TensorRT output has a different size as PyTorch/ONNX

AI & Data Science Deep Learning (Training & Inference) TensorRT
#1

Hi,

I have a encoder decoder network with input and output [-1,1,224,224].
From tensorRT ( 6.0.1.5 ) I get [-1, 1, 219,219 ].

This seems a bug to me.

Any help?

Greetings,

Roos

#2

Addition:
For example with the following pytorch layer:

ConvTranspose2d(in, out, 1, 2,padding = 0,output_padding = 1)

with 7x7 input gives 14x14 output in pytorch/onnx, but 13x13 in tensorRT :-(

Greetings,

Roos

#3

Hi,

Can you provide the following information so we can better help?
Provide details on the platforms you are using:
o Linux distro and version
o GPU type
o Nvidia driver version
o CUDA version
o CUDNN version
o Python version [if using python]
o Tensorflow and PyTorch version
o TensorRT version

Also, please share the script & model file to reproduce the issue.

Thanks