search

Francis0625 / Omni-SR

[CVPR2023] Implementation of ''Omni Aggregation Networks for Lightweight Image Super-Resolution".
192 stars 12 forks source link

Training settings #3

Closed duweihua closed 1 year ago

duweihua commented 1 year ago

I have read the paper, and try to train the model with public code. However, the training settings differ with the writing in paper. How to computer the iterations, epochs and batch_size ? image

image

Francis0625 commented 1 year ago

Sorry for these misalignments, and we will update the paper and the code. Using the provied training setting, you can achieve better results than the reported results in the paper. If you have more questions, you can chat with vx: 18616863691.