Exercise 6 - train_step

Implement the train_step() function for transfer learning

Use the Adam optimizer to minimize the total cost J.

Use a learning rate of 0.03.

Adam Optimizer documentation

You will use tf.GradientTape to update the image.

Within the tf.GradientTape():

Compute the encoding of the generated image using vgg_model_outputs

Compute the total cost J, using the variables a_C, a_S and a_G

Use alpha = 10 and beta = 40.

MAYBE BROKEN LINK AT tf.GradientTape()

(I meant to do only a report about this)

Have a nice day.