Week 2 Exercise 3 - ResNet50

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi! I am getting the following error in this exercise - ValueError: Operands could not be broadcast together with shapes (2, 2, 512) (8, 8, 512)

My code for reference:

### START CODE HERE
    
    ## Stage 3 (≈4 lines)
    X = convolutional_block(X, f = 3, filters = [128,128,512], s = 2)
    X = identity_block(X, 3, [128,128,512])
    X = identity_block(X, 3, [128,128,512])
    X = identity_block(X, 3, [128,128,512])
    
    ## Stage 4 (≈6 lines)
    X = convolutional_block(X, f = 3, filters = [256, 256, 1024], s = 2)
    X = identity_block(X, 3, [256, 256, 1024])
    X = identity_block(X, 3, [256, 256, 1024])
    X = identity_block(X, 3, [256, 256, 1024])
    X = identity_block(X, 3, [256, 256, 1024])
    X = identity_block(X, 3, [256, 256, 1024])

    ## Stage 5 (≈3 lines)
    X = convolutional_block(X, f = 3, filters = [512, 512, 2048], s = 2)
    X = identity_block(X, 3, [512, 512, 2048])
    X = identity_block(X, 3, [512, 512, 2048])

    ## AVGPOOL (≈1 line). Use "X = AveragePooling2D(...)(X)"
    X = tf.keras.layers.AveragePooling2D(pool_size=(2, 2), strides=None, padding='valid')

### END CODE HERE

How do I fix this error?

2

Hi mansi,

Look at the suggestion for the AveragePooling2D layer. Then look at your code. What are you missing? Good luck!

3

I have the same problem and not sure whats wrong really?