[8] Assertion failed: inputs.at(1).is_weights() && "The input pads is required to be an initializer."

jucic95 · January 12, 2022, 6:41am

Description

ModelImporter.cpp:726: ERROR: builtin_op_importers.cpp:2985 In function importPad:
[8] Assertion failed: inputs.at(1).is_weights() && “The input pads is required to be an initializer.”

Environment

TensorRT Version: 8.0.3.4
GPU Type: 2080Ti
Nvidia Driver Version: 495
CUDA Version: 11.3
CUDNN Version:
Operating System + Version: 18.04
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

Exact steps/commands to build your repro
Exact steps/commands to run your repro
Full traceback of errors encountered

jucic95 · January 12, 2022, 6:43am

above is the Pad in my onnx model, please help me to solve it.

NVES · January 12, 2022, 7:08am

Hi ,
We recommend you to check the supported features from the below link.

You can refer below link for all the supported operators list.
For unsupported operators, you need to create a custom plugin to support the operation

github.com

onnx/onnx-tensorrt/blob/main/docs/operators.md

<!--- SPDX-License-Identifier: Apache-2.0 -->

# Supported ONNX Operators

TensorRT 8.4 supports operators up to Opset 17. Latest information of ONNX operators can be found [here](https://github.com/onnx/onnx/blob/master/docs/Operators.md)

TensorRT supports the following ONNX data types: DOUBLE, FLOAT32, FLOAT16, INT8, and BOOL

> Note: There is limited support for INT32, INT64, and DOUBLE types. TensorRT will attempt to cast down INT64 to INT32 and DOUBLE down to FLOAT, clamping values to `+-INT_MAX` or `+-FLT_MAX` if necessary.

See below for the support matrix of ONNX operators in ONNX-TensorRT.

## Operator Support Matrix

| Operator                  | Supported  | Supported Types | Restrictions                                                                                                           |
|---------------------------|------------|-----------------|------------------------------------------------------------------------------------------------------------------------|
| Abs                       | Y          | FP32, FP16, INT32 |
| Acos                      | Y          | FP32, FP16 |
| Acosh                     | Y          | FP32, FP16 |
| Add                       | Y          | FP32, FP16, INT32 |

This file has been truncated. show original

Thanks!

jucic95 · January 12, 2022, 7:28am

I checked it before and know that tensorrt doesnot support dynamic padding size, however, what I want to do is to solve the problem, for example, using graphsurgeon to modifiy the Padding node’s inputs pads to be a constant, do you know is that solution viable and how to do that?

spolisetty · January 20, 2022, 7:21am

Hi,

You can try following. If you still face issue, we recommend you to please share issue reproducible onnx model to try from our end for better debugging.

github.com

onnx/onnx-tensorrt/blob/main/docs/faq.md#inputsat0-must-be-an-initializer-or-inputsat0is_weights

<!--- SPDX-License-Identifier: Apache-2.0 -->

# ONNX-TensorRT FAQ

For all uses we recommend installing the following tools:
* [ONNX-Graphsurgeon](https://github.com/NVIDIA/TensorRT/tree/main/tools/onnx-graphsurgeon)
* [Polygraphy](https://github.com/NVIDIA/TensorRT/tree/main/tools/Polygraphy)

## How do I import and run an ONNX model through TensorRT?

There are currently two officially supported tools for users to quickly check if an ONNX model can parse and build into a TensorRT engine from an ONNX file.

For C++ users, there is the [trtexec](https://github.com/NVIDIA/TensorRT/tree/main/samples/trtexec) binary that is typically found in the `<tensorrt_root_dir>/bin` directory. The basic command of running an ONNX model is:

`trtexec --onnx=model.onnx`

Refer to the link or run `trtexec -h` for more information on CLI options.

For Python users, there is the [polygraphy](https://github.com/NVIDIA/TensorRT/tree/main/tools/Polygraphy) tool. The basic command for running an onnx model is:

This file has been truncated. show original

Thank you.