Comments (8)
@niuyuanye 要修改类别数,比如:
// 网络输出中,det输出特征图宽度为:116,// 116=4+80+32,32为seg部分特征,经过NMS之后,输出为:N*38,其中38=4 + 2 + 32
还有外部num_classes也要改
from tensorrt-alpha.
在使用yolov8-seg时,转换官方模型都正常,在转换自己训练的模型(只有1类,python测试.pt都正常)时,程序不报错,但显示的分割结果错误
from tensorrt-alpha.
问题解决了
from tensorrt-alpha.
Eigen::MapEigen::MatrixXf img_ojb_seg_(ptr + 7, m_output_seg_h, 1); //使用eigen的map功能进行内存映射 [25,1]
m_mask_eigen160 = img_seg_ * img_ojb_seg_;//矩阵相乘 [160160,25][25,1]=[160*160,1]
分割后处理之一部分,耗时比较多,有什么优化的方法么
from tensorrt-alpha.
@niuyuanye 看你的平台,也可以试下opencv的矩阵乘法;还可尝试把最后处理全部放进cuda计算
from tensorrt-alpha.
@FeiYull 我是在orin下测试,使用opencv相乘效率提高很多,是因为orin下的Eigen 没有相应的底层不支持相应的加速么,你这边有相应的测试过么
from tensorrt-alpha.
@niuyuanye 感谢反馈,在pc上,使用intel处理器:i9-13900,实测eigen比opencv快。
from tensorrt-alpha.
@FeiYull 你好,使用TensorRT-7.1.3版本转换onnx-trt你测试过可以正常使用么,我这边测试有报错:ERROR: onnx2trt_utils.cpp:188 In function convertAxis:
[8] Assertion failed: axis >= 0 && axis < nbDims
看网上说,需要升级TensorRT,请问有其他解决办法么?
from tensorrt-alpha.
Related Issues (20)
- yolov8 obb HOT 1
- yolov8 vs项目生成报错 HOT 2
- 编译失败
- 如何计算转化后mAP值 HOT 1
- yolov8-pose推理时报错 HOT 1
- support yolo-world
- 抓狂,过了一夜报错:UDA initialization failure with error: 222.,之前还是跑通的
- 自己训练的模型检测框错位,标签乱 HOT 1
- Cuda12.1+tensorrt10.0 运行C++yolov8工程报错,提示getBindingDimensions 不是 nvinfer1::IExecutionContext成员 代码C2039 HOT 3
- spend more than 20ms on prepocess on jetson nano, batch=1 HOT 7
- make -j10在jetson nano上报错
- 希望后期可以支持目标跟踪 HOT 1
- onnx转换trt报错 HOT 1
- YOLOV8-SEG 如何快速获取mask掩码 HOT 6
- Windows Cmake编译错误 HOT 6
- Yolov8部署jetson后map精度问题
- v8-pose在Jetson AGX Xavier上的推理时间问题 HOT 1
- 期待加上目标跟踪功能
- YOLOv8-pose 出现编译错误 ,up帮忙看看给您磕头了 HOT 1
- yolov8 seg output有output0和output1,代码中使用output0有问题 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tensorrt-alpha.