After implementing the layers in the sequential model and running the cell, I encountered the following error:
AttributeError: The layer has never been called and thus has no defined output shape.
I have checked the parameters of each layer, and made sure the are commas separating the layers in the list (of the sequential model). I wonder if there are other reasons that may cause this error. Thank you.
Update: Added input_shape=(64, 64, 3) as a parameter to the first ZeroPadding2D layer and solved the error. It was somewhat confusing because the data format is written as (batch_size, rows, cols, channels) in the documentation, but I guess in this case it is the size of a single example without needing to specify the batch size (m) in front (i.e., not (m, 64, 64, 3)).