Comments (11)
Jinjicheng
commented on May 13, 2024
1
我添加了include路径：cmake -DCMAKE_INCLUDE_PATH='/home/jinjicheng/ENV/tensorrt-7.0/inlucde/'
from tensorrtx.
Jinjicheng
commented on May 13, 2024
1
ln -s libnvinfer.so.7 libnvinfer.so 用这条命令就解决了
多谢大佬的指导，最终成功了
加速后的速度在14ms左右，没有v3加速后的快啊（9ms左右），这是什么情况呢
from tensorrtx.
wang-xinyu
commented on May 13, 2024
tar安装，需要改下cmake，链接到nvinfer so所在的地方
from tensorrtx.
wang-xinyu
commented on May 13, 2024
加了include路径能找到头文件，.so需要添加link路径
from tensorrtx.
Jinjicheng
commented on May 13, 2024
你这套yolov4加速的代码支持tensorrt5.1版本吗
from tensorrtx.
wang-xinyu
commented on May 13, 2024
master分支用的7.0的api，可能有的接口在5.1没定义。
用trt4分支，5.1应该可以跑
https://github.com/wang-xinyu/tensorrtx/tree/trt4/yolov4
from tensorrtx.
Jinjicheng
commented on May 13, 2024
加了include路径能找到头文件，.so需要添加link路径
请问要怎么添加so的link路径，这方面我不是很懂
from tensorrtx.
wang-xinyu
commented on May 13, 2024
这个是c++的基础知识了，cmake，去学学，兄弟
from tensorrtx.
wang-xinyu
commented on May 13, 2024
yolov4本身网络比yolov3大，
另外慢的一个主要因素是yolov4用了mish, 比yolov3的leaky relu慢。
from tensorrtx.
Jinjicheng
commented on May 13, 2024
好的，明白了
最近出的yolov5，大佬看了没，这个能否用trt加速
from tensorrtx.
wang-xinyu
commented on May 13, 2024
因为yolov5命名的争议，而且项目频繁更新，还不在一个稳定的状态，之前没做，最近比较忙，后面应该会做
from tensorrtx.
Related Issues (20)
- YOLOv8 & TensorRT: When building engine file facing 'serialized_engine' faild HOT 3
- yolov5 v7.0 成功生成engine但是./yolov5_det -d yolov5s.engine ../images报错Aborted (core dumped) HOT 2
- Yolov8 输出结果的bbox格式 HOT 2
- yolov8n to engine fault HOT 3
- 如何在已有engine文件的情况下只编译主程序？
- A bug about yolov5 decoder HOT 1
- yolov9 for tensorrtx HOT 2
- Yolov8 seg， only X model occured error. HOT 3
- 什么时候支持下，OBB和yolov9 HOT 1
- retinface seems to fail to serialize on Jetson Orin AGX 64 GB
- yolov9 小尺寸模型部署 HOT 2
- RetinaFace, calibration int8, tensorRT8.6.1 error [pluginV2Runner.cpp::execute::265] Error Code 2: Internal Error (Assertion status == kSTATUS_SCUESS failed. ) HOT 7
- 使用yolov5s推理没有检测到目标(空) HOT 5
- showing results empty HOT 5
- YOLOV9 wts转换错误 HOT 16
- yolov8 转wts文件（自定义数据集）失败 HOT 2
- What is warpaffine in relation to yolov9? HOT 1
- [TRT] 2: [utils.cpp::checkMemLimit::380] Error Code 2: Internal Error (Assertion upperBound != 0 failed. Unknown embedded device HOT 3
- yolov5s.engine 推理得到的 bbox 和 pytorch 不一样 HOT 2
- yolov5_seg.cpp 为啥只有预测框 没有 mask 输出
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 tensorrtx.