dnth commited on
Commit
e9039a3
1 Parent(s): a1b4f2d
Files changed (8) hide show
  1. .github/workflows/main.yml +0 -21
  2. .gitignore +1 -1
  3. README.md +0 -37
  4. app.py +0 -73
  5. gradioapp.ipynb +0 -262
  6. models/model.pth +0 -3
  7. requirements.txt +0 -9
  8. train.ipynb +0 -0
.github/workflows/main.yml DELETED
@@ -1,21 +0,0 @@
1
- name: Sync to Hugging Face hub
2
- on:
3
- push:
4
- branches: [main]
5
-
6
- # to run this workflow manually from the Actions tab
7
- workflow_dispatch:
8
-
9
- jobs:
10
- sync-to-hub:
11
- runs-on: ubuntu-latest
12
- steps:
13
-
14
-
15
- - uses: actions/checkout@v2
16
- with:
17
- fetch-depth: 0
18
- - name: Push to hub
19
- env:
20
- HF_TOKEN: ${{ secrets.HF_TOKEN }}
21
- run: git push --force https://dnth:$HF_TOKEN@huggingface.co/spaces/dnth/webdemo-fridge-detection main
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
.gitignore CHANGED
@@ -1,3 +1,3 @@
1
  .ipynb_checkpoints
2
  .ipynb_checkpoints/*
3
- models/*.pth
 
1
  .ipynb_checkpoints
2
  .ipynb_checkpoints/*
3
+ models/**
README.md DELETED
@@ -1,37 +0,0 @@
1
- ---
2
- title: webdemo-fridge-detection
3
- emoji: 🍿
4
- colorFrom: red
5
- colorTo: purple
6
- sdk: gradio
7
- app_file: app.py
8
- pinned: false
9
- ---
10
-
11
- # Configuration
12
-
13
- `title`: _string_
14
- Display title for the Space
15
-
16
- `emoji`: _string_
17
- Space emoji (emoji-only character allowed)
18
-
19
- `colorFrom`: _string_
20
- Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
21
-
22
- `colorTo`: _string_
23
- Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
24
-
25
- `sdk`: _string_
26
- Can be either `gradio` or `streamlit`
27
-
28
- `sdk_version` : _string_
29
- Only applicable for `streamlit` SDK.
30
- See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
31
-
32
- `app_file`: _string_
33
- Path to your main application file (which contains either `gradio` or `streamlit` Python code).
34
- Path is relative to the root of the repository.
35
-
36
- `pinned`: _boolean_
37
- Whether the Space stays on top of your list.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app.py DELETED
@@ -1,73 +0,0 @@
1
- from icevision.all import *
2
- import icedata
3
- import PIL, requests
4
- import torch
5
- from torchvision import transforms
6
- import gradio as gr
7
-
8
- # Download the dataset
9
- url = "https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjects.zip"
10
- dest_dir = "fridge"
11
- data_dir = icedata.load_data(url, dest_dir)
12
-
13
- # Create the parser
14
- parser = parsers.VOCBBoxParser(annotations_dir=data_dir / "odFridgeObjects/annotations", images_dir=data_dir / "odFridgeObjects/images")
15
-
16
- # Parse annotations to create records
17
- train_records, valid_records = parser.parse()
18
-
19
- class_map = parser.class_map
20
-
21
- extra_args = {}
22
- model_type = models.torchvision.retinanet
23
- backbone = model_type.backbones.resnet50_fpn
24
- # Instantiate the model
25
- model = model_type.model(backbone=backbone(pretrained=True), num_classes=len(parser.class_map), **extra_args)
26
-
27
- # Transforms
28
- # size is set to 384 because EfficientDet requires its inputs to be divisible by 128
29
- image_size = 384
30
- train_tfms = tfms.A.Adapter([*tfms.A.aug_tfms(size=image_size, presize=512), tfms.A.Normalize()])
31
- valid_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(image_size), tfms.A.Normalize()])
32
- # Datasets
33
- train_ds = Dataset(train_records, train_tfms)
34
- valid_ds = Dataset(valid_records, valid_tfms)
35
- # Data Loaders
36
- train_dl = model_type.train_dl(train_ds, batch_size=8, num_workers=4, shuffle=True)
37
- valid_dl = model_type.valid_dl(valid_ds, batch_size=8, num_workers=4, shuffle=False)
38
- metrics = [COCOMetric(metric_type=COCOMetricType.bbox)]
39
- learn = model_type.fastai.learner(dls=[train_dl, valid_dl], model=model, metrics=metrics)
40
-
41
- learn = learn.load('model')
42
-
43
- def show_preds(input_image, display_label, display_bbox, detection_threshold):
44
-
45
- if detection_threshold==0: detection_threshold=0.5
46
-
47
- img = PIL.Image.fromarray(input_image, 'RGB')
48
-
49
- pred_dict = model_type.end2end_detect(img, valid_tfms, model, class_map=class_map, detection_threshold=detection_threshold,
50
- display_label=display_label, display_bbox=display_bbox, return_img=True,
51
- font_size=16, label_color="#FF59D6")
52
-
53
- return pred_dict['img']
54
-
55
- # display_chkbox = gr.inputs.CheckboxGroup(["Label", "BBox"], label="Display", default=True)
56
- display_chkbox_label = gr.inputs.Checkbox(label="Label", default=True)
57
- display_chkbox_box = gr.inputs.Checkbox(label="Box", default=True)
58
-
59
- detection_threshold_slider = gr.inputs.Slider(minimum=0, maximum=1, step=0.1, default=0.5, label="Detection Threshold")
60
-
61
- outputs = gr.outputs.Image(type="pil")
62
-
63
- # Option 1: Get an image from local drive
64
- gr_interface = gr.Interface(fn=show_preds, inputs=["image", display_chkbox_label, display_chkbox_box, detection_threshold_slider], outputs=outputs, title='IceApp - Fridge Object')
65
-
66
- # # Option 2: Grab an image from a webcam
67
- # gr_interface = gr.Interface(fn=show_preds, inputs=["webcam", display_chkbox_label, display_chkbox_box, detection_threshold_slider], outputs=outputs, title='IceApp - COCO', live=False)
68
-
69
- # # Option 3: Continuous image stream from the webcam
70
- # gr_interface = gr.Interface(fn=show_preds, inputs=["webcam", display_chkbox_label, display_chkbox_box, detection_threshold_slider], outputs=outputs, title='IceApp - COCO', live=True)
71
-
72
-
73
- gr_interface.launch(inline=False, share=True, debug=True)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
gradioapp.ipynb DELETED
@@ -1,262 +0,0 @@
1
- {
2
- "cells": [
3
- {
4
- "cell_type": "code",
5
- "execution_count": 1,
6
- "id": "ee7e0c23-3fa5-4547-8598-7df27a3876c5",
7
- "metadata": {},
8
- "outputs": [],
9
- "source": [
10
- "from icevision.all import *\n",
11
- "import icedata\n",
12
- "import PIL, requests\n",
13
- "import torch\n",
14
- "from torchvision import transforms\n",
15
- "import gradio as gr"
16
- ]
17
- },
18
- {
19
- "cell_type": "code",
20
- "execution_count": 2,
21
- "id": "646cc218-f7de-4f32-a3d9-fccdc9b54592",
22
- "metadata": {},
23
- "outputs": [],
24
- "source": [
25
- "# Download the dataset\n",
26
- "url = \"https://cvbp-secondary.z19.web.core.windows.net/datasets/object_detection/odFridgeObjects.zip\"\n",
27
- "dest_dir = \"fridge\"\n",
28
- "data_dir = icedata.load_data(url, dest_dir)"
29
- ]
30
- },
31
- {
32
- "cell_type": "code",
33
- "execution_count": 3,
34
- "id": "96184ca0-0b0a-4a20-8ab9-30dee6096588",
35
- "metadata": {},
36
- "outputs": [],
37
- "source": [
38
- "# Create the parser\n",
39
- "parser = parsers.VOCBBoxParser(annotations_dir=data_dir / \"odFridgeObjects/annotations\", images_dir=data_dir / \"odFridgeObjects/images\")"
40
- ]
41
- },
42
- {
43
- "cell_type": "code",
44
- "execution_count": 4,
45
- "id": "dfa20f76-4970-479a-9497-871fe4cfd170",
46
- "metadata": {},
47
- "outputs": [
48
- {
49
- "data": {
50
- "application/vnd.jupyter.widget-view+json": {
51
- "model_id": "fc8e676815314038a40c884c8c7f5b67",
52
- "version_major": 2,
53
- "version_minor": 0
54
- },
55
- "text/plain": [
56
- " 0%| | 0/128 [00:00<?, ?it/s]"
57
- ]
58
- },
59
- "metadata": {},
60
- "output_type": "display_data"
61
- },
62
- {
63
- "name": "stderr",
64
- "output_type": "stream",
65
- "text": [
66
- "\u001b[1m\u001b[1mINFO \u001b[0m\u001b[1m\u001b[0m - \u001b[1m\u001b[34m\u001b[1mAutofixing records\u001b[0m\u001b[1m\u001b[34m\u001b[0m\u001b[1m\u001b[0m | \u001b[36micevision.parsers.parser\u001b[0m:\u001b[36mparse\u001b[0m:\u001b[36m122\u001b[0m\n"
67
- ]
68
- },
69
- {
70
- "data": {
71
- "application/vnd.jupyter.widget-view+json": {
72
- "model_id": "3db4bc1ae388495eb3b62289459a5c00",
73
- "version_major": 2,
74
- "version_minor": 0
75
- },
76
- "text/plain": [
77
- " 0%| | 0/128 [00:00<?, ?it/s]"
78
- ]
79
- },
80
- "metadata": {},
81
- "output_type": "display_data"
82
- },
83
- {
84
- "data": {
85
- "text/plain": [
86
- "<ClassMap: {'background': 0, 'carton': 1, 'milk_bottle': 2, 'can': 3, 'water_bottle': 4}>"
87
- ]
88
- },
89
- "execution_count": 4,
90
- "metadata": {},
91
- "output_type": "execute_result"
92
- }
93
- ],
94
- "source": [
95
- "# Parse annotations to create records\n",
96
- "train_records, valid_records = parser.parse()\n",
97
- "parser.class_map"
98
- ]
99
- },
100
- {
101
- "cell_type": "code",
102
- "execution_count": 5,
103
- "id": "26d4f2f7-db51-413c-838f-f80c5898ab52",
104
- "metadata": {},
105
- "outputs": [],
106
- "source": [
107
- "class_map = parser.class_map"
108
- ]
109
- },
110
- {
111
- "cell_type": "code",
112
- "execution_count": 6,
113
- "id": "007b2e97-d546-4178-84e7-d4fe597f3731",
114
- "metadata": {},
115
- "outputs": [],
116
- "source": [
117
- "extra_args = {}\n",
118
- "model_type = models.torchvision.retinanet\n",
119
- "backbone = model_type.backbones.resnet50_fpn\n",
120
- "# Instantiate the model\n",
121
- "model = model_type.model(backbone=backbone(pretrained=True), num_classes=len(parser.class_map), **extra_args) "
122
- ]
123
- },
124
- {
125
- "cell_type": "code",
126
- "execution_count": 7,
127
- "id": "7b664cbf-3ab0-46df-a9d0-c4eb5c3c026d",
128
- "metadata": {},
129
- "outputs": [],
130
- "source": [
131
- "# Transforms\n",
132
- "# size is set to 384 because EfficientDet requires its inputs to be divisible by 128\n",
133
- "image_size = 384\n",
134
- "train_tfms = tfms.A.Adapter([*tfms.A.aug_tfms(size=image_size, presize=512), tfms.A.Normalize()])\n",
135
- "valid_tfms = tfms.A.Adapter([*tfms.A.resize_and_pad(image_size), tfms.A.Normalize()])\n",
136
- "# Datasets\n",
137
- "train_ds = Dataset(train_records, train_tfms)\n",
138
- "valid_ds = Dataset(valid_records, valid_tfms)\n",
139
- "# Data Loaders\n",
140
- "train_dl = model_type.train_dl(train_ds, batch_size=8, num_workers=4, shuffle=True)\n",
141
- "valid_dl = model_type.valid_dl(valid_ds, batch_size=8, num_workers=4, shuffle=False)\n",
142
- "metrics = [COCOMetric(metric_type=COCOMetricType.bbox)]\n",
143
- "learn = model_type.fastai.learner(dls=[train_dl, valid_dl], model=model, metrics=metrics)"
144
- ]
145
- },
146
- {
147
- "cell_type": "code",
148
- "execution_count": 8,
149
- "id": "7bddb248-215d-4998-9d90-14ea6989c236",
150
- "metadata": {},
151
- "outputs": [
152
- {
153
- "name": "stderr",
154
- "output_type": "stream",
155
- "text": [
156
- "/home/dnth/anaconda3/envs/icevision-gradio/lib/python3.8/site-packages/fastai/learner.py:56: UserWarning: Saved filed doesn't contain an optimizer state.\n",
157
- " elif with_opt: warn(\"Saved filed doesn't contain an optimizer state.\")\n"
158
- ]
159
- }
160
- ],
161
- "source": [
162
- "learn = learn.load('model')"
163
- ]
164
- },
165
- {
166
- "cell_type": "code",
167
- "execution_count": 9,
168
- "id": "745315f6-8aa5-486e-a7bc-e11348bec6a6",
169
- "metadata": {},
170
- "outputs": [],
171
- "source": [
172
- "def show_preds(input_image, display_label, display_bbox, detection_threshold):\n",
173
- "\n",
174
- " if detection_threshold==0: detection_threshold=0.5\n",
175
- "\n",
176
- " img = PIL.Image.fromarray(input_image, 'RGB')\n",
177
- "\n",
178
- " pred_dict = model_type.end2end_detect(img, valid_tfms, model, class_map=class_map, detection_threshold=detection_threshold,\n",
179
- " display_label=display_label, display_bbox=display_bbox, return_img=True, \n",
180
- " font_size=16, label_color=\"#FF59D6\")\n",
181
- "\n",
182
- " return pred_dict['img']"
183
- ]
184
- },
185
- {
186
- "cell_type": "code",
187
- "execution_count": null,
188
- "id": "63ac7fab-2068-4dbc-a464-0551b6fc12b2",
189
- "metadata": {},
190
- "outputs": [
191
- {
192
- "name": "stdout",
193
- "output_type": "stream",
194
- "text": [
195
- "Running on local URL: http://127.0.0.1:7860/\n",
196
- "Running on public URL: https://11839.gradio.app\n",
197
- "\n",
198
- "This share link will expire in 72 hours. To get longer links, send an email to: support@gradio.app\n"
199
- ]
200
- },
201
- {
202
- "name": "stderr",
203
- "output_type": "stream",
204
- "text": [
205
- "/home/dnth/anaconda3/envs/icevision-gradio/lib/python3.8/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.)\n",
206
- " return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]\n"
207
- ]
208
- }
209
- ],
210
- "source": [
211
- "# display_chkbox = gr.inputs.CheckboxGroup([\"Label\", \"BBox\"], label=\"Display\", default=True)\n",
212
- "display_chkbox_label = gr.inputs.Checkbox(label=\"Label\", default=True)\n",
213
- "display_chkbox_box = gr.inputs.Checkbox(label=\"Box\", default=True)\n",
214
- "\n",
215
- "detection_threshold_slider = gr.inputs.Slider(minimum=0, maximum=1, step=0.1, default=0.5, label=\"Detection Threshold\")\n",
216
- "\n",
217
- "outputs = gr.outputs.Image(type=\"pil\")\n",
218
- "\n",
219
- "# Option 1: Get an image from local drive\n",
220
- "gr_interface = gr.Interface(fn=show_preds, inputs=[\"image\", display_chkbox_label, display_chkbox_box, detection_threshold_slider], outputs=outputs, title='IceApp - COCO')\n",
221
- "\n",
222
- "# # Option 2: Grab an image from a webcam\n",
223
- "# gr_interface = gr.Interface(fn=show_preds, inputs=[\"webcam\", display_chkbox_label, display_chkbox_box, detection_threshold_slider], outputs=outputs, title='IceApp - COCO', live=False)\n",
224
- "\n",
225
- "# # Option 3: Continuous image stream from the webcam\n",
226
- "# gr_interface = gr.Interface(fn=show_preds, inputs=[\"webcam\", display_chkbox_label, display_chkbox_box, detection_threshold_slider], outputs=outputs, title='IceApp - COCO', live=True)\n",
227
- "\n",
228
- "\n",
229
- "gr_interface.launch(inline=False, share=True, debug=True)\n"
230
- ]
231
- },
232
- {
233
- "cell_type": "code",
234
- "execution_count": null,
235
- "id": "727a3589-364b-4bfd-9c32-bef5ebe34dbe",
236
- "metadata": {},
237
- "outputs": [],
238
- "source": []
239
- }
240
- ],
241
- "metadata": {
242
- "kernelspec": {
243
- "display_name": "Python 3",
244
- "language": "python",
245
- "name": "python3"
246
- },
247
- "language_info": {
248
- "codemirror_mode": {
249
- "name": "ipython",
250
- "version": 3
251
- },
252
- "file_extension": ".py",
253
- "mimetype": "text/x-python",
254
- "name": "python",
255
- "nbconvert_exporter": "python",
256
- "pygments_lexer": "ipython3",
257
- "version": "3.8.12"
258
- }
259
- },
260
- "nbformat": 4,
261
- "nbformat_minor": 5
262
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/model.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb46c5796093f5921996b04f3d85ded01f4070366e38898e748e06c00d262972
3
- size 129455527
 
 
 
 
requirements.txt DELETED
@@ -1,9 +0,0 @@
1
- #icevision[all]
2
-
3
- #opencv-python-headless
4
-
5
- git+https://github.com/dnth/icevision.git
6
- icedata
7
-
8
- #fastai
9
- #scikit-image
 
 
 
 
 
 
 
 
 
 
train.ipynb DELETED
The diff for this file is too large to render. See raw diff