search

yjn870 / WDSR-pytorch

PyTorch implementation of Wide Activation for Efficient and Accurate Image Super-Resolution (CVPR Workshop 2018)
https://arxiv.org/abs/1808.08718
15 stars 4 forks source link

an issue with weight_norm #2

Open MohitLamba94 opened 4 years ago

MohitLamba94 commented 4 years ago

torch.nn.utils.weight_norm does the crucial weight re-parametrization during training, but does it happen during testing also? If yes should not they be removed before proceeding for testing?