Exercise 2 - alpaca_model (linear)

In Programming Assignment: Transfer Learning with MobileNet at Exercise 2 - alpaca_model
when I use sigmoid as activation function does not pass test when I use linear as activation function it is pass why?
I think in binary classification should use sigmoid.

Please pay attention to the logits flag in the loss function:


When logits is True, softmax is not required as the output activation function. See this as well.

1 Like

Right: the point is that the sigmoid (or softmax) is included, but it’s being handled internally by the loss function instead of explicitly in your code. Here’s a thread which explains why they do it that way.

1 Like