ref: https://github.com/jfzhang95/pytorch-video-recognition
ref:https://github.com/dmlc/gluon-cv
The code was tested with Anaconda and Python 3.5. After installing the Anaconda environment:
-
Clone the repo:
git clone https://github.com/MachineLP/Pytorch_video_classifier.git cd Pytorch_video_classifier
-
Install dependencies:
For PyTorch dependency, see pytorch.org for more details.
For custom dependencies:
conda install opencv pip install tqdm scikit-learn tensorboardX
-
Download pretrained model from BaiduYun or GoogleDrive. Currently only support pretrained model for C3D.
-
Configure your dataset and pretrained model path in mypath.py.
-
You can choose different models and datasets in train.py.
To train the model, please do:
python train.py
-
inference To infer the model, please do:
python inference.py