Zhenhua Wang

@mdztravelling Thank you for reporting this issue. Could you help to check the input shape of Slice in your case?

@mdztravelling By "the input shape of Slice", I mean the real shape - with input shape profile, what the shape of it should be. `-1` would just mean that the...

We have a fix in TensorRT, will be included in the next release.

@Tian14267 Thank you for reporting this issue! I looked into your model, the problem is that the shapes of the two branch graphs of `If_501` node are different, see as...

@Tian14267 What's the error you are getting in your new model? I am getting ``` [05/23/2022-05:47:05] [E] [TRT] ModelImporter.cpp:773: While parsing node number 12 [RandomNormalLike -> "238"]: [05/23/2022-05:47:05] [E] [TRT]...

Have you changed your python code to use the new ONNX model? `onnx2trt` is the parser in your code.

For the `RandomNormalLike` issue, could you please create a new issue to track? (as this issue is about the model definition.

@wikipedia2008 Thank you for reporting this issue! The log seems related to the limitation of data type w.r.t. dynamic shapes. Could you please try TensorRT 8.4 EA?

@duduscript We don't fix any 8.2 issues anymore. Could you deploy your model with 8.4? And, have you tried the solution mentioned by @faithfulnguyen https://github.com/onnx/onnx-tensorrt/issues/784#issuecomment-1022059925

@duduscript Glad to hear that. Closing this issue. Feel free to reopen if any furthur issues.