Week 2 assignment 1 all pixels are identical

Hello,
I’m stuck in 3.2 - The Convolutional Block

I’ve somehow gotten a model with the correct size and number of Layers, but all the pixels contain the data that should be in the (0,0) pixel:
tf.Tensor(
[[[0. 0.66683817 0. 0. 0.88853896 0.5274254 ]
[0. 0.66683817 0. 0. 0.88853896 0.5274254 ]]

[[0. 0.66683817 0. 0. 0.88853896 0.5274254 ]
[0. 0.66683817 0. 0. 0.88853896 0.5274254 ]]], shape=(2, 2, 6), dtype=float32)

Do you have a hint how I could have ended up like that ?

Best regards

Christian

Ok I’ve solved it: i was applying the stride also in the 2nd convolution.

1 Like

It’s great that you were able to solve it under your own power! Onward! :nerd_face: