Zhenhua Wang

Results 56 comments of Zhenhua Wang

@PhaniShekhar If this is still an issue for you?

@isaacraf95 8.5 gives me different error. I suggest to create another issue for MarkRCNN since the "internal error" is not specific enough. And please share the environment and the command...

Thank you for the advice @andife We are evaluating this and will keep you posted if any update. cc @rajeevsrao

@lansfair If you are looking for convert from PyTorch to TensorRT directly, you might try https://github.com/pytorch/TensorRT; otherwise you can export PyTorch to ONNX and let TensorRT loads the ONNX model.

Which framework generates negative scales? The fix should be in that framework. Negative scales don't seem to be reasonable for me.

Hi @sunhailin-Leo , thank you for raising this issue. TensorRT only supports 2D and 3D Trilu for now. I think this is something TensorRT can enhanced to support your cases....

@sunhailin-Leo Glad to hear that. We will enable 4D+ cases thus you don't need to workaround it.

@taxuezcy Thank you for reporting this issue! As the log shown, your case is not supported in TensorRT 8.2. Could you please try the latest release - TensorRT 8.4 EA?

~~Glad to hear that! As the issue is resolved, I am going to close it. Please let me know if any further issues.~~ @taxuezcy could you help to add "For...