pytorch-SRDenseNet icon indicating copy to clipboard operation
pytorch-SRDenseNet copied to clipboard

Is transposing needed?

Open IanYeung opened this issue 6 years ago • 1 comments

It seems that you do not transpose the data after reading from h5 file. The data in MATLAB is organized in (H, W, C, N). However, after reading it from h5 file in Python, it is organized in a reverse setting: (N, C, W, H). And PyTorch needs (N, C, H, W). So is it necessary to transpose the data? Thanks!

IanYeung avatar Jun 06 '18 03:06 IanYeung

Hi @IanYeung. Since rotation/flipping are applied as augmentation, and the patch is in squared shape, it actually makes not difference between (N, C, W, H) and (N, C, H, W). Please let me know if you find the transposition could help improve the performance.

twtygqyy avatar Jun 07 '18 04:06 twtygqyy