search

YapengTian / TDAN-VSR-CVPR-2020

TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution, CVPR 2020
MIT License
400 stars 62 forks source link

x2 model #34

Closed ycjing closed 3 years ago

ycjing commented 3 years ago

Hi @YapengTian

Thank you for the great work! Is it possible to train a 2x VSR model with the training code? Thank you!

Best, Yongcheng

YapengTian commented 3 years ago

Yes, it can train a 2x model after changing the upscaling factor to 2 from 4.

ycjing commented 3 years ago

Hi @YapengTian

Thank you for the response! I appreciate it. May I ask is there anything else that should be changed in the code other than the parameter of the upscaling factor? Thank you!

Best, Yongcheng

YapengTian commented 3 years ago

No, I think only the upscaling factor parameter in train and dataloader functions needs to be modified.

ycjing commented 3 years ago

Hi @YapengTian

Thank you for the quick response! I really appreciate it. Wish you all the best!

Best, Yongcheng