Comments (15)
adapt_pts 是预测的adaptive point,目前demo.py还不支持,我马上提供一个demo.py。
from adaptivepose.
@buptxyb666
这个adapt_pts 应该就是中间的节点的, 我要训练自己的数据集的话,这种怎么设置比较好呢?
from adaptivepose.
训练自己的数据集的话直接把你的标签转换成coco提供的json格式就可以了,我下午最晚明天会提供demo.py。
from adaptivepose.
@buptxyb666 >
这个我已经训完了, 现在应该,就是人体的你分为好几个部分的adpt_pts, 但我只需要四个点, 还有这个算法有没有跟yolopose比呢, 论文中好像没有。
from adaptivepose.
目前最新的指标在这个repo的第二个表格中,之前没太关注yolopose这个工作,刚才看了下,之前的指标已经超过他最好的结果了,目前最新的指标更是。
from adaptivepose.
adpt_pts的设置经验的话,基本把在结构上距离比较近的点设置成一个part就ok了。
from adaptivepose.
目前最新的指标在这个repo的第二个表格中,之前没太关注yolopose这个工作,刚才看了下,之前的指标已经超过他最好的结果了,目前最新的指标更是。
这个还得看下模型大小,adpt_pts的设置经验 我目前是随机取了一个对称左右,其他的都删掉了, 后期可能还要好好学习一下你的代码。
from adaptivepose.
AdaptivePose的parameters跟input resolution在更小的情况下都取得了更好的结果,你可以去看他的table2,比如adaptivepose_dla_34: 22M 512 pixels 67.0 AP V.S. YOLOv5m6-pose: 41.4M 960 pixels 66.3 AP。
如果你的四个点很远的话,可以每个点都分为一个part,效果会更好。
from adaptivepose.
@buptxyb666 上面那个也是我的号, 就是想继续问一下。
我看到新加了oks loss , [我之前在centernet上也加了,但好像没有什么提升
/src/lib/utils/post_preocess.py中的muti_pose_wodet_post_process_vis函数中的36: 这个数据代表什么呢?
还有reshape(-1,16) 这个 16 代表啥。人体关键点17 。
demo运行的时候 , 还是adapt_pts为[]然后在detector/muti_pose_wodet.py:88 行adap_pts /= scale * meta['sf'] 报错
from adaptivepose.
关于OKS-loss:1. 没有提升可能是你loss本身实现有问题,或者对area的变换有错误。2. 实现正确的情况下,如果不能提升是因为centernet本身仅仅把直接回归的结果作为初始预测,后续还用了heatmap detection来优化,加上oks loss仅仅是把直接回归出来的结果有所提升,但是上限还是不能超过heatmap detection,所以带来的好处被heatmap优化给覆盖掉了。
adaptivepose使用了两跳回归,而且实验证实了上限也略高于heatmap检测结果,所以在推理时不再需要heatmap,oks_loss的效果也能显现出来。
from adaptivepose.
刚才已经提交了更新,demo现在应该可以用了。reshape(-1,16) 是adapt_pts,这块包括了center和7个adaptive points八个点的坐标。
from adaptivepose.
36:的数据是预测的center和7个adaptive points。
from adaptivepose.
36:的数据是预测的center和7个adaptive points。
@buptxyb666 谢谢 我再试试
from adaptivepose.
这个 我也想过是这个问题
from adaptivepose.
刚才已经提交了更新,demo现在应该可以用了。reshape(-1,16) 是adapt_pts,这块包括了center和7个adaptive points八个点的坐标。
谢谢可以跑通了。
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
- Can i ask you some questions HOT 4
- 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
- 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.