jkempson

Results 2 comments of jkempson

TypeError: list indices must be integers or slices, not NoneType

Having exactly this issue. @henriz can you post the code you changed in utils.py? There are obviously other issues here. Would probably help to post model numbers. I'm trying to...

The layer "sequential_1 has multiple inbound nodes, with different input shapes. Hence the notion of "input shape" is ill-defined for the layer. Use `get_input_shape_at(node_index)` instead.

Same. Looks like something changed in Keras?