Jaehun Ryu
Jaehun Ryu
https://github.com/pytorch/examples/blob/dcdabc22b305d2f2989c6f03570dfcd3919e8a5b/super_resolution/data.py#L41 I think resizing LANCZOS interpolation is better than default BILINEAR `Resize(crop_size // upscale_factor,interpolation=Image.LANCZOS)` __How does downsampling work in a normal SR?__ And In the Set5 dataset, I found that...
Hello , There are some issues using onnx file created in Pytorch. below code make simple NN and export onnx file using PyTorch. ``` import torch import torch.nn as nn...
Hi , TASO is only concerned about 2d batch norm case but some network has 1d or 3d batch norm case. https://github.com/jiazhihao/TASO/blob/f11782c4db180ad7d1e7ff7f4bb82e574ac3b6b8/src/core/batchnorm.cc#L72 I have a question about the above code....