Course 4 - Week 3 - MobileNet

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi!

I have few points to clarify re: MobileNet programming assignment. I have already passed the test!
Will appreciate clarifications please.

  1. What is the intuition to use linear activation in the final layer rather than Sigmoid? I tried with Sigmoid activation and it performed a bit better.

  2. With linear activation, how model.fit calculates loss for learning? Label y is either 0 or 1 whereas calculated y^ is a real number. Does it use liner output (y^) as it is for loss calculation?

  3. What is behaviour of data augmentation layer during predict() and evaluate()?

  4. I found based on the p that data is processed in different order in the below two calls:

             p = model2.predict(images, batch_size=BATCH_SIZE)

         p = model2.predict(validation_dataset)

    whereas ‘images’ is derived from validation_dataset by appending images in the order
    of batches. ‘images’ shape is (65, 160, 160, 3).

    Any insight on how predict() works on dataset?

2

Hi rajsura82,

For your first two questions you can have a look here.

As to your third question, data is only augmented during training. See RandomFlip layer and RandomRotation layer.

As to your fourth question, have a look around at stackoverflow, e.g. here or here, or do a search there to find additional information.

3

Thanks for your response. Links you provided answer my queries.