Comments (3)
That's still possible, though I don't have sample code for that. Those experiments from the paper were trained with the old repo using Tensorflow 1, where I did provide the commands for training.
It should be quite simple you just need to replace Metrabs with Metro in a few places in main.py (or introduce a command line argument to choose between them). The difference is that Metro gives no estimate for the absolute root position, and the result cannot be projected onto the image, it is simply a root-relative 3D output with unspecified 2D correspondence.
from metrabs.
That's still possible, though I don't have sample code for that. Those experiments from the paper were trained with the old repo using Tensorflow 1, where I did provide the commands for training.
It should be quite simple you just need to replace Metrabs with Metro in a few places in main.py (or introduce a command line argument to choose between them). The difference is that Metro gives no estimate for the absolute root position, and the result cannot be projected onto the image, it is simply a root-relative 3D output with unspecified 2D correspondence.
Hi, thx for your fast reply : ). This project is amazing, I wish there can be an update for Metro implementation guidance in this repo lol. So I looked through the init.py and there is an argument 'model_class' which can choose metro for the processes, and is that the only thing I need to change? or I have to change the setup of the datasets as well and such.
And I also checked through the metrabs.py and I found that it set up an option which if FLAGS.transform_coords is True then applying the function latent_points_to_joints() , what's the purpose for this function?
thx
from metrabs.
That's an experimental flag that should normally be off. It's not used for the paper. I will push an update sometime that cleans those things up.
Dataset-wise there's no difference. But actually MeTRAbs performs a strict superset of MeTRo's functionality at negligible additional computation and gives results that can be projected onto the image and the 2D head also improves the quantitative results somewhat. Though if I recall correctly pure MeTRo got a little better numbers on H36M, but H36M is also not totally representative of everything.
from metrabs.
Related Issues (20)
- Question about joint-transform-file HOT 1
- The pretrained model for WACV‘23 paper? HOT 1
- Can't install cameralib HOT 1
- Calculation of AUC HOT 1
- question about the paper HOT 2
- could not find ffmpeg after search through Python error HOT 1
- Bone length file Missing
- Error Converting Existing Model to Tennsorflow.js Web Format
- Extending Pose Estimation Model for 3D Objects: Customization and Challenges HOT 1
- 6 Datasets Models
- Missing files for converting models to PyTorch HOT 5
- How to use 3d joint estimates directly instead of images as input to the model? HOT 1
- Confidences for 3D kps
- train a model using a custom dataset
- Question on Soft argmax implementations.
- How export data
- How to obtain a robust heatmap
- split crop model into backbone and head then predict, the res is not right
- What Method was used to get the skeleton format of SMPL? HOT 6
- About joint information
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 metrabs.