When running the code in the section 5.5.1, it gives me the following error.
InvalidArgumentError: Shapes of all inputs must match: values[0].shape = [1,400,400,64] != values[1].shape = [1,200,200,128] [Op:Pack] name: packed
And the stack trace points to
—> 24 a_C_unrolled = tf.transpose(tf.reshape(content_output, shape=[n_H*n_W, n_C]))
that is what I used the above code to compute a_C_unrolled.
I also printed out the shape of content_target and style_targets and their shapes do not match:
Content shape is [<tf.Tensor: shape=(1, 400, 400, 64), dtype=float32, numpy=
and the other is <tf.Tensor: shape=(1, 200, 200, 128), dtype=float32, numpy=