Comments (21)
都是**人,跟我飚啥英语?<( ̄3 ̄)>哼!
from deep_sort_yolov3.
how about the speed ? performs well ?
from deep_sort_yolov3.
Same as README, about 12 fps after add deep_sort.
I excluded the disk reading
and the opencv drawing
got this result.
from deep_sort_yolov3.
I maked the CPU do less work and increase GPU usage to 60%, 20 fps
Can yolo batch detect pictures? That should be much faster.
from deep_sort_yolov3.
我这一直只能调用CPU版本的tensorflow,重装anaconda后只安装tensorflow-GPU也是这样,请问得怎样把活交给GPU干呢?
from deep_sort_yolov3.
@aimhabo
要先装好 cuda 和 cudnn
再根据cuda版本下载 tensorflow-GPU 或者自行编译
from deep_sort_yolov3.
我现在急需提升运行速度啊
能否并行调用 tf.session.run 来提高利用率?
from deep_sort_yolov3.
能不能改写成使用 tensorflow 队列传输数据啊,大佬帮帮我啊。
from deep_sort_yolov3.
@EYHN 不行啊,就是这样装的,fps不到0.3,直接在darknet里做都有2的
from deep_sort_yolov3.
终端使用 nvidia-smi 查看GPU 使用情况 @aimhabo
from deep_sort_yolov3.
并行? yolo 的session 和deep_sort的session并行运行? 那样的话需要解决检测框与图像的匹配,保证正确的传输给deep_sort 。 实际上如果你做过测试,deep_sort 基本不影响速度,单纯的运行deep_sort速度非常快,主要限制来自于yolo 。可以尝试在yolo部分加速,或去掉视频存储,检测框存储等功能。
还有我主要学习的不是tensorflow,对于tensorflow更多的东西不很了解。
from deep_sort_yolov3.
目前我是增加了视频读取缓存,增加了一个线程专门绘制检测框和输出视频
yolo和deep_sort共用同一个session
现在可以达到27fps,yolov3官网titan x 能跑 35fps,感觉还可以优化。
from deep_sort_yolov3.
做的不错!
from deep_sort_yolov3.
I closed this issue.
About the batch detect pictures: qqwweee/keras-yolo3#15
from deep_sort_yolov3.
你好!可以看看你的代码吗?三扣~~~
from deep_sort_yolov3.
@Innerpeace90
相关的代码在我fork的repository中 https://github.com/EYHN/deep_sort_yolov3/tree/eyhn
from deep_sort_yolov3.
@EYHN
你好請問你有成翁加速嗎?我也很需要能提高速度感謝
from deep_sort_yolov3.
目前我是增加了视频读取缓存,增加了一个线程专门绘制检测框和输出视频
yolo和deep_sort共用同一个session
现在可以达到27fps,yolov3官网titan x 能跑 35fps,感觉还可以优化。
@EYHN 想請問具體要怎麼實現?
from deep_sort_yolov3.
I maked the CPU do less work and increase GPU usage to 60%, 20 fps
Can yolo batch detect pictures? That should be much faster.
@EYHN
can you explain how did you increased the performance to 20fps ????
from deep_sort_yolov3.
@Innerpeace90
相关的代码在我fork的repository中 https://github.com/EYHN/deep_sort_yolov3/tree/eyhn
This code is running at 27 FPS?
from deep_sort_yolov3.
@gogoIsComing
use this repo
https://github.com/MuhammadAsadJaved/deep_sort_yolov3
Eyhn made some changed and I also changed a little from her repo.
from deep_sort_yolov3.
Related Issues (20)
- demo.py 异常 HOT 2
- yolo3模型是tensorflow生成的ckpt文件或者pb文件,如何转换到.h5文件用到这个项目中呢?
- encoder = gdet.create_box_encoder(model_filename, batch_size=1)中的batch_size有什么用?
- Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR HOT 1
- How to count each object separately?
- UnboundLocalError: local variable 'track' referenced before assignment HOT 3
- requirements.txt
- i want to set the gpu fraction,but it failed, gpu is always fully occupied
- process killed on running demo.py
- Error
- cpu占用率暴涨
- what is mars-small128.pb ? and what is it use for ?
- A typo in README.md
- confusing
- No ID of people on output .txt detections file
- 为什么我的darknet运行yolov4只有10帧左右
- 人出去之后,还有追踪框停留。max_age设置为0,依旧存在该问题
- 我在keras-yolov3训练了改动的yolov3,生成的h5用到deepsort,会多一个functional层,如何解决
- 我可以保存检测到的路径吗
- QQ群不见了吗 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 deep_sort_yolov3.