-
Hi, I am quantizing a CNN model using onnxruntime. The target hardware supports only ONNX IR version 7 and Opset 13. Is it possible to restrict onnxruntime to use at maximum a specific ONNX IR version and Opset? Or is the ONNX IR and the Opset applied, that have been used when creating the ONNX file? Thanks, |
Beta Was this translation helpful? Give feedback.
Answered by
faxu
Oct 26, 2022
Replies: 1 comment
-
You should be able to specify opset version during model conversion. |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
ai2ys
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
You should be able to specify opset version during model conversion.