Open joshylchen opened 3 years ago
you may refer to the original code and adjust it if you want to let this package could pass other parameter.
batch_size of 2 for batchnorm x = [torch.rand(2, *in_size).type(dtype).to(device=device) for in_size, dtype in zip(input_size, dtypes)]
model(*x)
For example in the forward path, I define as def forward(self, input, path1=True):
I realize that when I want to pass summary(model, [(3, 32,32),(True)]) or summary(model, [(3, 32,32),(True)] or summary(model, [(3, 32,32),True]) or summary(model, ((3, 32,32),True))
It either reported as argument must be an iterate or size must be tuple of ints. How could I resolve this to pass other parameters?
Thank you