About the value of 'train_ps' in training mode

[SUNJIMENG]

Thank you for your work. If the input size of the network is 256 x 256, should I increase one encoder and decoder layer to keep the bottleneck layer's feature size is 8 (equal to window-size)? Or keep the layer num and the bottleneck's is 16, which one performs better, please? The former will bring more computation cost. In another way, is it a trick that the feature size in bottleneck is equal to the window size, please?