Dynamic input shape get wrong result


we convert unet from stable-diffusion onnx model with dynamic inputshape
convert command:
./trtexec --onnx=unet.onnx --saveEngine=unet.plan --verbose --fp16 --minShapes=2x4x32x32 --optShapes=2x4x32x32 --maxShapes=2x4x96x96
when inputshape=2x4x40x64 or 2x4x64x64 get the right result but when inputshape=2x4x64x40 get the wrong result


TensorRT Version:
GPU Type: A10
Nvidia Driver Version: 470.129.06
CUDA Version: cuda 11.3
CUDNN Version: 8.05
Operating System + Version: 20.04


Could you please share with us the minimal issue repro ONNX model and script to try from our end for better debugging.

Thank you.

we solve this problem tricky by use multi profile

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.