Course 4 Week 1 Programming Assignment: Convolution Model Application

model = tf.keras.Sequential([
            ## ZeroPadding2D with padding 3, input shape of 64 x 64 x 3
            ## Conv2D with 32 7x7 filters and stride of 1
            ## BatchNormalization for axis 3
            ## ReLU
            ## Max Pooling 2D with default parameters
            ## Flatten layer
            ## Dense layer with 1 unit for output & 'sigmoid' activation

Even after following this exact sequence, I am getting this error:
Test failed
Expected value

[‘ReLU’, (None, 64, 64, 32), 0]

does not match the input value:

[‘Activation’, (None, 64, 64, 32), 0]

Hi @swapnilvishwakarma,

I believe you have to mention/pass the parameter as relu instead of activation. or vice versa.

Let me know if changing this helps.


You have not followed the instructions closely enough: you are using the generic Activation “layer” function and passing “relu” as the argument. That is logically equivalent, but they are expecting you to use the specific ReLU layer function instead. They give you the link to the documentation for that function in the instructions for that section.

1 Like

Thanks @paulinpaloalto
It worked :slightly_smiling_face:

Thanks @paulinpaloalto
It worked :slightly_smiling_face: