Creat a self -defined activation function

#1

I want to create an activation function, y=x^2, and call it in my network , how to realize it?

#2

y=torch.pow(x,2) ?

#4

how to make it as activation function

#5

For ReLU activation, we do this:

out = some_convolution(input)
out = nn.functional.relu(out)  # relu activation

In the same way, you can realize your quadratic activation as,

out = some_convolution(input)
out = torch.pow(out, 2)  # quadratic activation