Why don't I need to specify activation='sigmoid'?

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

In Week-4 of the transfer learning assignment, the last layer is “use a prediction layer with one neuron (as a binary classifier only needs one)”:

outputs = tf.keras.layers.Dense(1)(x)

Why can’t I use:
outputs = tf.keras.layers.Dense(1, activation='sigmoid')(x)

This will report an error saying that ‘linear’ doesn’t match with sigmoid. Why is that?

2

Does this help?

3

@balaji.ambresh Is that because from_logit=True has the same effect of ‘activation=sigmoid’?

4

You are correct. See this