Spaces:

pytorch
/

3D_ResNet

Runtime error

App Files Files Community

3D_ResNet / app.py

akhaliq HF staff

Update app.py

4f6be2d about 2 years ago

raw history blame contribute delete

No virus

3.82 kB

	import torch
	# Choose the `slow_r50` model
	model = torch.hub.load('facebookresearch/pytorchvideo', 'slow_r50', pretrained=True)
	import json
	import urllib
	from pytorchvideo.data.encoded_video import EncodedVideo

	from torchvision.transforms import Compose, Lambda
	from torchvision.transforms._transforms_video import (
	CenterCropVideo,
	NormalizeVideo,
	)
	from pytorchvideo.transforms import (
	ApplyTransformToKey,
	ShortSideScale,
	UniformTemporalSubsample
	)

	import gradio as gr
	# Set to GPU or CPU
	device = "cpu"
	model = model.eval()
	model = model.to(device)
	json_url = "https://dl.fbaipublicfiles.com/pyslowfast/dataset/class_names/kinetics_classnames.json"
	json_filename = "kinetics_classnames.json"
	try: urllib.URLopener().retrieve(json_url, json_filename)
	except: urllib.request.urlretrieve(json_url, json_filename)
	with open(json_filename, "r") as f:
	kinetics_classnames = json.load(f)

	# Create an id to label name mapping
	kinetics_id_to_classname = {}
	for k, v in kinetics_classnames.items():
	kinetics_id_to_classname[v] = str(k).replace('"', "")
	side_size = 256
	mean = [0.45, 0.45, 0.45]
	std = [0.225, 0.225, 0.225]
	crop_size = 256
	num_frames = 8
	sampling_rate = 8
	frames_per_second = 30

	# Note that this transform is specific to the slow_R50 model.
	transform = ApplyTransformToKey(
	key="video",
	transform=Compose(
	[
	UniformTemporalSubsample(num_frames),
	Lambda(lambda x: x/255.0),
	NormalizeVideo(mean, std),
	ShortSideScale(
	size=side_size
	),
	CenterCropVideo(crop_size=(crop_size, crop_size))
	]
	),
	)

	# The duration of the input clip is also specific to the model.
	clip_duration = (num_frames * sampling_rate)/frames_per_second
	url_link = "https://dl.fbaipublicfiles.com/pytorchvideo/projects/archery.mp4"
	video_path = 'archery.mp4'
	try: urllib.URLopener().retrieve(url_link, video_path)
	except: urllib.request.urlretrieve(url_link, video_path)
	# Select the duration of the clip to load by specifying the start and end duration
	# The start_sec should correspond to where the action occurs in the video
	def inference(in_vid):
	start_sec = 0
	end_sec = start_sec + clip_duration

	# Initialize an EncodedVideo helper class and load the video
	video = EncodedVideo.from_path(in_vid)

	# Load the desired clip
	video_data = video.get_clip(start_sec=start_sec, end_sec=end_sec)

	# Apply a transform to normalize the video input
	video_data = transform(video_data)

	# Move the inputs to the desired device
	inputs = video_data["video"]
	inputs = inputs.to(device)
	# Pass the input clip through the model
	preds = model(inputs[None, ...])

	# Get the predicted classes
	post_act = torch.nn.Softmax(dim=1)
	preds = post_act(preds)
	pred_classes = preds.topk(k=5).indices[0]

	# Map the predicted classes to the label names
	pred_class_names = [kinetics_id_to_classname[int(i)] for i in pred_classes]
	return "%s" % ", ".join(pred_class_names)

	inputs = gr.inputs.Video(label="Input Video")
	outputs = gr.outputs.Textbox(label="Top 5 predicted labels")

	title = "3D RESNET"
	description = "demo for 3D RESNET, Resnet Style Video classification networks pretrained on the Kinetics 400 dataset. To use it, simply upload your video, or click one of the examples to load them. Read more at the links below."
	article = "<p style='text-align: center'><a href='https://arxiv.org/abs/1812.03982'>SlowFast Networks for Video Recognition</a> \| <a href='https://github.com/facebookresearch/pytorchvideo'>Github Repo</a></p>"

	examples = [
	['archery.mp4']
	]

	gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, examples=examples, analytics_enabled=False).launch(enable_queue=True)