weichao zhao

question about the training process

4

Hi Yang: I use the code that you release in the github, and I run the train code with the parameter: two GPUs, batch_size 256, lr_rate 0.0005, now training 26000...

hello, thanks for your devotion for this wonderful work! I check your code /data/datasets/ehf.py and I want to know that how to create the ehf.npz file, could you share the...