C4 W2 Exercise 2

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi,

I have a question about course 4 week 2 exercise 2 for def alpaca_model(image_shape=IMG_SIZE, data_augmentation=data_augmenter()): , particularly this line below

    # use a prediction layer with one neuron (as a binary classifier only needs one)
    outputs =

I omitted my answer here to not break the code honor. When I first tried with sigmoid for activation with Dense function, it failed. I wonder why. Isn’t this for binary classification? Why would the linear activation function work instead?

2

You do not need sigmoid because you specified “from_logits” in the cost layer.

1 Like