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

Loss Module #13

Closed YoungJoongUNC closed 4 years ago

YoungJoongUNC commented 4 years ago

While I was trying to run the train.py, I faced the following error, because their is no loss code. Could you provide the loss code?

Thank you.

Traceback (most recent call last): File "train.py", line 4, in from loss import get_loss_fn ModuleNotFoundError: No module named 'loss'

YapengTian commented 4 years ago

Sorry, the code is not fully ready since I am working on incoming ddls. I have added the loss function and slightly modified the train.py. I used the Temple sequence from SPMCs set https://github.com/jiangsutx/SPMC_VideoSR as validation set.

YoungJoongUNC commented 4 years ago

Thank you for your fast reply :)

YoungJoongUNC commented 4 years ago

Also, may I ask if you could upload the SR_datasets.py? train.py refers to it.

train.py line 5: from SR_datasets import *

YapengTian commented 4 years ago

Yes, I have added it. Please check the SR_datasets.py.

YoungJoongUNC commented 4 years ago

Thank you so much for the fast feedback :D

YapengTian commented 4 years ago

Sorry for the inconvenience.