tensorrtx
tensorrtx copied to clipboard
Implementation of popular deep learning networks with TensorRT network definition API
Hi,Wang I try to convert yolov4 on Jetson TX2.but meet below issue. could you help to check it? the version of tensorrt is 7.2 home/yolo/yolov4/mish.h(33): error: member function declared with...
## Env - GPU, Xavier NX, . - OS, e.g. Ubuntu18.04,Jetpack 4.6.1 - Cuda version 10.2.300 - TensorRT version 8.2.1.8 ## About this repo - which model? yolov5, retinaface? -...
使用官方的YOLOv5n生成engine成功 ![image](https://user-images.githubusercontent.com/28384596/162393972-55116f37-5324-4a6d-b5d8-ba50137f9b59.png) 使用自己训练的YOLOv5n生成engine失败(类别数已做修改) ![image](https://user-images.githubusercontent.com/28384596/162393876-98d94456-dec1-4c6b-9a5f-d053f9a434b0.png) 紧接着通过多次重复实验,发现YOLOV5n v6.0版本的代码,在将多卡训练得到的wts转成engine时会偶发失败,报错如上图。但同样的参数在单卡训练得到的wts基础上进行转换则可成功转成engine ![7358af12882132f0ba47a009e2493fe](https://user-images.githubusercontent.com/28384596/162694281-09b707d3-8289-438c-848f-aab4a9c21ff5.png)
There are 2 main advantages : doesn't add a big padding for images of 16:9 aspect ratio that should be converted to 640*640 + It is faster ! the resizing...
我已经将mobilenet v3的模型转换为.engine文件了,但是怎么才能推理自己的数据呢, 请各位指导一下,谢谢。
## Env - GPU, e.g. V100, RTX2080, TX2, Xavier NX, Nano, etc. - OS, e.g. Ubuntu16.04, Win10, etc. - Cuda version - TensorRT version ## About this repo - which...
## Env - GPU: NVIDIA GeForce RTX 3060 - OS: Win10 - Cuda version:cuda 11.1.74 - TensorRT version: TensorRT 8.0.1.6 ## About this repo - which branch/tag/commit are you using?...
if I use yolov5's obb model to .engine, How i to modify doInference function. I want to get (x,y,w,h, theta) not HBB(x,y,w,h)
## Env - GPU, 2060. - OS, Win10,. - Cuda 10.2 - TensorRT 8.4 I have no problem using x64 with visual studio 2015 on win10, but not with win32.Does...