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.

Exercise 2 - alpaca_model (linear)

balaji.ambresh August 16, 2023, 12:04pm 2

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

loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),

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

1 Like

Topic		Replies	Views
Transfer_learning_with_MobileNet: Convolutional Neural Networks	1	496	November 22, 2021
Week2- programming assignment- mobile net- activation funcation Convolutional Neural Networks	2	537	November 3, 2021
Alcapa_model: why not sigmoid at prediction? Convolutional Neural Networks	5	633	April 25, 2021
[Week 2] Assignment 2, Exercise 2 : Why should we choose 'linear' output instead of sigmoid output if it's binary classification problem and not linear regression? Convolutional Neural Networks	1	757	April 19, 2021
Transfer Learning Assignment - Binary Classification Question Convolutional Neural Networks	2	513	July 9, 2023