File size: 9,919 Bytes
3133fdb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Torch Hub Inference Tutorial\n",
    "\n",
    "In this tutorial you'll learn:\n",
    "- how to load a pretrained model using Torch Hub \n",
    "- run inference to classify the action in a demo video"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Install and Import modules"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If `torch`, `torchvision` and `pytorchvideo` are not installed, run the following cell:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "try:\n",
    "    import torch\n",
    "except ModuleNotFoundError:\n",
    "    !pip install torch torchvision\n",
    "    import os\n",
    "    import sys\n",
    "    import torch\n",
    "    \n",
    "if torch.__version__=='1.6.0+cu101' and sys.platform.startswith('linux'):\n",
    "    !pip install pytorchvideo\n",
    "else:\n",
    "    need_pytorchvideo=False\n",
    "    try:\n",
    "        # Running notebook locally\n",
    "        import pytorchvideo\n",
    "    except ModuleNotFoundError:\n",
    "        need_pytorchvideo=True\n",
    "    if need_pytorchvideo:\n",
    "        # Install from GitHub\n",
    "        !pip install \"git+https://github.com/facebookresearch/pytorchvideo.git\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json \n",
    "from torchvision.transforms import Compose, Lambda\n",
    "from torchvision.transforms._transforms_video import (\n",
    "    CenterCropVideo,\n",
    "    NormalizeVideo,\n",
    ")\n",
    "from pytorchvideo.data.encoded_video import EncodedVideo\n",
    "from pytorchvideo.transforms import (\n",
    "    ApplyTransformToKey,\n",
    "    ShortSideScale,\n",
    "    UniformTemporalSubsample,\n",
    "    UniformCropVideo\n",
    ") \n",
    "from typing import Dict"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Setup \n",
    "\n",
    "Download the id to label mapping for the Kinetics 400 dataset on which the Torch Hub models were trained. \n",
    "This will be used to get the category label names from the predicted class ids."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!wget https://dl.fbaipublicfiles.com/pyslowfast/dataset/class_names/kinetics_classnames.json "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"kinetics_classnames.json\", \"r\") as f:\n",
    "    kinetics_classnames = json.load(f)\n",
    "\n",
    "# Create an id to label name mapping\n",
    "kinetics_id_to_classname = {}\n",
    "for k, v in kinetics_classnames.items():\n",
    "    kinetics_id_to_classname[v] = str(k).replace('\"', \"\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load Model using Torch Hub API\n",
    "\n",
    "PyTorchVideo provides several pretrained models through Torch Hub. Available models are described in [model zoo documentation](https://github.com/facebookresearch/pytorchvideo/blob/main/docs/source/model_zoo.md#kinetics-400). \n",
    "\n",
    "Here we are selecting the `slowfast_r50` model which was trained using a 8x8 setting on the Kinetics 400 dataset. \n",
    "\n",
    "\n",
    "NOTE: to run on GPU in Google Colab, in the menu bar selet: Runtime -> Change runtime type -> Harware Accelerator -> GPU\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Device on which to run the model\n",
    "# Set to cuda to load on GPU\n",
    "device = \"cpu\"\n",
    "\n",
    "# Pick a pretrained model \n",
    "model_name = \"slowfast_r50\"\n",
    "model = torch.hub.load(\"facebookresearch/pytorchvideo:main\", model=model_name, pretrained=True)\n",
    "\n",
    "# Set to eval mode and move to desired device\n",
    "model = model.to(device)\n",
    "model = model.eval()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Define the transformations for the input required by the model\n",
    "\n",
    "Before passing the video into the model we need to apply some input transforms and sample a clip of the correct duration.\n",
    "\n",
    "NOTE: The input transforms are specific to the model. If you choose a different model than the example in this tutorial, please refer to the code provided in the Torch Hub documentation and copy over the relevant transforms:\n",
    "- [SlowFast](https://pytorch.org/hub/facebookresearch_pytorchvideo_slowfast/)\n",
    "- [X3D](https://pytorch.org/hub/facebookresearch_pytorchvideo_x3d/)\n",
    "- [Slow](https://pytorch.org/hub/facebookresearch_pytorchvideo_resnet/)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "####################\n",
    "# SlowFast transform\n",
    "####################\n",
    "\n",
    "side_size = 256\n",
    "mean = [0.45, 0.45, 0.45]\n",
    "std = [0.225, 0.225, 0.225]\n",
    "crop_size = 256\n",
    "num_frames = 32\n",
    "sampling_rate = 2\n",
    "frames_per_second = 30\n",
    "alpha = 4\n",
    "\n",
    "class PackPathway(torch.nn.Module):\n",
    "    \"\"\"\n",
    "    Transform for converting video frames as a list of tensors. \n",
    "    \"\"\"\n",
    "    def __init__(self):\n",
    "        super().__init__()\n",
    "        \n",
    "    def forward(self, frames: torch.Tensor):\n",
    "        fast_pathway = frames\n",
    "        # Perform temporal sampling from the fast pathway.\n",
    "        slow_pathway = torch.index_select(\n",
    "            frames,\n",
    "            1,\n",
    "            torch.linspace(\n",
    "                0, frames.shape[1] - 1, frames.shape[1] // alpha\n",
    "            ).long(),\n",
    "        )\n",
    "        frame_list = [slow_pathway, fast_pathway]\n",
    "        return frame_list\n",
    "\n",
    "transform =  ApplyTransformToKey(\n",
    "    key=\"video\",\n",
    "    transform=Compose(\n",
    "        [\n",
    "            UniformTemporalSubsample(num_frames),\n",
    "            Lambda(lambda x: x/255.0),\n",
    "            NormalizeVideo(mean, std),\n",
    "            ShortSideScale(\n",
    "                size=side_size\n",
    "            ),\n",
    "            CenterCropVideo(crop_size),\n",
    "            PackPathway()\n",
    "        ]\n",
    "    ),\n",
    ")\n",
    "\n",
    "# The duration of the input clip is also specific to the model.\n",
    "clip_duration = (num_frames * sampling_rate)/frames_per_second"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load an example video\n",
    "We can test the classification of an example video from the kinetics validation set such as this [archery video](https://www.youtube.com/watch?v=3and4vWkW4s)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Download the example video file\n",
    "!wget https://dl.fbaipublicfiles.com/pytorchvideo/projects/archery.mp4 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the example video\n",
    "video_path = \"archery.mp4\"  \n",
    "\n",
    "# Select the duration of the clip to load by specifying the start and end duration\n",
    "# The start_sec should correspond to where the action occurs in the video\n",
    "start_sec = 0\n",
    "end_sec = start_sec + clip_duration \n",
    "\n",
    "# Initialize an EncodedVideo helper class\n",
    "video = EncodedVideo.from_path(video_path)\n",
    "\n",
    "# Load the desired clip\n",
    "video_data = video.get_clip(start_sec=start_sec, end_sec=end_sec)\n",
    "\n",
    "# Apply a transform to normalize the video input\n",
    "video_data = transform(video_data)\n",
    "\n",
    "# Move the inputs to the desired device\n",
    "inputs = video_data[\"video\"]\n",
    "inputs = [i.to(device)[None, ...] for i in inputs]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Get model predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Pass the input clip through the model \n",
    "preds = model(inputs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Get the predicted classes \n",
    "post_act = torch.nn.Softmax(dim=1)\n",
    "preds = post_act(preds)\n",
    "pred_classes = preds.topk(k=5).indices\n",
    "\n",
    "# Map the predicted classes to the label names\n",
    "pred_class_names = [kinetics_id_to_classname[int(i)] for i in pred_classes[0]]\n",
    "print(\"Predicted labels: %s\" % \", \".join(pred_class_names))"
   ]
  }
 ],
 "metadata": {
  "bento_stylesheets": {
   "bento/extensions/flow/main.css": true,
   "bento/extensions/kernel_selector/main.css": true,
   "bento/extensions/kernel_ui/main.css": true,
   "bento/extensions/new_kernel/main.css": true,
   "bento/extensions/system_usage/main.css": true,
   "bento/extensions/theme/main.css": true
  },
  "kernelspec": {
   "display_name": "pytorchvideo_etc (local)",
   "language": "python",
   "name": "pytorchvideo_etc_local"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}