Chenly1993

Results 3 issues of Chenly1993

I just used the sample data with ground truth npy, and use the resampling.py to unwarp the imgs. The results are not good. The background cannot be cropped. ![image](https://user-images.githubusercontent.com/28524540/93749574-b265d480-fc2c-11ea-92d8-9069f0fed459.png)

Thank you for your contribution! Now ,I want to use it for 256 dimensional labels classification. Each label is 0 or 1. But the loss of training is strange. It...