Comments (8)
Hi @Wwupup 你好,我想问下: 1、data\widerface\labelv2下只有train文件下的labelv2.txt才有关键点的标注信息;在val\labelv2.txt文件中没有人脸关键点的标注信息吗? 2、data\widerface\labelv2\labelv2.txt中,449 330 571 479 488.90601 373.64301 0 542.08899 376.44199 0 515.03101 412.82999 0 485.17401 425.89301 0 538.35699 431.49100 0; 对应的格式是x1,y1,x2,y2,关键点1,0,关键的2,0,关键点3,0,关键点4,0,关键点5,0吗?这个0是什么含义?我看有些是0,有些是1,有些是-1?
- 本项目的关键点仅做训练,不做评估,所以训练集下面是有关键点标注的,验证集没有 。
- labelv2.txt 每行有19个数,分别是(x, y, X, Y, (px, py, weight) * 5)。全是-1表示这个人脸没标注关键点,那么其weight被设置为0;而原始weight为0和1的都会在以下代码中设置为1.
libfacedetection.train/mmdet/datasets/retinaface.py
Lines 32 to 49 in dce0165
from libfacedetection.train.
肯定是支持的啊,你可以参考我的compare_inference.py中后处理的实现,这边是可以进行关键点输出的。pytorch中head里面由于不需要评估关键点,所以直接忽略了关键点。
from libfacedetection.train.
肯定是支持的啊,你可以参考我的compare_inference.py中后处理的实现,这边是可以进行关键点输出的。pytorch中head里面由于不需要评估关键点,所以直接忽略了关键点。
Hi @Wwupup , 请教一下现有模型的关键点检测能力是在哪个数据集上训练的呀?想重新训练复现一下关键点检测的能力。WilderFace没有带人脸关键点的标注
from libfacedetection.train.
你好,本项目使用的关键点标注是来自(SCRFD)[https://github.com/deepinsight/insightface/tree/master/detection/scrfd],当然本项目的/data文件夹下的labelv2就是WIDER-FACE数据集带关键点的标注文件。
肯定是支持的啊,你可以参考我的compare_inference.py中后处理的实现,这边是可以进行关键点输出的。pytorch中head里面由于不需要评估关键点,所以直接忽略了关键点。
Hi @Wwupup , 请教一下现有模型的关键点检测能力是在哪个数据集上训练的呀?想重新训练复现一下关键点检测的能力。WilderFace没有带人脸关键点的标注
from libfacedetection.train.
@Wwupup 感谢解答哈
from libfacedetection.train.
Hi @Wwupup 你好,我想问下:
1、data\widerface\labelv2下只有train文件下的labelv2.txt才有关键点的标注信息;在val\labelv2.txt文件中没有人脸关键点的标注信息吗?
2、data\widerface\labelv2\labelv2.txt中,449 330 571 479 488.90601 373.64301 0 542.08899 376.44199 0 515.03101 412.82999 0 485.17401 425.89301 0 538.35699 431.49100 0;
对应的格式是x1,y1,x2,y2,关键点1,0,关键的2,0,关键点3,0,关键点4,0,关键点5,0吗?这个0是什么含义?我看有些是0,有些是1,有些是-1?
from libfacedetection.train.
2. 关键点,那么其weight被设置为0;而原始weight为0和1的都会在以下代码中设置为1.
哦哦,感谢老师的解答,那我自定义数据集就仿造labelv2的格式,可以不用去设置0/1和weights的影响吧,我打算默认设置为0,weights设置为1
from libfacedetection.train.
- 关键点,那么其weight被设置为0;而原始weight为0和1的都会在以下代码中设置为1.
哦哦,感谢老师的解答,那我自定义数据集就仿造labelv2的格式,可以不用去设置0/1和weights的影响吧,我打算默认设置为0,weights设置为1
是的,只要数据加载出来和项目上一致即可。
from libfacedetection.train.
Related Issues (20)
- 当转onnx的时候,验证pytorch模型推理和onnx推理时候出现问题 HOT 2
- Cannot download labelsv2 HOT 3
- nonsquare input size training and exporting HOT 1
- How to train with custom dataset by using the pretrained model? HOT 2
- where can we get datasets with key points to train Yunet?
- 最小像素点修改 HOT 1
- 图像预处理时的均值和方差为什么是[0,0,0]和[1,1,1] HOT 1
- 老师,如果在Win上配置了MMDET环境后,如何修改指令执行train.py呀? HOT 5
- Why can't I find the yunet_final.pth weight file HOT 2
- Did you try Focal loss, how about its performance ? HOT 1
- The problem has been solved
- Train on rotated images to improve landmarks. HOT 1
- pytrch2onnx convervsion issue HOT 2
- 训练完成导出C++部署不成功
- Problems installing the repo HOT 1
- Batch inference problem! HOT 1
- Not able to setup the training environment HOT 9
- 为啥数据不做归一化 HOT 1
- 带出onnx出错 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 libfacedetection.train.