tensorrtx

tensorrtx copied to clipboard

自己数据集训练的yolov9模型tensorrt的输出结果与pytorch结果差别很大，精度完全没有对齐

9

## Env - GPU, e.g. RTX3060 - OS, e.g. Ubuntu20.04 - Cuda version: cuda-11.1 - TensorRT version: tensorrt-7.2.3 ## About this repo - which branch/tag/commit are you using？ master-branch -...

guanshanjushib

yolov8 reasoning process to context.enqueue(batchsize, buffers, stream, nullptr here appears 0x00007FF7B6A01DC5 (located in you_tu_system.exe) caused by the exception: 0xC0000094: Integer division by zero.why？

zengjianyou

虽然最终得到了engine模型，但是报了这个错误，我是否应该忽视

1

## Env - GPU3090ti - Win11 - Cuda version:11.8 - TensorRT version:8.6.1.6 ## About this repo - tag: yolov5s v6.0 - yolov5 ## My problem - my command: yolov5.exe -s...

22ling

ubuntu下yolov5_v5.0的.wts转.engine失败

1

配置环境： ubuntu 20.04 cuda v11.2 TensorRT 8.6.1 ## About this repo cmake成功，make成功 yolov5_v5跑的，.pt文件也是从yolov5_v5中下载的yolov5s，.pt转.wts成功 ## Your problem sudo ./yolov5 -s ../yolov5s.wts yolov5s.engine s报错： [05/31/2024-10:57:10] [E] [TRT] 2: [builder.cpp::createCaskKernelLibraryImpl::169] Error Code 2:...

silas-yy

widonws下yolov8模型生成wts转engine文件报错

2

## Env - GPU, e.g. 4070 - OS, e.g. Win10, etc. - Cuda v11.8 - TensorRT 8.6.1 ## About this repo - which branch/tag/commit are you using? - which model?...

XuJWood

YOLOV8 Assertion `serialized_engine' failed. 使用自己的.pt 生成 .wts 是成功的，但转.engine 是报错。chat说是卷积层权重数量不匹配

5

各版本 cuda 12.1 tensorrt 8.6.1 pytorch 2.2.2 cudnn 8.9.7 生成.pt的框架(是yolov8的官方镜像) pytorch 2.0 cuda 11.8 :~/YOLO/yolov8$ python gen_wts.py -w cricle-n.pt -o c8n.wts -t detect Generating .wts for detect model Loading cricle-n.pt...

cimmen