tensorrtx

tensorrtx copied to clipboard

API Usage Error (Parameter check failed

4

## Env - GPU, 2080RTX Ti - docker nvcr.io/nvidia/tensorrt:22.07-py3 - 11.2 - TensorRT [8.4.1](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/index.html). ## About this repo yolov5 ## Your problem > root@23fd790e8b4b:/tensorrtx/yolov5/build# ./yolov5 -s yolov5s.wts yolov5s.engine s >...

MyraBaba

Yolov5 classification

1

Hi, Is it possible to support [Yolov5-classification](https://github.com/ultralytics/yolov5/pull/8956) models? Thanks

sctrueew

## Env - GPU : GTX 1650 - OS ; Ubuntu 22.04 - Cuda version 12.2 - Cudnn version 8.9.7 - TensorRT version 8.6.1 - Yolo v8 segmentation Issue: When...

Muthukumar4796

yolov8x to engine fault

12

Hi, everyone. I hope you are very well. I'm facing this problem. ## Env - GPU, e.g. V100, RTX2080, TX2, Xavier NX, Nano, etc. I'm using Docker with this image:...

adrianosantospb

Yolov7--Compared pytorch and tensorrtx faced detections issue.

3

## Env - GPU: NVIDIA GeForce GTX 1050 Ti. - OS: Ubuntu 18.04.6 LTS - Cuda version: 12.1 - TensorRT version: 8.6 ## About this repo - which branch/tag/commit are...

AMIYAMAITY

Yolov8 Classification

2

Is there a way to use this code but for yolov8 classification models?

advait2000

does yolov8 support tracking ?!

3

I have used yolov8 on python and can use Tracking with yolov8. Does this repository support tracking with the yolov8 model?

SJavad

yolov8 TRT问题

2

请问，tensorrtx/yolov8 是否支持tensorrt7.2.3.4 呢，我在cmake 的时候发现了一个错误， ``` linuxbrew@89f198c31474:/workspace/robot/tensorrtx-master/yolov8/build$ make -j Scanning dependencies of target myplugins [ 5%] Building CUDA object CMakeFiles/myplugins.dir/plugin/yololayer.cu.o /workspace/robot/tensorrtx-master/yolov8/plugin/yololayer.h(57): warning: function "nvinfer1::IPluginV2Ext::configurePlugin(const nvinfer1::Dims *, int32_t, const nvinfer1::Dims *, int32_t,...

SHOUshou0426

INT8量化问题：最后输出模型时报错，提示"[E] [TRT] 1: Unexpected exception invalid unordered_map<K, T> key"

4

## Env - RTX2070 - Win10 - CUDA 11.6 - TensorRT 8.6.1.6 ## About this repo - yolov5-v7.0 ## Your problem 大佬，我最近在尝试使用INT8量化yolov5模型的时候报错了，错误信息提示“[E] [TRT] 1: Unexpected exception invalid unordered_map key”；但是我切换回FP16或是FP32的推理时，engine文件可以正常生成，使用INT8则不行，麻烦大佬帮忙看下，感谢。 

Mr-MoNET

从wts文件读取权重数据，应该是hex的float值， 为什么存储在 uint32_t中啊

2

问一下下面这段代码中， 是从wts文件读取权重数据，应该是hex的float值， 为什么存储在 uint32_t中啊？ while (count--) { Weights wt{ DataType::kFLOAT, nullptr, 0 }; uint32_t size; // Read name and type of blob std::string name; input >> name >> std::dec >>...

HouLingLXH