tensorrtx

tensorrtx copied to clipboard

Are there any plans to implement support for YOLO-NAS?

2

YOLO-NAS is reported to outperform the other SOTA models including Yolov8, v7 etc. and license is fairly permissive. https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md Are there any plans to add support for this? Thank you!

Transigent

yolov8模型在1280*1280下出现多检

5

## Env - GPU, jetson-agx - OS, e.g. Ubuntu20.04 - Cuda 11.4 - TensorRT 8.5.2 ## About this repo - which branch/tag/commit are you using? master - which model? yolov5,...

BouncyKnight12

yolov8s to engine fault

5

## Env - GPU, jetson agx orin - OS, Ubuntu20.04 - Cuda version 11.4 - TensorRT version ## About this repo yolov8s to engine fault ## Your problem Error Code...

lkw052715

尝试修改输入分辨率后，pt转wts报错

6

## Env - GPU, RTX1060. - OS, Win10 - Cuda version 11.6 - TensorRT version TensorRT-8.4.1.5.Windows10.x86_64.cuda-11.6.cudnn8.4 ## About this repo - which branch/tag/commit are you using? master - which model?...

xjcvip007

yolov8s在960x960输入size存在较大概率误检，同一个模型用onnx或者torch推理正常的

6

## Env - GPU, e.g. V100, RTX2080, TX2, Xavier NX, Nano, etc. GTX1660S、RTX2080Ti - OS, e.g. Ubuntu16.04, Win10, etc. Ubuntu1804 - Cuda version cuda-11.4 - TensorRT version 8.5 ## About...

asflower

yolov5s.wts读取时出现报错：Segmentation fault

3

## Env - GPU, e.g. RTX3070 - OS, e.g. Ubuntu18.04. - Cuda version 11.1 - TensorRT version 8.2.1,8 -pycuda 2023.1 ## About this repo 所使用的版本为yolov5-7.0 def load_weights(file): print(f"Loading weights: {file}")...

chen-del

retinaface序列化时的报错

2

## Env - GPU, titan rtx - OS, ubuntu18.04 - Cuda 11.3 - TensorRT 8.6.1 ## About this repo retinaface ## Your problem 在执行 ./retina_r50 -s 和 ./retina_mnet -s 时，出现如下错误：...

dzw001

engine->destroy(); runtime->destroy(); not work

5

## Env - GPU RTX1060ti - OS, ubuntu 20.04 - Cuda 11.4 - TensorRT version TensorRT-8.0.1.6 ## About this repo - which branch/tag/commit are you using? yolov5-6.0 - which model?...

ReverseSystem001

yolov5 编译错误

1

## Env - GPU, RTX3060 - OS, Ubuntu18.04 - Cuda version 11.4 - TensorRT version 8.2.5.1 ## About this repo - which branch/tag/commit are you using? - which model? yolov5...

Y-pandaman

使用程序将wts转成engine时报错，但是engine可以生成也可以使用

4

## Env - RTX2070 - Win10 - CUDA 11.6 - TensorRT 8.6.1.6 ## About this repo - yolov5-v6.0 ## Your problem 我在使用程序将wts转成engine时报错，但是engine可以生成也可以使用；报错详细信息如下： (个人感觉这个报错只是提示回收方式不得当，但是对模型本身精度转换没有影响，因此这行ERROR是在转换完成后才提示的。想请教下大佬这个错误是什么原因造成的，希望能学习一下) [11/13/2023-19:06:28] [E] [TRT] 3: [builder.cpp::nvinfer1::builder::Builder::~Builder::341] Error Code...

Mr-MoNET