TensorRT group convolution get wrong results


When run convolution with groups != 1 in TensorRT8.2.0, get wrong results.


TensorRT Version: 8.2.0
GPU Type: 2070super
Operating System + Version: Ubuntu 18.04 LTS
Python Version (if applicable): 3.8

Relevant Files

go GitHub - iilialsa/groupConvolution: Test group convolution in trt8.2.0 ., see my test code.

Steps To Reproduce

When set convolution channel_in=28, channel_out=28, groups=4, it gets right results.
When set convolution channel_in=32, channel_out=32, groups=4, it gets wrong results.

I test this in trt7.x.x, it always get right results. Seems like a bug in trt8.2.0.

Hi, Please refer to the below links to perform inference in INT8


I am not using int8, my problem happens in fp32.


Could you please provide issue repro test data and steps, onnx model to try from our end for better debugging.

Thank you.

Hi, @spolisetty , sorry for late reply.
My test onnx model just has a convolution layer.
You can run following code to see the different result between pytorch and tensorrt.
code: common.py (6.6 KB)
groupconv.py (3.0 KB)
onnx:groupconv.onnx (9.4 KB)
results:result.txt (8.7 KB)

It works well in docker, so my local tensorrt may not be installed well. Sorry to ask this problem.