Comments (12)
speed.py do not do any postprocess, maybe it's the difference.
from objectdetection-onestagedet.
把conf_threshold设置为0.2以上,速度就上来了,因为conf_threshold越低mAP越高,但是速度越慢(需要NMS大量的bbox)
from objectdetection-onestagedet.
把conf_threshold设置为0.2以上,速度就上来了,因为conf_threshold越低mAP越高,但是速度越慢(需要NMS大量的bbox)
对的,还有就是后处理的锅了(笑哭)
from objectdetection-onestagedet.
I write a img_detect func which detect per img, so I have not use dataloader. The other code is same to yours. when I test on 1080ti, I get only 0.05s/per img.Is the problem is whether using dataloader?
楼主可以把你的检测代码分享给我么,我的邮箱是[email protected],我这边写了一个可以画pr曲线输出mAP的代码,如果你有需要,我也可以发给你,不甚感谢。
from objectdetection-onestagedet.
@qhykwsw @Stinky-Tofu Could you kindly share your code for calculating mAP?
from objectdetection-onestagedet.
@wangg12 https://github.com/Stinky-Tofu/Stronger-yolo
from objectdetection-onestagedet.
@qhykwsw @Stinky-Tofu Could you kindly share your code for calculating mAP?
给我你的邮箱?
from objectdetection-onestagedet.
@Stinky-Tofu Thanks, I will have a try.
from objectdetection-onestagedet.
@qhykwsw My email is [email protected]. Thanks.
from objectdetection-onestagedet.
@LDoubleZhi 你好可以发我一份你的检测代码吗?[email protected],我这边加了focalloaa 以及cbam的代码,你需要我也可以发你
from objectdetection-onestagedet.
from objectdetection-onestagedet.
@LDoubleZhi 你好,可以发我一份你的检测代码吗?[email protected],谢谢了
from objectdetection-onestagedet.
Related Issues (20)
- 可以直接加载txt标签文件吗
- how to export onnx? HOT 1
- a bug?
- 没有GPU,应该怎么修改运行
- RuntimeError: shape '[256, 128, 3, 3]' is invalid for input of size 81624
- 问题报告 HOT 1
- yolov3 loss function
- mobilenet v3
- 为什么运行训练代码没反应? HOT 3
- 请问执行make -j命令后报以下错误怎么解决呢? HOT 1
- win 10 下运行 make -j32 报错AttributeError: 'MSVCCompiler' object has no attribute 'compiler_so'怎么办?
- New weight file syntax
- 使用voc数据集训练的模型进行测试,测试结果comp4_det_test_*.txt当中每张图片有几千个测试结果
- 执行python examples/train.py Yolov2报No module named 'utils.test.nms.gpu_nms'
- what is the meaning of input_shape in yolov3.yml ?
- test mAP
- NICE JOB. But where is kmeans part in your code?
- Upsample Layer
- 请问region_shufflenetv2有预训练模型吗?
- something wrong with examples/train.py
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 objectdetection-onestagedet.