当前位置:网站首页>[8] Assertion failed: dims. nbDims == 4 || dims. nbDims == 5
[8] Assertion failed: dims. nbDims == 4 || dims. nbDims == 5
2022-04-23 07:28:00 【wujpbb7】
onnx turn trt There was a mistake :
[04/22/2022-15:45:13] [W] [TRT] onnx2trt_utils.cpp:220: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[04/22/2022-15:45:13] [E] [TRT] (Unnamed Layer* 371) [Shuffle]: at most one dimension may be inferred
ERROR: onnx2trt_utils.cpp:1517 In function scaleHelper:
[8] Assertion failed: dims.nbDims == 4 || dims.nbDims == 5
[04/22/2022-15:45:13] [E] Failed to parse onnx file
[04/22/2022-15:45:13] [E] Parsing model failed
[04/22/2022-15:45:13] [E] Engine creation failed
[04/22/2022-15:45:13] [E] Engine set up failed
according to This article , Can solve , But it needs to be upgraded trt.
No upgrade trt The solution is , recompile libnvonnxparser.so, Replace trtexec Version used .
The specific steps are :( Assuming the current trt The version is 7.2.1.6, Installed in /usr/local/TensroRT7.2.1.6)
1、 download
git clone -b 7.2.1 https://github.com/onnx/onnx-tensorrt.git
2、 compile
cd onnx-tensorrt
git submodule update --init --recursive
mkdir build && cd build
cmake .. -DTENSORRT_ROOT=/usr/local/TensorRT-7.2.1.6 && make -j
3、 use ldd trtexec Look at what it depends on libnvonnxparser.so Where is the , Replace with the corresponding newly generated file .
Reference resources :
版权声明
本文为[wujpbb7]所创,转载请带上原文链接,感谢
https://yzsam.com/2022/04/202204230611549983.html
边栏推荐
- Gephi tutorial [1] installation
- x86架构初探之8086
- Pep517 error during pycuda installation
- Wechat applet uses wxml2canvas plug-in to generate some problem records of pictures
- 基于51单片机的温湿度监测+定时报警系统(c51源码)
- 【期刊会议系列】IEEE系列模板下载指南
- PyTorch 13. 嵌套函数和闭包(狗头)
- AUTOSAR从入门到精通100讲(八十七)-高级EEA的关键利器-AUTOSAR与DDS
- AUTOSAR从入门到精通100讲(八十六)-UDS服务基础篇之2F
- 多机多卡训练时的错误
猜你喜欢
随机推荐
安装 pycuda 出现 PEP517 的错误
C language, a number guessing game
直观理解 torch.nn.Unfold
GIS实战应用案例100篇(五十二)-ArcGIS中用栅格裁剪栅格,如何保持行列数量一致并且对齐?
基于Labview上位机的51单片机步进电机控制系统(上位机代码+下位机源码+ad原理图+51完整开发环境)
关于短视频技术轮廓探讨
Pytoch model saving and loading (example)
《Attention in Natural Language Processing》翻译
【无标题】制作一个0-99的计数器,P1.7接按键,P2接数码管段,共阳极数码管,P3.0,P3.1接数码管位码,每按一次键,数码管显示加一。请写出单片机的C51代码
AUTOSAR从入门到精通100讲(八十三)-BootLoader自我刷新
【点云系列】SO-Net:Self-Organizing Network for Point Cloud Analysis
Gather, unsqueeze and other operators when PTH is converted to onnx
【3D形状重建系列】Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
【Tensorflow】共享机制
美摄科技起诉天目传媒使用火山引擎侵权代码的声明
【技术规范】:如何写好技术文档?
Cmder Chinese garbled code problem
美摄科技推出桌面端专业视频编辑解决方案——美映PC版
面试总结之特征工程
UEFI学习01-ARM AARCH64编译、ArmPlatformPriPeiCore(SEC)









