How do I trace back to offending network-layer in my python code when an error occurs during CoreML-conversion #2152
Labels
question
Response providing clarification needed. Will not be assigned to a release. (type)
❓Question
When I encounter an error during
convert_nodes
, is there a way to trace back to what part of my network layers caused this.Currently I can inspect what node, and its op-name & operands and try to guess what part of my network could have originated it.
But as you can imagine there could be many source-points that could have triggered this.
Is there any way we can pin-point this more easily? Any additional debugging I should enable(if so, how do I go about doing this?)
TIA
The text was updated successfully, but these errors were encountered: