Alex Strick van Linschoten commited on
Commit
b0f2ac0
1 Parent(s): 8de9fe5

update app

Browse files
LICENSE ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "[]"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright [yyyy] [name of copyright owner]
190
+
191
+ Licensed under the Apache License, Version 2.0 (the "License");
192
+ you may not use this file except in compliance with the License.
193
+ You may obtain a copy of the License at
194
+
195
+ http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+ Unless required by applicable law or agreed to in writing, software
198
+ distributed under the License is distributed on an "AS IS" BASIS,
199
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+ See the License for the specific language governing permissions and
201
+ limitations under the License.
README.md CHANGED
@@ -1,13 +1 @@
1
- ---
2
- title: Redaction Detector
3
- emoji: 🔍
4
- colorFrom: yellow
5
- colorTo: purple
6
- sdk: streamlit
7
- sdk_version: 1.2.0
8
- app_file: app.py
9
- pinned: false
10
- license: apache-2.0
11
- ---
12
-
13
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference
 
1
+ # redaction-detector-streamlit
 
 
 
 
 
 
 
 
 
 
 
 
allsynthetic-imgsize768.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65362ca715c08973334b0488fb0cada234bff39a20cfa6a6d79eb111e744864e
3
+ size 131183383
app.py DELETED
@@ -1,4 +0,0 @@
1
- import streamlit as st
2
-
3
- x = st.slider('Select a value')
4
- st.write(x, 'squared is', x * x)
 
 
 
 
 
article.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ I've been working through the first two lessons of
2
+ [the fastai course](https://course.fast.ai/). For lesson one I trained a model
3
+ to recognise my cat, Mr Blupus. For lesson two the emphasis is on getting those
4
+ models out in the world as some kind of demo or application.
5
+ [Gradio](https://gradio.app) and
6
+ [Huggingface Spaces](https://huggingface.co/spaces) makes it super easy to get a
7
+ prototype of your model on the internet.
8
+
9
+ This MVP app runs two models to mimic the experience of what a final deployed
10
+ version of the project might look like.
11
+
12
+ - The first model (a classification model trained with fastai, available on the
13
+ Huggingface Hub
14
+ [here](https://huggingface.co/strickvl/redaction-classifier-fastai) and
15
+ testable as a standalone demo
16
+ [here](https://huggingface.co/spaces/strickvl/fastai_redaction_classifier)),
17
+ classifies and determines which pages of the PDF are redacted. I've written
18
+ about how I trained this model [here](https://mlops.systems/fastai/redactionmodel/computervision/datalabelling/2021/09/06/redaction-classification-chapter-2.html).
19
+ - The second model (an object detection model trained using [IceVision](https://airctic.com/) (itself
20
+ built partly on top of fastai)) detects which parts of the image are redacted.
21
+ This is a model I've been working on for a while and I described my process in
22
+ a series of blog posts (see below).
23
+
24
+ This MVP app does several things:
25
+
26
+ - it extracts any pages it considers to contain redactions and displays that
27
+ subset as an [image carousel](https://gradio.app/docs/#o_carousel). It also
28
+ displays some text alerting you to which specific pages were redacted.
29
+ - if you click the "Analyse and extract redacted images" checkbox, it will:
30
+ - pass the pages it considered redacted through the object detection model
31
+ - calculate what proportion of the total area of the image was redacted as
32
+ well as what proportion of the actual content (i.e. excluding margins etc
33
+ where there is no content)
34
+ - create a PDF that you can download that contains only the redacted images,
35
+ with an overlay of the redactions that it was able to identify along with
36
+ the confidence score for each item.
37
+
38
+ ## The Dataset
39
+
40
+ I downloaded a few thousand publicly-available FOIA documents from a government
41
+ website. I split the PDFs up into individual `.jpg` files and then used
42
+ [Prodigy](https://prodi.gy/) to annotate the data. (This process was described
43
+ in
44
+ [a blogpost written last
45
+ year](https://mlops.systems/fastai/redactionmodel/computervision/datalabelling/2021/09/06/redaction-classification-chapter-2.html).)
46
+ For the object detection model, the process was quite a bit more involved and I
47
+ direct you to the series of articles referenced below in the 'Further Reading' section.
48
+
49
+ ## Training the model
50
+
51
+ I trained the classification model with fastai's flexible `vision_learner`, fine-tuning
52
+ `resnet18` which was both smaller than `resnet34` (no surprises there) and less
53
+ liable to early overfitting. I trained the model for 10 epochs.
54
+
55
+ The object detection model is trained using IceVision, with VFNet as the
56
+ model and `resnet50` as the backbone. I trained the model for 50 epochs and
57
+ reached 89% accuracy on the validation data.
58
+
59
+ ## Further Reading
60
+
61
+ This initial dataset spurred an ongoing interest in the domain and I've since
62
+ been working on the problem of object detection, i.e. identifying exactly which
63
+ parts of the image contain redactions.
64
+
65
+ Some of the key blogs I've written about this project:
66
+
67
+ - How to annotate data for an object detection problem with Prodigy
68
+ ([link](https://mlops.systems/redactionmodel/computervision/datalabelling/2021/11/29/prodigy-object-detection-training.html))
69
+ - How to create synthetic images to supplement a small dataset
70
+ ([link](https://mlops.systems/redactionmodel/computervision/python/tools/2022/02/10/synthetic-image-data.html))
71
+ - How to use error analysis and visual tools like FiftyOne to improve model
72
+ performance
73
+ ([link](https://mlops.systems/redactionmodel/computervision/tools/debugging/jupyter/2022/03/12/fiftyone-computervision.html))
74
+ - Creating more synthetic data focused on the tasks my model finds hard
75
+ ([link](https://mlops.systems/tools/redactionmodel/computervision/2022/04/06/synthetic-data-results.html))
76
+ - Data validation for object detection / computer vision (a three part series —
77
+ [part 1](https://mlops.systems/tools/redactionmodel/computervision/datavalidation/2022/04/19/data-validation-great-expectations-part-1.html),
78
+ [part 2](https://mlops.systems/tools/redactionmodel/computervision/datavalidation/2022/04/26/data-validation-great-expectations-part-2.html),
79
+ [part 3](https://mlops.systems/tools/redactionmodel/computervision/datavalidation/2022/04/28/data-validation-great-expectations-part-3.html))
fastai-classification-model.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec0645d5b4428fa3da139e9138653657bb7b1fcad2a138937dcdeb5bb51cf0c
3
+ size 87496043
packages.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ python3-opencv
2
+ python-tk
requirements.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ --find-links https://download.openmmlab.com/mmcv/dist/cpu/torch1.10.0/index.html
2
+ mmcv-full==1.3.17
3
+ mmdet==2.17.0
4
+ gradio==2.7.5
5
+ icevision[all]==0.12.0
6
+
7
+ fastai
8
+ scikit-image
9
+ pymupdf
10
+ fpdf
11
+
streamlit_app.py ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from io import BytesIO
2
+ import os
3
+ import pathlib
4
+ import tempfile
5
+ import time
6
+
7
+ import fitz
8
+ import gradio as gr
9
+ import PIL
10
+ import skimage
11
+ import streamlit as st
12
+ from fastai.learner import load_learner
13
+ from fastai.vision.all import *
14
+ from fpdf import FPDF
15
+ from icevision.all import *
16
+ from icevision.models.checkpoint import *
17
+ from PIL import Image as PILImage
18
+
19
+
20
+ CHECKPOINT_PATH = "./allsynthetic-imgsize768.pth"
21
+
22
+
23
+ @st.cache
24
+ def load_icevision_model():
25
+ return model_from_checkpoint(CHECKPOINT_PATH)
26
+
27
+
28
+ @st.cache
29
+ def load_fastai_model():
30
+ return load_learner("fastai-classification-model.pkl")
31
+
32
+
33
+ checkpoint_and_model = load_icevision_model()
34
+ model = checkpoint_and_model["model"]
35
+ model_type = checkpoint_and_model["model_type"]
36
+ class_map = checkpoint_and_model["class_map"]
37
+
38
+ img_size = checkpoint_and_model["img_size"]
39
+ valid_tfms = tfms.A.Adapter(
40
+ [*tfms.A.resize_and_pad(img_size), tfms.A.Normalize()]
41
+ )
42
+
43
+
44
+ learn = load_fastai_model()
45
+ labels = learn.dls.vocab
46
+
47
+
48
+ @st.experimental_memo
49
+ def get_content_area(pred_dict) -> int:
50
+ if "content" not in pred_dict["detection"]["labels"]:
51
+ return 0
52
+ content_bboxes = [
53
+ pred_dict["detection"]["bboxes"][idx]
54
+ for idx, label in enumerate(pred_dict["detection"]["labels"])
55
+ if label == "content"
56
+ ]
57
+ cb = content_bboxes[0]
58
+ return (cb.xmax - cb.xmin) * (cb.ymax - cb.ymin)
59
+
60
+
61
+ @st.experimental_memo
62
+ def get_redaction_area(pred_dict) -> int:
63
+ if "redaction" not in pred_dict["detection"]["labels"]:
64
+ return 0
65
+ redaction_bboxes = [
66
+ pred_dict["detection"]["bboxes"][idx]
67
+ for idx, label in enumerate(pred_dict["detection"]["labels"])
68
+ if label == "redaction"
69
+ ]
70
+ return sum(
71
+ (bbox.xmax - bbox.xmin) * (bbox.ymax - bbox.ymin)
72
+ for bbox in redaction_bboxes
73
+ )
74
+
75
+
76
+ st.title("Redaction Detector")
77
+
78
+ st.image(
79
+ "./synthetic-redactions.jpg",
80
+ width=300,
81
+ )
82
+ uploaded_pdf = st.file_uploader(
83
+ "Upload a PDF...",
84
+ type="pdf",
85
+ accept_multiple_files=False,
86
+ help="This application processes PDF files. Please upload a document you believe to contain redactions.",
87
+ on_change=None,
88
+ )
89
+
90
+ # Add a selectbox to the sidebar:
91
+ st.sidebar.header("Customisation Options")
92
+
93
+ graph_checkbox = st.sidebar.checkbox(
94
+ "Show analysis charts",
95
+ value=True,
96
+ help="Display charts analysising the redactions found in the document.",
97
+ )
98
+
99
+ extract_images_checkbox = st.sidebar.checkbox(
100
+ "Extract redacted images",
101
+ value=True,
102
+ help="Create a PDF file containing the redacted images with an object detection overlay highlighting their locations and the confidence the model had when detecting the redactions.",
103
+ )
104
+
105
+ # Add a slider to the sidebar:
106
+ confidence = st.sidebar.slider(
107
+ "Confidence level (%)",
108
+ min_value=0,
109
+ max_value=100,
110
+ value=80,
111
+ )
112
+
113
+
114
+ @st.cache
115
+ def get_pdf_document(input):
116
+ with open(
117
+ pathlib.Path(filename_without_extension / "output.pdf"), "wb"
118
+ ) as f:
119
+ f.write(uploaded_pdf.getbuffer())
120
+ return fitz.open("output.pdf")
121
+
122
+
123
+ @st.cache
124
+ def get_image_predictions(img):
125
+ return model_type.end2end_detect(
126
+ img,
127
+ valid_tfms,
128
+ model,
129
+ class_map=class_map,
130
+ detection_threshold=confidence / 100,
131
+ display_label=True,
132
+ display_bbox=True,
133
+ return_img=True,
134
+ font_size=16,
135
+ label_color="#FF59D6",
136
+ )
137
+
138
+
139
+ if uploaded_pdf is None:
140
+ st.markdown(pathlib.Path("article.md").read_text())
141
+ else:
142
+ st.text("Opening PDF...")
143
+ filename_without_extension = uploaded_pdf.name[:-4]
144
+ results = []
145
+ images = []
146
+ document = get_pdf_document(uploaded_pdf)
147
+ total_image_areas = 0
148
+ total_content_areas = 0
149
+ total_redaction_area = 0
150
+ tmp_dir = tempfile.gettempdir()
151
+
152
+ for page_num, page in enumerate(document, start=1):
153
+ image_pixmap = page.get_pixmap()
154
+ image = image_pixmap.tobytes()
155
+ _, _, probs = learn.predict(image)
156
+ results.append(
157
+ {labels[i]: float(probs[i]) for i in range(len(labels))}
158
+ )
159
+ if probs[0] > (confidence / 100):
160
+ redaction_count = len(images)
161
+ if not os.path.exists(
162
+ os.path.join(tmp_dir, filename_without_extension or "abc")
163
+ ):
164
+ os.makedirs(os.path.join(tmp_dir, filename_without_extension))
165
+ image_pixmap.save(
166
+ os.path.join(
167
+ tmp_dir, filename_without_extension, f"page-{page_num}.png"
168
+ )
169
+ )
170
+ images.append(
171
+ [
172
+ f"Redacted page #{redaction_count + 1} on page {page_num}",
173
+ os.path.join(
174
+ tmp_dir,
175
+ filename_without_extension,
176
+ f"page-{page_num}.png",
177
+ ),
178
+ ]
179
+ )
180
+ redacted_pages = [
181
+ str(page + 1)
182
+ for page in range(len(results))
183
+ if results[page]["redacted"] > (confidence / 100)
184
+ ]
185
+ report = os.path.join(
186
+ tmp_dir, filename_without_extension, "redacted_pages.pdf"
187
+ )
188
+
189
+ if extract_images_checkbox:
190
+ pdf = FPDF(unit="cm", format="A4")
191
+ pdf.set_auto_page_break(0)
192
+ imagelist = sorted(
193
+ [
194
+ i
195
+ for i in os.listdir(
196
+ os.path.join(tmp_dir, filename_without_extension)
197
+ )
198
+ if i.endswith("png")
199
+ ]
200
+ )
201
+ for image in imagelist:
202
+ with PILImage.open(
203
+ os.path.join(tmp_dir, filename_without_extension, image)
204
+ ) as img:
205
+ size = img.size
206
+ width, height = size
207
+ if width > height:
208
+ pdf.add_page(orientation="L")
209
+ else:
210
+ pdf.add_page(orientation="P")
211
+ pred_dict = get_image_predictions(img)
212
+
213
+ total_image_areas += pred_dict["width"] * pred_dict["height"]
214
+ total_content_areas += get_content_area(pred_dict)
215
+ total_redaction_area += get_redaction_area(pred_dict)
216
+
217
+ pred_dict["img"].save(
218
+ os.path.join(
219
+ tmp_dir, filename_without_extension, f"pred-{image}"
220
+ ),
221
+ )
222
+ pdf.image(
223
+ os.path.join(
224
+ tmp_dir, filename_without_extension, f"pred-{image}"
225
+ ),
226
+ w=pdf.w,
227
+ h=pdf.h,
228
+ )
229
+ pdf.output(report, "F")
230
+
231
+ text_output = f"A total of {len(redacted_pages)} pages were redacted. \n\nThe redacted page numbers were: {', '.join(redacted_pages)}. \n\n"
232
+
233
+ if not extract_images_checkbox:
234
+ st.text(text_output)
235
+ # DISPLAY IMAGES
236
+ else:
237
+ total_redaction_proportion = round(
238
+ (total_redaction_area / total_image_areas) * 100, 1
239
+ )
240
+ content_redaction_proportion = round(
241
+ (total_redaction_area / total_content_areas) * 100, 1
242
+ )
243
+
244
+ redaction_analysis = f"- {total_redaction_proportion}% of the total area of the redacted pages was redacted. \n- {content_redaction_proportion}% of the actual content of those redacted pages was redacted."
245
+
246
+ st.text(text_output + redaction_analysis)
247
+ # DISPLAY IMAGES
synthetic-redactions.jpg ADDED