tensorRT_Pro icon indicating copy to clipboard operation
tensorRT_Pro copied to clipboard

C++ library based on tensorrt integration

Results 98 tensorRT_Pro issues
Sort by recently updated
recently updated
newest added

请问是否支持cuda11.x 我的显卡是3060,如果安装cuda10.2,无法使用pytorch

请问,web端,您是用什么库进行开发的???

This version of the ONNX parser only supports TensorRT INetworkDefinitions with an explicit batch dimension. Please ensure the network was created using the EXPLICIT_BATCH NetworkDefinitionCreationFlag

from .libtrtpyc import * ImportError: libavcodec-64ac49e1.so.58.91.100: cannot open shared object file: No such file or directory

目前使用yolo 6.1 版本参考 README,导出onnx会报错误。 ![image](https://user-images.githubusercontent.com/4592367/160744224-ace3030e-fbbd-4f69-9815-8d56f71ca13a.png)

我个人觉得这个比较有玩头,感谢大佬。

你好,在转换trt的时候,[TensorRT] ERROR: INVALID_ARGUMENT: getPluginCreator could not find plugin ScatterND version 1 是因为我用的tensorrt是7的原因吗? 那么,可以帮忙在使用tensorrt7的工程中,添加ScatterND 的插件吗?期待更新 https://github.com/NVIDIA/TensorRT/tree/release/8.0/plugin/scatterPlugin

Hi, I want to use multi-thread to re-use engine, is this thread safe? or any recommendations?

您好 这是什么原因呢? ![image](https://user-images.githubusercontent.com/59229974/157134988-5e65aa38-a5fb-4b3d-be83-c893dba4a1b4.png)