Sandbox::https://pytorchvideo.org/#dataset

A deep learning library for video understanding research

Get Started

Tutorials

GitHub

Based on PyTorch

Built using PyTorch. Makes it easy to use all the PyTorch-ecosystem components.

Reproducible Model Zoo

Variety of state of the art pretrained video models and their associated benchmarks that are ready to use.

Efficient Video Components

Video-focused fast and efficient components that are easy to use. Supports accelerated inference on hardware.

Get Started

Install pytorchvideo (Confirm requirements following the instructions here)
```
pip install pytorchvideo
```

Try Video classification with Model Zoo (For detailed instructions, refer to the PyTorchVideo Model Zoo Inference Tutorial

# Import all the required components
...

# Load pre-trained model 
model = torch.hub.load('facebookresearch/pytorchvideo', 'slow_r50', pretrained=True)

# Load video
video = EncodedVideo.from_path('some_video.avi')

# Compose video data transforms
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))
        ]
    ),
)

# Get clip
clip_start_sec = 0.0 # secs
clip_duration = 2.0 # secs
video_data = video.get_clip(start_sec=clip_start_sec, end_sec=clip_start_sec + clip_duration)
video_data = transform(video_data)

# Generate top 5 predictions
preds = torch.nn.functional.softmax(preds)
pred_class_ids = preds.topk(k=5).indices