sanghyun-son / EDSR-PyTorch

PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)
MIT License
2.42k stars 668 forks source link

about video output result #261

Open jsh-me opened 4 years ago

jsh-me commented 4 years ago

Hi thank you for sharing code. I trained my own dataset and used my model with this command:

python main.py --scale 4 --pre_train '../experiment/path/to/mymodel' --test_only --data_test video --dir_demo '../path/to/video' --save_results

but the result is strange. image

How can I use the trained model? thanks!