Skip to content

video_features allows you to extract features from raw videos in parallel with multiple GPUs. It supports several extractors that capture visual appearance, optical flow, and audio features.

Quick Start

Open In Colab

# clone the repo and change the working directory
git clone
cd video_features

# install environment
conda env create -f conda_env_torch_zoo.yml

# load the environment
conda activate torch_zoo

# extract r(2+1)d features for the sample videos
python \
    feature_type=r21d \
    device_ids="[0]" \
    video_paths="[./sample/v_ZNVhz7ctTq0.mp4, ./sample/v_GGSY1Qvo990.mp4]"

# use `device_ids="[0, 2]"` to run on 0th and 2nd devices in parallel

Supported Models

Action Recognition

Sound Recognition

Optical Flow

Image Recognition