2019 naic challege code
- Python 3 (Recommend to use Anaconda)
- PyTorch >= 1.1
- NVIDIA GPU + CUDA
- Deformable Convolution. We use mmdetection's dcn implementation. Please first compile it.
cd ./codes/models/archs/dcn python setup.py develop
- Python packages:
pip install numpy opencv-python lmdb pyyaml tqdm tensorboardX scikit-video
- Other packages: FFMPEG
- TensorBoard:
- PyTorch >= 1.1:
pip install tb-nightly future
- PyTorch >= 1.1:
运行codes/data_scripts下的 video_to_img_lmdb.py 生成训练用的png和lmdb文件.
在codes目录下,运行 python train.py -opt options/train/ly_20191123_edvr_continue_ft.yml
- 修改codes/naic_inference.py 中的video_dir为待处理视频所在的目录
- 修改codes/naic_inference.py 中的save_dir为你期望结果保存目录
- 在codes目录下,运行
python naic_inference.py