xuguodong

Error in cpp

3

weighted_softmax_loss_layer.cpp的122行，k的范围好像有些问题，上限应该是channels的数量，不是dim，cu文件里的是对的

The asymmetry of KL divergence.

1

Hi, I notice that in the 'train_nasty.py', when the KL divergence is computed, normal teacher's output (output_stu) is regarded as input and nasty teacher's output (output_tch) is regarded as target....

Hi Liheng, General affine transformation or projective transformation can bring black areas at image border. Do these artifacts help network learn trivial shortcuts, such as predicting transformation parameters just according...