Comments (4)
- z['ap'] 只是用于可视化,没有显示的监督,adaptivepose使用中心特征预测ap偏移,再取出ap位置的特征第二跳偏移,整个两跳path是梯度可回传的,所以相当于隐式监督的。
- Resample2D就是warp操作,通过双线性插值取ap位置特征。self.gradient_mul这块意思跟降低该层的学习率一个意思。
- 我这边实验效果 oks+L1 > oks > L1。先RegWeightedL1Loss_coco(),再oks这个操作你可以自己试试。自己的数据集如果是人体关键点你直接按着coco取对应位置的sigma就可以了,sigma跟数据集无关。算oks的时候把中心坐标加到偏移上了,建议仔细看看
from adaptivepose.
@buptxyb666
off_to_pose中将中心坐标加到偏移上, 是我没看清楚。 sigma的话我想问的是如果不是人体关键点的话, 该怎么估算呢?
from adaptivepose.
首先认为标注过程符合高斯分布,sigma 跟 scale这俩参数乘积,就是高斯分布的方差,直觉上理解就是对偏差的容忍度,比如同样偏移五个像素,可能对于eye的预测误差就是不可容忍的,对于hip的预测误差是可容忍的,对于large scale是可容忍的,对small scale是不可容忍的。coco上提供的标注,也是脸部关键点的sigma最小,其他的大一些,你可以按着这个思路来估算下你所估计的点的sigma。
from adaptivepose.
好的 谢谢了
from adaptivepose.
Related Issues (17)
- 你好,AdaptivePose++的代码何时能提交呢 HOT 4
- test.py: error: unrecognized arguments: multi_pose_wodet
- 怎么运行demo啊,有没有一个出结果的例子 HOT 3
- src/lib/models/predictor.py HOT 2
- the pretrain_models of CrowdPose data HOT 8
- 无法测试,TypeError: __init__() missing 1 required positional argument: 'hps_channel' HOT 3
- How to get good pose estimation? HOT 2
- problem about 'resample2d_cuda' HOT 2
- Can you publish a py to onnx
- No such file or directory: '/home/aa/AdaptivePose-master/src/lib/../../exp/multi_pose_wodet/hrnet_48_coco640/model_last.pth' HOT 1
- The jitter of performance HOT 1
- NameError: name 'resample2d_cuda' is not defined HOT 2
- Compare with mmpose
- torch12 HOT 8
- how to run demo.py? HOT 15
- Is 3D coordinate estimation supported? 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 adaptivepose.