chengven027-intellif opened a new issue, #12708: URL: https://github.com/apache/tvm/issues/12708
hi，tvm When I load a onnx model. I found the tvm result is different ONNX-RT result. The reason is because of `batch_norm` op. But I can`t found any error with the op. Can you help me to analyze it. Thanks very much. ### Expected behavior The model result between tvm and onnx-RT is equal. ### Actual behavior The model result between tvm and onnx-RT is not equal. ### Environment x86 ### Steps to reproduce run the model with tvm and onnx-RT. -- 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]
