Comments (6)
I'm not clear about your experiments.
- First I train it on H36M+MPII,the MPJPE is about 50+. This is normal -> what is the test set?
- Then i change the dataset using MPII_3DHP+MPII to train. 50MPJPE in trainset but 200+ in validate dataset. -> what are the training and validation sets?
from 3dmppe_posenet_release.
I'm not clear about your experiments.
- First I train it on H36M+MPII,the MPJPE is about 50+. This is normal -> what is the test set?
- Then i change the dataset using MPII_3DHP+MPII to train. 50MPJPE in trainset but 200+ in validate dataset. -> what are the training and validation sets?
1、train with H36M + MPII2D train dataset;test with H36M validate dataset
2、train with MPII_3DHP+MPII2D train dataset;test with MPII_3DHP validate dataset
from 3dmppe_posenet_release.
I don't think this is from overfitting. I guess there is something wrong in your evaluation code?
from 3dmppe_posenet_release.
I don't think this is from overfitting. I guess there is something wrong in your evaluation code?
I checked the code and found that there was an issue with bbox, which has been fixed. However, the results of subsequent testing were still overfitting. The validation set MPJPE was around 150, trainset is about 60. Here are some of my visualization results. Some samples also have poor results
from 3dmppe_posenet_release.
Error 60 on training set means definitely underfitting
from 3dmppe_posenet_release.
Error 60 on training set means definitely underfitting
Firstly, thank you for communicating with me.
I know that continuing training may improve performance in the training set, but at this point, the validation set error no longer decreases, so I stopped training, and there was a significant difference between the validation set error and the training set error.
By the way, during my training and validation process, I did not use object detection algorithms to predict bbox, but instead used key point positions to fit the bounding box. I am not sure if this method will affect the training.
from 3dmppe_posenet_release.
Related Issues (20)
- Camera Parameters Abour MuPoTS HOT 3
- Keypoints probability HOT 3
- 2.6Mdatasets
- Human3.6M
- Run environment and video tests.
- Run my own img on demo.py HOT 4
- something about bbox_list HOT 2
- something about dataset HOT 2
- Some extended problems
- about h36m parsing. HOT 1
- Problems with Reproduced Papers HOT 12
- Problem when visualize on MuPoTS using bbox_root provided by RootNet
- Change resnet type HOT 5
- Question regarding bbox and rootNet HOT 2
- Extracting human36 parsed images HOT 12
- About inference my own images HOT 4
- PoseNet HOT 9
- about human36 data File name format HOT 6
- about datasets Human3.6m HOT 3
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 3dmppe_posenet_release.