Comments (2)
Thanks for pointing out the questions!
Q&A1: Sorry for the inconsistent descriptions in the paper/code. When we implement the loss functions, we mainly adopt the loss functions from GraphCMR (CVPR 2019). As the authors (CVPR 2019) discussed in their paper, they empirically found L1 loss gives more stable training compared to MSE loss. However, in their implementation, they actually use MSE loss for the 2D/3D joints, and L1 loss for the 3D vertices. Probably replacing MSE with L1 could further improve our training, but we haven't tried it.
Q&A2: In line 207-211, we are trying to prepare GT data, and we normalize 3D GT joints based on a pre-defined pelvis. When we compute loss in line 125-128, we want to make sure both prediction and ground truth are in the same 3D space, so we normalize them again based on their pelvis (which is computed on the fly by (left_hip+right_ hip)/2).
from meshtransformer.
Thanks for the detailed explanation about my questions!
I greatly appreciate your help :)
from meshtransformer.
Related Issues (20)
- This repo is missing important files
- How to visualize attention correlation as the paper
- Training on single dataset HOT 1
- Output Score / Confidence
- Project dependencies may have API risk issues
- Cannot render my hand by my photo HOT 1
- About the template vertices and joints
- Question about training with hand dataset? HOT 1
- Can't download 'https://datarelease.blob.core.windows.net/metro/datasets/filename.tar'
- pre-trained models!ERROR 400: Bad Request.
- Demo Lack of three-digit reconstruction effect,缺少三位重建 HOT 1
- COCO SMPL Data Missing
- About DDP train on the specified gpu
- It is stopped in 2023-10-31 16:00:44,169 METRO Inference INFO: Using 1 GPUs
- Exception: Unable to get url: http://files.is.tue.mpg.de/mloper/opendr/osmesa/OSMesa.Linux.aarch64.zip HOT 1
- Question about the learning rate adjustment strategy
- Question about weight decay setting
- Pre-trained model licensing
- How to do single-player multi-card training? HOT 1
- Apex version incompatible HOT 2
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 meshtransformer.