I meet an error when I doing onnx2tensorRT

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

Description

I meet an error when I doing onnx2tensorRT:
[TensorRT] WARNING: /data/nfs_ssd/kailong/wenet/tensorRT/TensorRT-release-7.0/parsers/onnx/onnx2trt_utils.cpp:235: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[TensorRT] ERROR: (Unnamed Layer* 37) [Slice]: only activation or Int32 types allowed as input to this layer.
[TensorRT] ERROR: (Unnamed Layer* 37) [Slice]: only activation or Int32 types allowed as input to this layer.
[TensorRT] ERROR: (Unnamed Layer* 37) [Slice]: only activation or Int32 types allowed as input to this layer.
[TensorRT] ERROR: (Unnamed Layer* 37) [Slice]: only activation or Int32 types allowed as input to this layer.
In node 20 (convertAxis): UNSUPPORTED_NODE: Assertion failed: axis >= 0 && axis < nbDims

Environment

TensorRT Version: 7.0
GPU Type: 1080Ti
Nvidia Driver Version:
CUDA Version: CUDA 10.0
CUDNN Version: 7.6.4
Operating System + Version: Linux
Python Version (if applicable): 3.6
TensorFlow Version (if applicable):
PyTorch Version (if applicable): 1.6
Baremetal or Container (if container which image + tag):

2

Hi,

We recommend you to please try on latest TensorRT version 8.2.
If you still face this issue, we recommend you to please share issue repro onnx model and compete verbose logs.

Thank you.

3

Hi,
Request you to share the ONNX model and the script if not shared already so that we can assist you better.
Alongside you can try few things:

  1. validating your model with the below snippet

check_model.py

import sys
import onnx
filename = yourONNXmodel
model = onnx.load(filename)
onnx.checker.check_model(model).
2) Try running your model with trtexec command.
https://github.com/NVIDIA/TensorRT/tree/master/samples/opensource/trtexec
In case you are still facing issue, request you to share the trtexec “”–verbose"" log for further debugging
Thanks!