I am stuck in the Exercise 3 for about 2 hours now, basically my output of the function compute_layer_style_cost is: tf.Tensor(2.9225328, shape=(), dtype=float32)
I don’t know what I am doing wrong. I checked it multiple times, but I cannot find the bug.
I need some light in the end of the tunnel about the things that can go wrong, that make the value about 4 times lower than the correct version.
Thanks for the help!
I managed to find the bug. For people having trouble with this kind of error, please check this post here: Flattening Images in the Logistic Regression Assignment in Course 1 Week 2
It’s great to hear that you were able to find the solution under your own power. Congrats!
For anyone else who sees this, in addition to the thread Fernando links above, there is also this thread which gives a specific example for the flattening that happens in the Art Generation with Neural Style Transfer assignment.