I want to us maxout activation in pytorch, and I use torch.max() function to implement.
class Maxout(nn.Module):
def __init__(self):
super(Maxout, self).__init__()
def forward(self, x, y):
return x.max(y)
Is it right?
I want to us maxout activation in pytorch, and I use torch.max() function to implement.
class Maxout(nn.Module):
def __init__(self):
super(Maxout, self).__init__()
def forward(self, x, y):
return x.max(y)
Is it right?
I also have the same question. In my case, I use the code below. Can anyone help?
class Maxout(nn.Module):
def __init__(self):
super(Maxout, self).__init__()
def forward(self, x, y):
return torch.max(x,y)```
You can define a layer like that but it’s not necesary, you can call torch max in forward and it will do the same.
You can also check out this MaxOut2D implementation that performs maxout on the channels for an input that is C x H x W