Week3 assignment 2 unet Exercise 1 - conv_block

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Dear Mentor,
I am facing the problem that exercise give me all test passed message plus error, and that error create problem in later stage of the assignment when i am trying to implement Unet.
next_layer = tf.keras.layers.MaxPool2D(pool_size=(2, 2))(conv).
error
ValueError: Input 0 of layer max_pooling2d_3 is incompatible with the layer: expected ndim=4, found ndim=0. Full shape received:

2

Hi Afsar_Khan,

It looks like the code preceding the code you provide causes the number of dimensions to diverge from the dimensions expected by the MaxPool2D layer. It may help to look again at the description of the conv_block as provided just above UNQ_C1 and see if you implemented those preceding layers correctly.

Good luck!