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

Training Condition #49

Open reminayano opened 3 years ago

reminayano commented 3 years ago

I created a scale x2 model with the following conditions, but I could not get a better PSNR than bicubic. How did you set the epochs, learning rate, etc. when creating the scale 4 model?

train data (vimeo seplet dataset) ・HR : 448×256 ・LR : 224x128 scale : 2 batchsize : 64 leaning rate : 1e-4 num_epochs : 600

YapengTian commented 3 years ago

Sorry for the very late response. Did you change the scale to 2 in both the train and dataloader code? I think the params are ok.

reminayano commented 3 years ago

Thank you for your response.

Yes, I changed scale at train.py and SR_datasets.py(class VSR_Dataset).