# Onnx to torchrt convertion error

**URL:** <https://forums.developer.nvidia.com/t/onnx-to-torchrt-convertion-error/202590>\
**Category:** TensorRT\
**Tags:** tf-trt, tensorrt, onnx, cuda, jetson\
**Created:** [February 6, 2022, 1:40pm UTC](https://forums.developer.nvidia.com/t/onnx-to-torchrt-convertion-error/202590 "2022-02-06T13:40:00Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![HirenNamera](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@HirenNamera](https://forums.developer.nvidia.com/u/HirenNamera)\
**Post date:** [February 6, 2022, 1:40pm UTC](https://forums.developer.nvidia.com/t/onnx-to-torchrt-convertion-error/202590/1 "2022-02-06T13:40:00Z")

</div>

## Description

I am trying to convert pytorch model to tensorrt engine.  
I had successfully converted pytorch model to onnx but when converting onnx to tensorrt engine it is given below error.

## Environment

**TensorRT Version** : 7.2.1  
**GPU Type** : Jetson tx1  
**CUDA Version** : 10.2

Please include:

- main repo [GitHub - VITA-Group/DeblurGANv2: [ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang](https://github.com/VITA-Group/DeblurGANv2)

[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2590  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Conv\_498 [Conv] inputs: [2000 → (1, 1088, 60, 80)], [2589 → (256, 1088, 1, 1)], [2590 → (256)],  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:450: Convolution input dimensions: (1, 1088, 60, 80)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Conv\_498 for ONNX node: Conv\_498  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:533: Using kernel: (1, 1), strides: (1, 1), prepadding: (0, 0), postpadding: (0, 0), dilations: (1, 1), numOutputs: 256  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:534: Convolution output dimensions: (1, 256, 60, 80)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2588 for ONNX tensor: 2588  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Conv\_498 [Conv] outputs: [2588 → (1, 256, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Relu\_499 [Relu]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2588  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Relu\_499 [Relu] inputs: [2588 → (1, 256, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Relu\_499 for ONNX node: Relu\_499  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2003 for ONNX tensor: 2003  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Relu\_499 [Relu] outputs: [2003 → (1, 256, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Conv\_500 [Conv]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2003  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2592  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2593  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Conv\_500 [Conv] inputs: [2003 → (1, 256, 60, 80)], [2592 → (384, 256, 3, 3)], [2593 → (384)],  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:450: Convolution input dimensions: (1, 256, 60, 80)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Conv\_500 for ONNX node: Conv\_500  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:533: Using kernel: (3, 3), strides: (2, 2), prepadding: (0, 0), postpadding: (0, 0), dilations: (1, 1), numOutputs: 384  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:534: Convolution output dimensions: (1, 384, 29, 39)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2591 for ONNX tensor: 2591  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Conv\_500 [Conv] outputs: [2591 → (1, 384, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Relu\_501 [Relu]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2591  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Relu\_501 [Relu] inputs: [2591 → (1, 384, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Relu\_501 for ONNX node: Relu\_501  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2006 for ONNX tensor: 2006  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Relu\_501 [Relu] outputs: [2006 → (1, 384, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Conv\_502 [Conv]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2000  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2595  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2596  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Conv\_502 [Conv] inputs: [2000 → (1, 1088, 60, 80)], [2595 → (256, 1088, 1, 1)], [2596 → (256)],  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:450: Convolution input dimensions: (1, 1088, 60, 80)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Conv\_502 for ONNX node: Conv\_502  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:533: Using kernel: (1, 1), strides: (1, 1), prepadding: (0, 0), postpadding: (0, 0), dilations: (1, 1), numOutputs: 256  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:534: Convolution output dimensions: (1, 256, 60, 80)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2594 for ONNX tensor: 2594  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Conv\_502 [Conv] outputs: [2594 → (1, 256, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Relu\_503 [Relu]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2594  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Relu\_503 [Relu] inputs: [2594 → (1, 256, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Relu\_503 for ONNX node: Relu\_503  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2009 for ONNX tensor: 2009  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Relu\_503 [Relu] outputs: [2009 → (1, 256, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Conv\_504 [Conv]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2009  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2598  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2599  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Conv\_504 [Conv] inputs: [2009 → (1, 256, 60, 80)], [2598 → (288, 256, 3, 3)], [2599 → (288)],  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:450: Convolution input dimensions: (1, 256, 60, 80)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Conv\_504 for ONNX node: Conv\_504  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:533: Using kernel: (3, 3), strides: (2, 2), prepadding: (0, 0), postpadding: (0, 0), dilations: (1, 1), numOutputs: 288  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:534: Convolution output dimensions: (1, 288, 29, 39)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2597 for ONNX tensor: 2597  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Conv\_504 [Conv] outputs: [2597 → (1, 288, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Relu\_505 [Relu]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2597  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Relu\_505 [Relu] inputs: [2597 → (1, 288, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Relu\_505 for ONNX node: Relu\_505  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2012 for ONNX tensor: 2012  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Relu\_505 [Relu] outputs: [2012 → (1, 288, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Conv\_506 [Conv]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2000  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2601  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2602  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Conv\_506 [Conv] inputs: [2000 → (1, 1088, 60, 80)], [2601 → (256, 1088, 1, 1)], [2602 → (256)],  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:450: Convolution input dimensions: (1, 1088, 60, 80)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Conv\_506 for ONNX node: Conv\_506  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:533: Using kernel: (1, 1), strides: (1, 1), prepadding: (0, 0), postpadding: (0, 0), dilations: (1, 1), numOutputs: 256  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:534: Convolution output dimensions: (1, 256, 60, 80)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2600 for ONNX tensor: 2600  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Conv\_506 [Conv] outputs: [2600 → (1, 256, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Relu\_507 [Relu]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2600  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Relu\_507 [Relu] inputs: [2600 → (1, 256, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Relu\_507 for ONNX node: Relu\_507  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2015 for ONNX tensor: 2015  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Relu\_507 [Relu] outputs: [2015 → (1, 256, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Conv\_508 [Conv]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2015  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2604  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2605  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Conv\_508 [Conv] inputs: [2015 → (1, 256, 60, 80)], [2604 → (288, 256, 3, 3)], [2605 → (288)],  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:450: Convolution input dimensions: (1, 256, 60, 80)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Conv\_508 for ONNX node: Conv\_508  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:533: Using kernel: (3, 3), strides: (1, 1), prepadding: (1, 1), postpadding: (1, 1), dilations: (1, 1), numOutputs: 288  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:534: Convolution output dimensions: (1, 288, 60, 80)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2603 for ONNX tensor: 2603  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Conv\_508 [Conv] outputs: [2603 → (1, 288, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Relu\_509 [Relu]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2603  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Relu\_509 [Relu] inputs: [2603 → (1, 288, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Relu\_509 for ONNX node: Relu\_509  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2018 for ONNX tensor: 2018  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Relu\_509 [Relu] outputs: [2018 → (1, 288, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Conv\_510 [Conv]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2018  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2607  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2608  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Conv\_510 [Conv] inputs: [2018 → (1, 288, 60, 80)], [2607 → (320, 288, 3, 3)], [2608 → (320)],  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:450: Convolution input dimensions: (1, 288, 60, 80)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Conv\_510 for ONNX node: Conv\_510  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:533: Using kernel: (3, 3), strides: (2, 2), prepadding: (0, 0), postpadding: (0, 0), dilations: (1, 1), numOutputs: 320  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:534: Convolution output dimensions: (1, 320, 29, 39)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2606 for ONNX tensor: 2606  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Conv\_510 [Conv] outputs: [2606 → (1, 320, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Relu\_511 [Relu]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2606  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Relu\_511 [Relu] inputs: [2606 → (1, 320, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Relu\_511 for ONNX node: Relu\_511  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2021 for ONNX tensor: 2021  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Relu\_511 [Relu] outputs: [2021 → (1, 320, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: MaxPool\_512 [MaxPool]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2000  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: MaxPool\_512 [MaxPool] inputs: [2000 → (1, 1088, 60, 80)],  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: MaxPool\_512 for ONNX node: MaxPool\_512  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2022 for ONNX tensor: 2022  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: MaxPool\_512 [MaxPool] outputs: [2022 → (1, 1088, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Concat\_513 [Concat]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2006  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2012  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2021  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2022  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Concat\_513 [Concat] inputs: [2006 → (1, 384, 29, 39)], [2012 → (1, 288, 29, 39)], [2021 → (1, 320, 29, 39)], [2022 → (1, 1088, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Concat\_513 for ONNX node: Concat\_513  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2023 for ONNX tensor: 2023  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Concat\_513 [Concat] outputs: [2023 → (1, 2080, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Conv\_514 [Conv]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2023  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: fpn.lateral4.weight  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Conv\_514 [Conv] inputs: [2023 → (1, 2080, 29, 39)], [fpn.lateral4.weight → (256, 2080, 1, 1)],  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:450: Convolution input dimensions: (1, 2080, 29, 39)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:141: Registering layer: Conv\_514 for ONNX node: Conv\_514  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:533: Using kernel: (1, 1), strides: (1, 1), prepadding: (0, 0), postpadding: (0, 0), dilations: (1, 1), numOutputs: 256  
[02/06/2022-19:02:25] [V] [TRT] builtin\_op\_importers.cpp:534: Convolution output dimensions: (1, 256, 29, 39)  
[02/06/2022-19:02:25] [V] [TRT] ImporterContext.hpp:116: Registering tensor: 2024 for ONNX tensor: 2024  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:179: Conv\_514 [Conv] outputs: [2024 → (1, 256, 29, 39)],  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:103: Parsing node: Pad\_515 [Pad]  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:119: Searching for input: 2024  
[02/06/2022-19:02:25] [V] [TRT] ModelImporter.cpp:125: Pad\_515 [Pad] inputs: [2024 → (1, 256, 29, 39)],  
ERROR: builtin\_op\_importers.cpp:2191 In function importPad:  
[8] Assertion failed: mode == “constant” && value == 0.f && “This version of TensorRT only supports constant 0 padding!”  
[02/06/2022-19:02:25] [E] Failed to parse onnx file  
[02/06/2022-19:02:25] [E] Parsing model failed  
[02/06/2022-19:02:25] [E] Engine creation failed  
[02/06/2022-19:02:25] [E] Engine set up failed  
&&&& FAILED TensorRT.trtexec # /usr/src/tensorrt/bin/trtexec --onnx=deblur.onnx --verbose

---

<div class="post-metadata">

**Author:** ![spolisetty](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/spolisetty/32/14047_2.png) [@spolisetty](https://forums.developer.nvidia.com/u/spolisetty)\
**Post date:** [February 7, 2022, 1:44pm UTC](https://forums.developer.nvidia.com/t/onnx-to-torchrt-convertion-error/202590/2 "2022-02-07T13:44:10Z")

</div>

Hi,

Looks like you’re using an old version of TensorRT. I believe this issue has been fixed in the new release. We recommend you to please try on latest TensorRT verison 8.2  
Please refer following similar issue for more details.  
[https://github.com/NVIDIA/TensorRT/issues/1019](https://github.com/NVIDIA/TensorRT/issues/1019)

Thank you.

---

<div class="post-metadata">

**Author:** ![HirenNamera](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@HirenNamera](https://forums.developer.nvidia.com/u/HirenNamera)\
**Post date:** [February 7, 2022, 5:18pm UTC](https://forums.developer.nvidia.com/t/onnx-to-torchrt-convertion-error/202590/3 "2022-02-07T17:18:29Z")

</div>

I can not use latest version due to business reason. Can I do any other workaround with model or add that layer in trt 7.

---

<div class="post-metadata">

**Author:** ![spolisetty](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/spolisetty/32/14047_2.png) [@spolisetty](https://forums.developer.nvidia.com/u/spolisetty)\
**Post date:** [February 8, 2022, 3:41pm UTC](https://forums.developer.nvidia.com/t/onnx-to-torchrt-convertion-error/202590/4 "2022-02-08T15:41:06Z")

</div>

Hi,

Unfortunately there is no workaround, if we are using non-0 or non-constant padding TRT 7 cannot handle it.

Thank you.
