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

dataset #2

Closed guiji0812 closed 5 years ago

guiji0812 commented 5 years ago

hi, how to get the first and last two hr images when training since use 5 frames every time and make the middle image as the reffrence image

YapengTian commented 5 years ago

During training, you can either use padding as in eval.py or ignore these frames.