leandron commented on PR #12040: URL: https://github.com/apache/tvm/pull/12040#issuecomment-1181481152
> @leandron could you comment more about what's changing here? Onnx changed the models to have variable batch size on the input. The new version is causing two issues: * we need to specify the input shape when using it * It fails on autotuning This pr just locks the model in the version we were using before. I will raise the appropriate issues, but wanted to be sure the tutorial were not broken first. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
