Tony-Tseng
Results
3
comments of
Tony-Tseng
I think it is designed intentionally for the pseudo burst architecture. If we modify the input to 5 dim (Batch, Burst, feat, H/2, W/2), we have to convert conv2d to...
![Screen Shot 2020-05-18 at 4 27 49 PM](https://user-images.githubusercontent.com/35694556/82191075-940d6680-9924-11ea-8c24-9f2d0e3f1813.png) I can train the model after modifying networks.py.
We also need to modify the input channel of the fine SR Decoder.