Skip to content

Onnx model checker error #513

Answered by heborras
ElMahdiElAnnabi asked this question in Q&A
Discussion options

You must be logged in to vote

Hi @ElMahdiElAnnabi,
FINN uses custom node types in it's ONNX graphs to represent functionality not supported by the standard ONNX op-set. This is for example quantization below 8 bits, Multi-threshold activations and so on. Since these nodes are not part of the official op-set the onnx model checker will say that it doesn't know what to do with these nodes. So, the error which you are seeing is in a sense expected behavior, due to how FINN implements its custom ops.

Replies: 2 comments

Comment options

You must be logged in to vote
0 replies
Answer selected by ElMahdiElAnnabi
Comment options

You must be logged in to vote
0 replies
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants