This is an official pytorch implementation of EZ-CLIP: Efficient Zero-Shot Video Action Recognition [arXiv]
- Trained model download link of google driver.
We provide the conda requirements.txt to help you install these libraries. You can initialize environment by using pip install -r requirements.txt
.
We need to first extract videos into frames for fast reading. Please refer 'Dataset_creation_scripts' data pre-processing. We have successfully trained on Kinetics, UCF101, HMDB51,
# Train Zero shot
python train.py --config configs/K-400/k400_train.yaml
# Test Zero shot
python test_zero_and_few_shot.py --config configs/ucf101/UCF_zero_shot_testing.yaml
Our code is based on ActionCLIP