Closed yuanshuai220 closed 7 years ago
@yuanshuai220 SRResNet takes 3-channel patches as input, while VDSR takes 1-channel patches. Please modify the matlab code from VDSR into 3-channel version.
@yuanshuai220 I've uploaded the code for training data generation. Please find them here: https://github.com/twtygqyy/pytorch-SRResNet/tree/master/data
@twtygqyy Thank you very much!
When I run the
python main.py --cuda --batchSize 4
, I got this error.I generated the trianing data with
generate_train.m
from VDSR.