Comments (2)
Wow, that was an instant feedback. Cheers for that.
Regarding the extreme case that the entire body is occluded. The reason why I have asked is that it actually works good, considering that it sees nothing. also the score is scarily high.
Finally, regarding the spikes, you are right, it is the early training stage, I was checking it just because it happens that in some evaluations it actually works fine, then in the following one, the spikes appear again, but I assume it also depends from random evaluation images.
For example after 238000 iterations:
and it goes back and forth.
But your feedback, that it is because image-mesh alignment is not good, makes absolute sense. As is too early to make other assumption.
Have a good one,
Cheers
from meshtransformer.
Thanks for the questions!
We usually use (partially-) occluded training samples to improve model training. In many datasets, their 2D keypoint annotations have the visibility flags. If a specific keypoint is invisible (i.e., occluded), we will simply ignore it. However, in the examples you mentioned above, I see there is one extreme case that the entire human body is occluded. We may need to remove these kind of training samples in future. I believe the training sample is from MuCo-3DHP dataset.
I also observed the spike issue. I usually see the spikes when it is in an early training stage. This is probably because the image-mesh alignment is still not good. Could you please let me know the number of iterations/epoches you tried to obtain these examples?
from meshtransformer.
Related Issues (20)
- 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 3
- Acceleration Error.
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.