+                    'output': {0: 'batch'},
+                }
+            dynamic_axes.update(output_axes)
+        if opt.grid:
+            if opt.end2end:
+                print('\nStarting export end2end onnx model for %s...' % 'TensorRT' if opt.max_wh is None else 'onnxruntime')
+                model = End2End(model,opt.topk_all,opt.iou_thres,opt.conf_thres,opt.max_wh,device,len(labels))
+                if opt.end2end and opt.max_wh is None:
+                    output_names = ['num_dets', 'det_boxes', 'det_scores', 'det_classes']
+                    shapes = [opt.batch_size, 1, opt.batch_size, opt.topk_all, 4,
+                              opt.batch_size, opt.topk_all, opt.batch_size, opt.topk_all]
+                else:
+                    output_names = ['output']
+            else:
+                model.model[-1].concat = True
+
+        torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'],
+                          output_names=output_names,
+                          dynamic_axes=dynamic_axes)
+
+        # Checks
+        onnx_model = onnx.load(f)  # load onnx model
+        onnx.checker.check_model(onnx_model)  # check onnx model
+
+        if opt.end2end and opt.max_wh is None:
+            for i in onnx_model.graph.output:
+                for j in i.type.tensor_type.shape.dim:
+                    j.dim_param = str(shapes.pop(0))
+
+        # print(onnx.helper.printable_graph(onnx_model.graph))  # print a human readable model
+
+        # # Metadata
+        # d = {'stride': int(max(model.stride))}
+        # for k, v in d.items():
+        #     meta = onnx_model.metadata_props.add()
+        #     meta.key, meta.value = k, str(v)
+        # onnx.save(onnx_model, f)
+
+        if opt.simplify:
+            try:
+                import onnxsim
+
+                print('\nStarting to simplify ONNX...')
+                onnx_model, check = onnxsim.simplify(onnx_model)
+                assert check, 'assert check failed'
+            except Exception as e:
+                print(f'Simplifier failure: {e}')
+
+        # print(onnx.helper.printable_graph(onnx_model.graph))  # print a human readable model
+        onnx.save(onnx_model,f)
+        print('ONNX export success, saved as %s' % f)
+
+        if opt.include_nms:
+            print('Registering NMS plugin for ONNX...')
+            mo = RegisterNMS(f)
+            mo.register_nms()
+            mo.save(f)
+
+    except Exception as e:
+        print('ONNX export failure: %s' % e)
+
+    # Finish
+    print('\nExport complete (%.2fs). Visualize with https://github.com/lutzroeder/netron.' % (time.time() - t))

hubconf.py

@@ -0,0 +1,97 @@
+"""PyTorch Hub models
+
+Usage:
+    import torch
+    model = torch.hub.load('repo', 'model')
+"""
+
+from pathlib import Path
+
+import torch
+
+from models.yolo import Model
+from utils.general import check_requirements, set_logging
+from utils.google_utils import attempt_download
+from utils.torch_utils import select_device
+
+dependencies = ['torch', 'yaml']
+check_requirements(Path(__file__).parent / 'requirements.txt', exclude=('pycocotools', 'thop'))
+set_logging()
+
+
+def create(name, pretrained, channels, classes, autoshape):
+    """Creates a specified model
+
+    Arguments:
+        name (str): name of model, i.e. 'yolov7'
+        pretrained (bool): load pretrained weights into the model
+        channels (int): number of input channels
+        classes (int): number of model classes
+
+    Returns:
+        pytorch model
+    """
+    try:
+        cfg = list((Path(__file__).parent / 'cfg').rglob(f'{name}.yaml'))[0]  # model.yaml path
+        model = Model(cfg, channels, classes)
+        if pretrained:
+            fname = f'{name}.pt'  # checkpoint filename
+            attempt_download(fname)  # download if not found locally
+            ckpt = torch.load(fname, map_location=torch.device('cpu'))  # load
+            msd = model.state_dict()  # model state_dict
+            csd = ckpt['model'].float().state_dict()  # checkpoint state_dict as FP32
+            csd = {k: v for k, v in csd.items() if msd[k].shape == v.shape}  # filter
+            model.load_state_dict(csd, strict=False)  # load
+            if len(ckpt['model'].names) == classes:
+                model.names = ckpt['model'].names  # set class names attribute
+            if autoshape:
+                model = model.autoshape()  # for file/URI/PIL/cv2/np inputs and NMS
+        device = select_device('0' if torch.cuda.is_available() else 'cpu')  # default to GPU if available
+        return model.to(device)
+
+    except Exception as e:
+        s = 'Cache maybe be out of date, try force_reload=True.'
+        raise Exception(s) from e
+
+
+def custom(path_or_model='path/to/model.pt', autoshape=True):
+    """custom mode
+
+    Arguments (3 options):
+        path_or_model (str): 'path/to/model.pt'
+        path_or_model (dict): torch.load('path/to/model.pt')
+        path_or_model (nn.Module): torch.load('path/to/model.pt')['model']
+
+    Returns:
+        pytorch model
+    """
+    model = torch.load(path_or_model, map_location=torch.device('cpu')) if isinstance(path_or_model, str) else path_or_model  # load checkpoint
+    if isinstance(model, dict):
+        model = model['ema' if model.get('ema') else 'model']  # load model
+
+    hub_model = Model(model.yaml).to(next(model.parameters()).device)  # create
+    hub_model.load_state_dict(model.float().state_dict())  # load state_dict
+    hub_model.names = model.names  # class names
+    if autoshape:
+        hub_model = hub_model.autoshape()  # for file/URI/PIL/cv2/np inputs and NMS
+    device = select_device('0' if torch.cuda.is_available() else 'cpu')  # default to GPU if available
+    return hub_model.to(device)
+
+
+def yolov7(pretrained=True, channels=3, classes=80, autoshape=True):
+    return create('yolov7', pretrained, channels, classes, autoshape)
+
+
+if __name__ == '__main__':
+    model = custom(path_or_model='yolov7.pt')  # custom example
+    # model = create(name='yolov7', pretrained=True, channels=3, classes=80, autoshape=True)  # pretrained example
+
+    # Verify inference
+    import numpy as np
+    from PIL import Image
+
+    imgs = [np.zeros((640, 480, 3))]
+
+    results = model(imgs)  # batched inference
+    results.print()
+    results.save()

interfacetest2.py

@@ -0,0 +1,223 @@
+import argparse
+import time
+from pathlib import Path
+import os
+import cv2
+import torch
+import torch.backends.cudnn as cudnn
+from numpy import random
+import numpy as np
+from models.experimental import attempt_load
+from utils.datasets import LoadImages
+from utils.general import check_img_size, non_max_suppression, scale_coords, set_logging, increment_path
+from utils.plots import plot_one_box
+from utils.torch_utils import select_device, time_synchronized
+import gradio as gr
+import ffmpeg
+from fastapi import FastAPI, Request
+from starlette.responses import HTMLResponse
+import uvicorn
+def convert_to_h264(input_path):
+    # Construct output path manually by appending '_h264' before the extension
+    output_path = str(Path(input_path).with_suffix('')) + "_h264.mp4"
+    try:
+        stream = ffmpeg.input(input_path)
+        stream = ffmpeg.output(stream, output_path, vcodec='libx264', acodec='aac', format='mp4', pix_fmt='yuv420p')
+        ffmpeg.run(stream, overwrite_output=True)
+        return output_path
+    except ffmpeg.Error as e:
+        print(f"FFmpeg conversion error: {e.stderr.decode()}")
+        return input_path
+
+# IoU and scanner movement functions (unchanged)
+def compute_iou(box1, box2):
+    x1, y1, x2, y2 = box1
+    x1_, y1_, x2_, y2_ = box2
+    xi1 = max(x1, x1_)
+    yi1 = max(y1, y1_)
+    xi2 = min(x2, x2_)
+    yi2 = min(y2, y2_)
+    inter_width = max(0, xi2 - xi1)
+    inter_height = max(0, yi2 - yi1)
+    inter_area = inter_width * inter_height
+    box1_area = (x2 - x1) * (y2 - y1)
+    box2_area = (x2_ - x1_) * (y2_ - y1_)
+    union_area = box1_area + box2_area - inter_area
+    return inter_area / union_area if union_area != 0 else 0.0
+
+def is_scanner_moving(prev_centroids, curr_box, scanner_id, threshold=5.0):
+    x1, y1, x2, y2 = curr_box
+    curr_centroid = ((x1 + x2) / 2, (y1 + y2) / 2)
+    if scanner_id in prev_centroids:
+        prev_x, prev_y = prev_centroids[scanner_id]
+        distance = np.sqrt((curr_centroid[0] - prev_x)**2 + (curr_centroid[1] - prev_y)**2)
+        return distance > threshold
+    return False
+
+def detect_video(video_path, weights, conf_thres=0.25, iou_thres=0.45, img_size=640, device='', save_dir='runs/detect/exp'):
+    save_dir = Path(increment_path(Path(save_dir), exist_ok=True))
+    save_dir.mkdir(parents=True, exist_ok=True)
+    
+    set_logging()
+    device = select_device(device)
+    half = device.type != 'cpu'
+    model = attempt_load(weights, map_location=device)
+    stride = int(model.stride.max())
+    imgsz = check_img_size(img_size, s=stride)
+    if half:
+        model.half()
+
+    dataset = LoadImages(video_path, img_size=imgsz, stride=stride)
+    names = model.module.names if hasattr(model, 'module') else model.names
+    colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
+
+    vid_path, vid_writer = None, None
+    prev_centroids = {}
+    scanner_id_counter = 0
+
+    for path, img, im0s, vid_cap in dataset:
+        img = torch.from_numpy(img).to(device)
+        img = img.half() if half else img.float()
+        img /= 255.0
+        if img.ndimension() == 3:
+            img = img.unsqueeze(0)
+
+        with torch.no_grad():
+            pred = model(img)[0]
+        pred = non_max_suppression(pred, conf_thres, iou_thres)
+
+        for i, det in enumerate(pred):
+            p = Path(path)
+            save_path = str(save_dir / p.name.replace('.mp4', '_output.mp4'))
+            im0 = im0s
+
+            if len(det):
+                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
+                item_boxes, scanner_data, phone_boxes = [], [], []
+                curr_scanner_boxes = []
+
+                for *xyxy, conf, cls in det:
+                    x1, y1, x2, y2 = map(int, xyxy)
+                    class_name = names[int(cls)]
+                    color = colors[int(cls)]
+                    if class_name.lower() == "item":
+                        item_boxes.append([x1, y1, x2, y2])
+                    elif class_name.lower() == "phone":
+                        phone_boxes.append([x1, y1, x2, y2])
+                    elif class_name.lower() == "scanner":
+                        curr_scanner_boxes.append([x1, y1, x2, y2])
+                    plot_one_box(xyxy, im0, label=class_name, color=color, line_thickness=2)
+
+                new_prev_centroids = {}
+                if prev_centroids and curr_scanner_boxes:
+                    for curr_box in curr_scanner_boxes:
+                        curr_centroid = ((curr_box[0] + curr_box[2]) / 2, (curr_box[1] + curr_box[3]) / 2)
+                        best_match_id = min(prev_centroids.keys(), 
+                                          key=lambda k: np.sqrt((curr_centroid[0] - prev_centroids[k][0])**2 + 
+                                                                (curr_centroid[1] - prev_centroids[k][1])**2), 
+                                          default=None)
+                        if best_match_id is not None and np.sqrt((curr_centroid[0] - prev_centroids[best_match_id][0])**2 + 
+                                                                 (curr_centroid[1] - prev_centroids[best_match_id][1])**2) < 50:
+                            scanner_id = best_match_id
+                        else:
+                            scanner_id = scanner_id_counter
+                            scanner_id_counter += 1
+                        is_moving = is_scanner_moving(prev_centroids, curr_box, scanner_id)
+                        movement_status = "Scanning" if is_moving else "Idle"
+                        scanner_data.append([curr_box, movement_status, scanner_id])
+                        new_prev_centroids[scanner_id] = curr_centroid
+                elif curr_scanner_boxes:
+                    for curr_box in curr_scanner_boxes:
+                        scanner_id = scanner_id_counter
+                        scanner_id_counter += 1
+                        movement_status = "Idle"
+                        curr_centroid = ((curr_box[0] + curr_box[2]) / 2, (curr_box[1] + curr_box[3]) / 2)
+                        scanner_data.append([curr_box, movement_status, scanner_id])
+                        new_prev_centroids[scanner_id] = curr_centroid
+
+                prev_centroids = new_prev_centroids
+
+                for scanner_box, movement_status, scanner_id in scanner_data:
+                    x1, y1, x2, y2 = scanner_box
+                    label = f"scanner {movement_status} (ID: {scanner_id})"
+                    plot_one_box([x1, y1, x2, y2], im0, label=label, color=colors[names.index("scanner")], line_thickness=2)
+
+                product_scanning_status = ""
+                payment_scanning_status = ""
+                for scanner_box, movement_status, _ in scanner_data:
+                    for item_box in item_boxes:
+                        if movement_status == "Scanning" and compute_iou(scanner_box, item_box) > 0.1:
+                            product_scanning_status = "Product scanning is finished"
+                    for phone_box in phone_boxes:
+                        if movement_status == "Scanning" and compute_iou(scanner_box, phone_box) > 0.1:
+                            payment_scanning_status = "Payment scanning is finished"
+
+                if product_scanning_status:
+                    cv2.putText(im0, product_scanning_status, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.9, colors[names.index("scanner")], 2)
+                if payment_scanning_status:
+                    cv2.putText(im0, payment_scanning_status, (10, 60), cv2.FONT_HERSHEY_SIMPLEX, 0.9, colors[names.index("scanner")], 2)
+
+            if vid_path != save_path:
+                vid_path = save_path
+                if isinstance(vid_writer, cv2.VideoWriter):
+                    vid_writer.release()
+                fps = vid_cap.get(cv2.CAP_PROP_FPS) if vid_cap else 30
+                w, h = im0.shape[1], im0.shape[0]
+                vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+            vid_writer.write(im0)
+
+    if isinstance(vid_writer, cv2.VideoWriter):
+        vid_writer.release()
+
+    # Convert to H.264 for browser compatibility
+    output_h264 = str(Path(save_path).with_name(f"{Path(save_path).stem}_h264.mp4"))
+    try:
+        stream = ffmpeg.input(save_path)
+        stream = ffmpeg.output(stream, output_h264, vcodec='libx264', acodec='aac', format='mp4', pix_fmt='yuv420p')
+        ffmpeg.run(stream, overwrite_output=True)
+        os.remove(save_path)  # Remove original
+        return output_h264
+    except ffmpeg.Error as e:
+        print(f"FFmpeg error: {e.stderr.decode()}")
+        return save_path
+
+def gradio_interface(video, conf_thres, iou_thres):
+    weights = "/home/myominhtet/Desktop/deepsortfromscratch/yolov7/best.pt"
+    img_size = 640
+    video = convert_to_h264(video)
+    output_video = detect_video(video, weights, conf_thres, iou_thres, img_size)
+    return output_video if output_video else "Error processing video."
+
+# Create Gradio interface
+interface = gr.Interface(
+    fn=gradio_interface,
+    inputs=[
+        gr.Video(label="Upload Video"),
+        gr.Slider(0, 1, value=0.25, step=0.05, label="Confidence Threshold"),
+        gr.Slider(0, 1, value=0.45, step=0.05, label="IoU Threshold"),
+    ],
+    outputs=gr.Video(label="Processed Video"),
+    title="YOLO Video Detection",
+    description="Upload a video to run YOLO detection with custom parameters."
+)
+
+# Initialize FastAPI app
+app = FastAPI()
+
+# Mount Gradio interface to FastAPI
+app = gr.mount_gradio_app(app, interface, path="/gradio")
+
+# Optional: Add a simple root endpoint
+@app.get("/", response_class=HTMLResponse)
+async def root():
+    return """
+    <html>
+        <body>
+            <h1>Welcome to YOLO Video Detection API</h1>
+            <p>Visit <a href="/gradio">/gradio</a> to access the interactive UI.</p>
+        </body>
+    </html>
+    """
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=8000)

models/__init__.py

@@ -0,0 +1 @@
+# init