Add files

.gitattributes

@@ -1,3 +1,5 @@
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+mmdet_configs/configs

.pre-commit-config.yaml

@@ -0,0 +1,46 @@
+exclude: ^mmdet_configs/configs/
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.2.0
+  hooks:
+  - id: check-executables-have-shebangs
+  - id: check-json
+  - id: check-merge-conflict
+  - id: check-shebang-scripts-are-executable
+  - id: check-toml
+  - id: check-yaml
+  - id: double-quote-string-fixer
+  - id: end-of-file-fixer
+  - id: mixed-line-ending
+    args: ['--fix=lf']
+  - id: requirements-txt-fixer
+  - id: trailing-whitespace
+- repo: https://github.com/myint/docformatter
+  rev: v1.4
+  hooks:
+  - id: docformatter
+    args: ['--in-place']
+- repo: https://github.com/pycqa/isort
+  rev: 5.10.1
+  hooks:
+    - id: isort
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v0.812
+  hooks:
+    - id: mypy
+      args: ['--ignore-missing-imports']
+- repo: https://github.com/google/yapf
+  rev: v0.32.0
+  hooks:
+  - id: yapf
+    args: ['--parallel', '--in-place']
+- repo: https://github.com/kynan/nbstripout
+  rev: 0.5.0
+  hooks:
+    - id: nbstripout
+      args: ['--extra-keys', 'metadata.interpreter metadata.kernelspec cell.metadata.pycharm']
+- repo: https://github.com/nbQA-dev/nbQA
+  rev: 1.3.1
+  hooks:
+    - id: nbqa-isort
+    - id: nbqa-yapf

.style.yapf

@@ -0,0 +1,5 @@
+[style]
+based_on_style = pep8
+blank_line_before_nested_class_or_def = false
+spaces_before_comment = 2
+split_before_logical_operator = true

README.md

@@ -1,10 +1,11 @@
 ---
-title: Mmdetection Detection
+title: MMDetection
 emoji: 🔥
 colorFrom: pink
 colorTo: purple
 sdk: gradio
-sdk_version: 3.0.6
+python_version: 3.9.13
+sdk_version: 3.0.9
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,176 @@
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+import argparse
+import os
+import pathlib
+import subprocess
+import tarfile
+
+if os.getenv('SYSTEM') == 'spaces':
+    import mim
+
+    mim.uninstall('mmcv-full', confirm_yes=True)
+    mim.install('mmcv-full==1.5.2', is_yes=True)
+
+    subprocess.call('pip uninstall -y opencv-python'.split())
+    subprocess.call('pip uninstall -y opencv-python-headless'.split())
+    subprocess.call('pip install opencv-python-headless'.split())
+
+import gradio as gr
+
+from model import Model
+
+DEFAULT_MODEL_TYPE = 'detection'
+DEFAULT_MODEL_NAMES = {
+    'detection': 'YOLOX-l',
+    'instance_segmentation': 'QueryInst (R-50-FPN)',
+    'panoptic_segmentation': 'MaskFormer (R-50)',
+}
+DEFAULT_MODEL_NAME = DEFAULT_MODEL_NAMES[DEFAULT_MODEL_TYPE]
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--device', type=str, default='cpu')
+    parser.add_argument('--theme', type=str)
+    parser.add_argument('--share', action='store_true')
+    parser.add_argument('--port', type=int)
+    parser.add_argument('--disable-queue',
+                        dest='enable_queue',
+                        action='store_false')
+    return parser.parse_args()
+
+
+def extract_tar() -> None:
+    if pathlib.Path('mmdet_configs/configs').exists():
+        return
+    with tarfile.open('mmdet_configs/configs.tar') as f:
+        f.extractall('mmdet_configs')
+
+
+def update_model_name(model_type: str) -> dict:
+    model_dict = getattr(Model, f'{model_type.upper()}_MODEL_DICT')
+    model_names = list(model_dict.keys())
+    model_name = DEFAULT_MODEL_NAMES[model_type]
+    return gr.Dropdown.update(choices=model_names, value=model_name)
+
+
+def update_visualization_score_threshold(model_type: str) -> dict:
+    return gr.Slider.update(visible=model_type != 'panoptic_segmentation')
+
+
+def update_redraw_button(model_type: str) -> dict:
+    return gr.Button.update(visible=model_type != 'panoptic_segmentation')
+
+
+def set_example_image(example: list) -> dict:
+    return gr.Image.update(value=example[0])
+
+
+def main():
+    args = parse_args()
+
+    extract_tar()
+    model = Model(DEFAULT_MODEL_NAME, args.device)
+
+    css = '''
+h1#title {
+  text-align: center;
+}
+img#overview {
+  max-width: 1000px;
+  max-height: 600px;
+}
+'''
+
+    with gr.Blocks(theme=args.theme, css=css) as demo:
+        gr.Markdown('''<h1 id="title">MMDetection</h1>
+
+This is an unofficial demo for [https://github.com/open-mmlab/mmdetection](https://github.com/open-mmlab/mmdetection).
+<center><img id="overview" alt="overview" src="https://user-images.githubusercontent.com/12907710/137271636-56ba1cd2-b110-4812-8221-b4c120320aa9.png" /></center>
+''')
+
+        with gr.Row():
+            with gr.Column():
+                with gr.Row():
+                    input_image = gr.Image(label='Input Image', type='numpy')
+                with gr.Group():
+                    with gr.Row():
+                        model_type = gr.Radio(list(DEFAULT_MODEL_NAMES.keys()),
+                                              value=DEFAULT_MODEL_TYPE,
+                                              label='Model Type')
+                    with gr.Row():
+                        model_name = gr.Dropdown(list(
+                            model.DETECTION_MODEL_DICT.keys()),
+                                                 value=DEFAULT_MODEL_NAME,
+                                                 label='Model')
+                with gr.Row():
+                    run_button = gr.Button(value='Run')
+                    prediction_results = gr.Variable()
+            with gr.Column():
+                with gr.Row():
+                    visualization = gr.Image(label='Result', type='numpy')
+                with gr.Row():
+                    visualization_score_threshold = gr.Slider(
+                        0,
+                        1,
+                        step=0.05,
+                        value=0.3,
+                        label='Visualization Score Threshold')
+                with gr.Row():
+                    redraw_button = gr.Button(value='Redraw')
+
+        with gr.Row():
+            paths = sorted(pathlib.Path('images').rglob('*.jpg'))
+            example_images = gr.Dataset(components=[input_image],
+                                        samples=[[path.as_posix()]
+                                                 for path in paths])
+
+        gr.Markdown(
+            '<center><img src="https://visitor-badge.glitch.me/badge?page_id=hysts.mmdetection" alt="visitor badge"/></center>'
+        )
+
+        model_type.change(fn=update_model_name,
+                          inputs=[model_type],
+                          outputs=[model_name])
+        model_type.change(fn=update_visualization_score_threshold,
+                          inputs=[model_type],
+                          outputs=[visualization_score_threshold])
+        model_type.change(fn=update_redraw_button,
+                          inputs=[model_type],
+                          outputs=[redraw_button])
+
+        model_name.change(fn=model.set_model,
+                          inputs=[model_name],
+                          outputs=None)
+        run_button.click(fn=model.detect_and_visualize,
+                         inputs=[
+                             input_image,
+                             visualization_score_threshold,
+                         ],
+                         outputs=[
+                             prediction_results,
+                             visualization,
+                         ])
+        redraw_button.click(fn=model.visualize_detection_results,
+                            inputs=[
+                                input_image,
+                                prediction_results,
+                                visualization_score_threshold,
+                            ],
+                            outputs=[visualization])
+        example_images.click(fn=set_example_image,
+                             inputs=[example_images],
+                             outputs=[input_image])
+
+    demo.launch(
+        enable_queue=args.enable_queue,
+        server_port=args.port,
+        share=args.share,
+    )
+
+
+if __name__ == '__main__':
+    main()

images/README.md

@@ -0,0 +1,9 @@
+These images are freely-usable ones from https://www.pexels.com/.
+
+- https://www.pexels.com/photo/assorted-color-kittens-45170/
+- https://www.pexels.com/photo/white-wooden-kitchen-cabinet-1599791/
+- https://www.pexels.com/photo/assorted-books-on-book-shelves-1370295/
+- https://www.pexels.com/photo/pile-of-assorted-varieties-of-vegetables-2255935/
+- https://www.pexels.com/photo/sliced-fruits-on-tray-1132047/
+- https://www.pexels.com/photo/group-of-people-carrying-surfboards-1549196/
+- https://www.pexels.com/photo/aerial-photo-of-vehicles-in-the-city-1031698/

mmdet_configs/LICENSE

@@ -0,0 +1,203 @@
+Copyright 2018-2023 OpenMMLab. All rights reserved.
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2018-2023 OpenMMLab.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

mmdet_configs/README.md

@@ -0,0 +1,2 @@
+`configs.tar` is a tarball of https://github.com/open-mmlab/mmdetection/tree/v2.24.1/configs.
+The license file of the mmdetection is also included in this directory.

mmdet_configs/configs.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d2091e07da6b74a6cd694e895b653485f7ce9d5d17738a415ca77a56940b989
+size 3389440

model.py

@@ -0,0 +1,98 @@
+from __future__ import annotations
+
+import os
+
+import huggingface_hub
+import numpy as np
+import torch
+import torch.nn as nn
+import yaml
+from mmdet.apis import inference_detector, init_detector
+
+
+def _load_model_dict(path: str) -> dict[str, dict[str, str]]:
+    with open(path) as f:
+        dic = yaml.safe_load(f)
+    _update_config_path(dic)
+    _update_model_dict_if_hf_token_is_given(dic)
+    return dic
+
+
+def _update_config_path(model_dict: dict[str, dict[str, str]]) -> None:
+    for dic in model_dict.values():
+        dic['config'] = dic['config'].replace(
+            'https://github.com/open-mmlab/mmdetection/tree/master',
+            'mmdet_configs')
+
+
+def _update_model_dict_if_hf_token_is_given(
+        model_dict: dict[str, dict[str, str]]) -> None:
+    token = os.getenv('HF_TOKEN')
+    if token is None:
+        return
+
+    for dic in model_dict.values():
+        ckpt_path = dic['model']
+        name = ckpt_path.split('/')[-1]
+        ckpt_path = huggingface_hub.hf_hub_download('hysts/mmdetection',
+                                                    f'models/{name}',
+                                                    use_auth_token=token)
+        dic['model'] = ckpt_path
+
+
+class Model:
+    DETECTION_MODEL_DICT = _load_model_dict('model_dict/detection.yaml')
+    INSTANCE_SEGMENTATION_MODEL_DICT = _load_model_dict(
+        'model_dict/instance_segmentation.yaml')
+    PANOPTIC_SEGMENTATION_MODEL_DICT = _load_model_dict(
+        'model_dict/panoptic_segmentation.yaml')
+    MODEL_DICT = DETECTION_MODEL_DICT | INSTANCE_SEGMENTATION_MODEL_DICT | PANOPTIC_SEGMENTATION_MODEL_DICT
+
+    def __init__(self, model_name: str, device: str | torch.device):
+        self.device = torch.device(device)
+        self._load_all_models_once()
+        self.model = self._load_model(model_name)
+
+    def _load_all_models_once(self) -> None:
+        for name in self.MODEL_DICT:
+            self._load_model(name)
+
+    def _load_model(self, name: str) -> nn.Module:
+        dic = self.MODEL_DICT[name]
+        return init_detector(dic['config'], dic['model'], device=self.device)
+
+    def set_model(self, name: str) -> None:
+        self.model = self._load_model(name)
+
+    def detect_and_visualize(
+        self, image: np.ndarray, score_threshold: float
+    ) -> tuple[list[np.ndarray] | tuple[list[np.ndarray],
+                                        list[list[np.ndarray]]]
+               | dict[str, np.ndarray], np.ndarray]:
+        out = self.detect(image)
+        vis = self.visualize_detection_results(image, out, score_threshold)
+        return out, vis
+
+    def detect(
+        self, image: np.ndarray
+    ) -> list[np.ndarray] | tuple[
+            list[np.ndarray], list[list[np.ndarray]]] | dict[str, np.ndarray]:
+        image = image[:, :, ::-1]  # RGB -> BGR
+        out = inference_detector(self.model, image)
+        return out
+
+    def visualize_detection_results(
+            self,
+            image: np.ndarray,
+            detection_results: list[np.ndarray]
+        | tuple[list[np.ndarray], list[list[np.ndarray]]]
+        | dict[str, np.ndarray],
+            score_threshold: float = 0.3) -> np.ndarray:
+        image = image[:, :, ::-1]  # RGB -> BGR
+        vis = self.model.show_result(image,
+                                     detection_results,
+                                     score_thr=score_threshold,
+                                     bbox_color=None,
+                                     text_color=(200, 200, 200),
+                                     mask_color=None)
+        return vis[:, :, ::-1]  # BGR -> RGB

model_dict/detection.yaml

@@ -0,0 +1,42 @@
+Faster R-CNN (R-50-FPN):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_2x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_2x_coco/faster_rcnn_r50_fpn_2x_coco_bbox_mAP-0.384_20200504_210434-a5d8aa15.pth
+Faster R-CNN (X-101-64x4d-FPN):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_x101_64x4d_fpn_1x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_x101_64x4d_fpn_1x_coco/faster_rcnn_x101_64x4d_fpn_1x_coco_20200204-833ee192.pth
+SSD (VGG16):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/ssd/ssd512_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/ssd/ssd512_coco/ssd512_coco_20210803_022849-0a47a1ca.pth
+RetinaNet (X-101-64x4d-FPN):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/retinanet/retinanet_x101_64x4d_fpn_mstrain_640-800_3x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_x101_64x4d_fpn_mstrain_3x_coco/retinanet_x101_64x4d_fpn_mstrain_3x_coco_20210719_051838-022c2187.pth
+YOLOv3 (DarkNet-53 608):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/yolo/yolov3_d53_mstrain-608_273e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/yolo/yolov3_d53_mstrain-608_273e_coco/yolov3_d53_mstrain-608_273e_coco_20210518_115020-a2c3acb8.pth
+CornerNet (HourglassNet-104):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/cornernet/cornernet_hourglass104_mstest_10x5_210e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/cornernet/cornernet_hourglass104_mstest_10x5_210e_coco/cornernet_hourglass104_mstest_10x5_210e_coco_20200824_185720-5fefbf1c.pth
+FCOS (X-101):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/fcos/fcos_x101_64x4d_fpn_gn-head_mstrain_640-800_2x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/fcos/fcos_x101_64x4d_fpn_gn-head_mstrain_640-800_2x_coco/fcos_x101_64x4d_fpn_gn-head_mstrain_640-800_2x_coco-ede514a8.pth
+DETR:
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/detr/detr_r50_8x2_150e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/detr/detr_r50_8x2_150e_coco/detr_r50_8x2_150e_coco_20201130_194835-2c4b8974.pth
+YOLOX-tiny:
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/yolox/yolox_tiny_8x8_300e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_tiny_8x8_300e_coco/yolox_tiny_8x8_300e_coco_20211124_171234-b4047906.pth
+YOLOX-s:
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/yolox/yolox_s_8x8_300e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_s_8x8_300e_coco/yolox_s_8x8_300e_coco_20211121_095711-4592a793.pth
+YOLOX-l:
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/yolox/yolox_l_8x8_300e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_l_8x8_300e_coco/yolox_l_8x8_300e_coco_20211126_140236-d3bd2b23.pth
+YOLOX-x:
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/yolox/yolox_x_8x8_300e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_x_8x8_300e_coco/yolox_x_8x8_300e_coco_20211126_140254-1ef88d67.pth
+Deformable DETR (R-50 two-stage Deformable DETR):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/deformable_detr/deformable_detr_twostage_refine_r50_16x2_50e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/deformable_detr/deformable_detr_twostage_refine_r50_16x2_50e_coco/deformable_detr_twostage_refine_r50_16x2_50e_coco_20210419_220613-9d28ab72.pth
+TOOD (R-101-dcnv2):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/tood/tood_r101_fpn_dconv_c3-c5_mstrain_2x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/tood/tood_r101_fpn_dconv_c3-c5_mstrain_2x_coco/tood_r101_fpn_dconv_c3-c5_mstrain_2x_coco_20211210_213728-4a824142.pth

model_dict/instance_segmentation.yaml

@@ -0,0 +1,39 @@
+Mask R-CNN (R-50-FPN):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r50_fpn_mstrain-poly_3x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_mstrain-poly_3x_coco/mask_rcnn_r50_fpn_mstrain-poly_3x_coco_20210524_201154-21b550bb.pth
+Mask R-CNN (X-101-64x4d-FPN):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_x101_64x4d_fpn_mstrain-poly_3x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_64x4d_fpn_mstrain-poly_3x_coco/mask_rcnn_x101_64x4d_fpn_mstrain-poly_3x_coco_20210526_120447-c376f129.pth
+Cascade Mask R-CNN (X-101-64x4d-FPN):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_mstrain_3x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_mstrain_3x_coco/cascade_mask_rcnn_x101_64x4d_fpn_mstrain_3x_coco_20210719_210311-d3e64ba0.pth
+Mask Scoring R-CNN (R-X101-64x4d):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/ms_rcnn/ms_rcnn_x101_64x4d_fpn_1x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/ms_rcnn/ms_rcnn_x101_64x4d_fpn_1x_coco/ms_rcnn_x101_64x4d_fpn_1x_coco_20200206-86ba88d2.pth
+HTC (X-101-64x4d-FPN):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/htc/htc_x101_64x4d_fpn_16x1_20e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/htc/htc_x101_64x4d_fpn_16x1_20e_coco/htc_x101_64x4d_fpn_16x1_20e_coco_20200318-b181fd7a.pth
+YOLACT:
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/yolact/yolact_r50_1x8_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/yolact/yolact_r50_1x8_coco/yolact_r50_1x8_coco_20200908-f38d58df.pth
+Instaboost (Mask R-CNN (X-101-64x4d-FPN)):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/instaboost/mask_rcnn_x101_64x4d_fpn_instaboost_4x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/instaboost/mask_rcnn_x101_64x4d_fpn_instaboost_4x_coco/mask_rcnn_x101_64x4d_fpn_instaboost_4x_coco_20200515_080947-8ed58c1b.pth
+SOLO:
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/solo/solo_r50_fpn_3x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/solo/solo_r50_fpn_3x_coco/solo_r50_fpn_3x_coco_20210901_012353-11d224d7.pth
+PointRend (R-50-FPN):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/point_rend/point_rend_r50_caffe_fpn_mstrain_3x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/point_rend/point_rend_r50_caffe_fpn_mstrain_3x_coco/point_rend_r50_caffe_fpn_mstrain_3x_coco-e0ebb6b7.pth
+DetectoRS (HTC + ResNet-101):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/detectors/detectors_htc_r101_20e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/detectors/detectors_htc_r101_20e_coco/detectors_htc_r101_20e_coco_20210419_203638-348d533b.pth
+SCNet (X-101-64x4d-FPN):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/scnet/scnet_x101_64x4d_fpn_20e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/scnet/scnet_x101_64x4d_fpn_20e_coco/scnet_x101_64x4d_fpn_20e_coco-fb09dec9.pth
+QueryInst (R-50-FPN):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/queryinst/queryinst_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco/queryinst_r50_fpn_300_proposals_crop_mstrain_480-800_3x_coco_20210904_101802-85cffbd8.pth
+QueryInst (R-101-FPN):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/queryinst/queryinst_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/queryinst/queryinst_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco/queryinst_r101_fpn_300_proposals_crop_mstrain_480-800_3x_coco_20210904_153621-76cce59f.pth

model_dict/panoptic_segmentation.yaml

@@ -0,0 +1,9 @@
+Panoptic FPN (R-50-FPN):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/panoptic_fpn/panoptic_fpn_r50_fpn_mstrain_3x_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/panoptic_fpn/panoptic_fpn_r50_fpn_mstrain_3x_coco/panoptic_fpn_r50_fpn_mstrain_3x_coco_20210824_171155-5650f98b.pth
+MaskFormer (R-50):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/maskformer/maskformer_r50_mstrain_16x1_75e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/maskformer/maskformer_r50_mstrain_16x1_75e_coco/maskformer_r50_mstrain_16x1_75e_coco_20220221_141956-bc2699cb.pth
+MaskFormer (Swin-L):
+    config: https://github.com/open-mmlab/mmdetection/tree/master/configs/maskformer/maskformer_swin-l-p4-w12_mstrain_64x1_300e_coco.py
+    model: https://download.openmmlab.com/mmdetection/v2.0/maskformer/maskformer_swin-l-p4-w12_mstrain_64x1_300e_coco/maskformer_swin-l-p4-w12_mstrain_64x1_300e_coco_20220326_221612-061b4eb8.pth

requirements.txt

@@ -0,0 +1,7 @@
+mmcv-full==1.5.2
+mmdet==2.24.1
+numpy==1.22.4
+opencv-python-headless==4.5.5.64
+openmim==0.1.5
+torch==1.11.0
+torchvision==0.12.0