Which Module or layer is consuming More Time and Ops?

1

How to know which particular layer or Module (ASPP, Vortex Pooling) is consuming more Time and Operations in a Model Architecture?

2

I think you could add some code for timing in your forward function. For example,

def forward(self, x):
    start = time.time()
    out = self.aspp(x)
    print(time.time() - start)

I am new to pytorch, so not sure if there is other better way to do it.

3

You could use the pytorch bottleneck to do so.

Note: if you want to do timing like this, you need to call

torch.cuda.synchronize()

before calling time.time() due to the asynchronous behavior of cuda operations.

3 Likes