Comments (4)
KeepmovingBenLee
commented on July 19, 2024
And I also wonder that how you generate openpose keypoints.
from 4d-humans.
geopavlakos
commented on July 19, 2024
We use ViTPose to generate 2D keypoints. We do this for the AVA, InstaVariety and AI Challenger datasets.
from 4d-humans.
KeepmovingBenLee
commented on July 19, 2024
We use ViTPose to generate 2D keypoints. We do this for the AVA, InstaVariety and AI Challenger datasets.
I see. So you use ViTPose to generate pseudo lables in openpose format for the above three datasets, while for other datasets you just use ground truth lables (without pseudo lables in openpose format), right?
from 4d-humans.
geopavlakos
commented on July 19, 2024
For MPII, COCO and MPI-INF-3DHP, we use pseudo ground truth SMPL parameters generated by SPIN. For H36M, we use ground truth SMPL parameters from MoSh.
from 4d-humans.
Related Issues (20)
- Multi gpu training HOT 1
- Visualization of the reconstructed human mesh HOT 2
- Unable to download hmr2_data.tar.gz HOT 2
- A colab error about tracking HOT 2
- The meaning of 'NUM_TRAIN_SAMPLES', 'NUM_TEST_SAMPLES' and the question of the discriminator.
- PHALP tracker taking lot of CPU utilization HOT 1
- Can not import expand_bbox_to_aspect_ratio from hmr2.datasets.utills HOT 1
- about the training data，do you use EFT fits or what? HOT 6
- how about using smpl 49 keypoints(like spin did) instead of your smpl 44 keypoints? will the result be worse? HOT 2
- Is it easy to train this work with 4 V100 24G or 8 3090 24G? (no A100) HOT 1
- Error of downloading training dataset HOT 1
- Is there any specific reason for choosing Detectron2 as human detection model? HOT 1
- Using 4 V100-16, and set batchsize=1, torch.cuda.OutOfMemoryError:
- Have you tried to use a smaller backbone? HOT 1
- use SMPLX model with hands and feet? HOT 2
- Pseudo labels generation
- evaluation datasets image HOT 3
- download problem of hmr2.0a_model.tar.gz HOT 4
- Training data preprocessing
- Why is loss not divided by the batch size? HOT 1
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 4d-humans.