Week 1 Assignment 2 Exercise 2

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

using a tf.Tensor as a Python bool is not allowed in Graph execution. Use Eager execution or decorate this function with @tf.function.
This is my error when i am executing convolution_model function.
Can someone please help with this?
Below is the part of my code:

Z1 = tf.keras.layers.Conv2D(filters= 8 , kernel_size= (4,4) ,strides = (1,1), padding='same')(input_img)

A1 = tf.keras.layers.ReLU(Z1)

P1 = tf.keras.layers.MaxPool2D(A1, pool_size=(8, 8), strides=(8,8), padding='same')

Z2 = tf.keras.layers.Conv2D(filters= 16 , kernel_size= (2,2), strides = (1,1) , padding='same')(P1)

A2 = tf.keras.layers.ReLU(Z2)

P2 = tf.keras.layers.MaxPool2D(A2, pool_size=(4, 4), strides=(4,4), padding='same')

F = tf.keras.layers.Flatten(P2)
    
outputs = tf.keras.layers.Dense(units=6, activation='softmax')(F)
1 Like
3

@ddashutosh
I think you are missing the (A1) and (A2) parameters after your max pool layer statements.
Also your syntax for the ReLU layers may not be correct.

4

In my code, the A1 and A2 are separate (…) arguments, not embedded in the layer call.

5

It is still showing error for failed test.

6

Please see this other thread for an explanation of the issue.