Closed EthanZhangYi closed 5 years ago
batch-size=1 works file since the wight and bias are fix(requires_grad=False in ResNetMulti class)
So for VGG net without Batch Normalization layer, batch_size = 1 is ok for trainning all the parameters? That is very interesting.
batch-size=1 works file since the wight and bias are fix(requires_grad=False in ResNetMulti class)