Comments (6)
Hi, it’s a good point.
Actually I don’t do any augmentation to train Pose2Mesh. Only do flip augmentation for training PoseNet. So there’s no aug code for mesh_cam.
from pose2mesh_release.
Ah, got it! However, for the "Joint coordinate loss", the joints are regressed from the mesh. So, if the mesh isn't augmented, wouldn't it result in the wrong joints being regressed and used for computing the "Joint coordinate loss"? (line 131 Pose2Mesh_RELEASE/lib/core/base.py)
from pose2mesh_release.
Good! The flip aug is only done in pre-training PoseNet. When training Pose2Mesh in an end-to-end manner, there is no augmentation. So the joints are also never flipped.
from pose2mesh_release.
I see. Was this done on purpose? Does it result in better convergence?
from pose2mesh_release.
Yes, the model gave the best accuracy without augmentation. But you can try the augmentation referring to the dataloader codes in https://github.com/mks0601/I2L-MeshNet_RELEASE.
from pose2mesh_release.
Ah, okay. Thanks a lot for the responses. They helped me a lot in understanding your work better. I'll take a look at https://github.com/mks0601/I2L-MeshNet_RELEASE to try the augmentation :) Closing issue now.
from pose2mesh_release.
Related Issues (20)
- About Train pose2mesh freihand HOT 1
- How can i get the demo input about hand?(like human_joint_input.npy) HOT 1
- Question about evaluation on 3DPW HOT 7
- How can i get the demo input about human(smpl)? HOT 4
- retrain for the upper body only HOT 1
- Question about preprocessing SURREAL. HOT 1
- Can I input a picture of my hand to create a 3D model of the shape HOT 1
- About MeshNet with 3D gt as input! HOT 7
- Estimation uncertainty problem
- visualization - 2D keypoints with input image HOT 6
- About the loss weight during training HOT 1
- Recover joint angles from mesh HOT 2
- The input of Multiple People demo is not available HOT 2
- Multiple 3D pose from different angles as input and paint the texture to the generated model HOT 4
- Could you also release the pre-train model for meshnet HOT 1
- Queries in regards to shape parameters and results HOT 2
- Keypoints Conversion - SMPL to COCO HOT 1
- adding synthesis errors on hand joints HOT 1
- How to train Joint regressor for a different dataset HOT 3
- Recover mesh from 3D joint inputs
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 pose2mesh_release.