Comments (2)
Pokerlishao
commented on June 30, 2024
I run it on a single 4090, for a 43s video (1300 frames), it takes about 12 mins.
from 4d-humans.
shubham-goel
commented on June 30, 2024
Thanks for your interest in our work!
The demo code time is currently dictated by detection and rendering. Here are some numbers using example_data/images/skates.png, which is super high resolution (4016x6016 resolution).
On an A100, with a batch size of 1, HMR2 inference alone (no detection, no rendering) takes ~35 ms.
Each rendering takes ~230ms.
Detection (ViTDet) takes ~1.3 sec per image, depending on the resolution.
The tracking speed reported by @Pokerlishao can be improved with batched processing and faster detection and rendering. This is a WIP.
from 4d-humans.
Related Issues (20)
- Evaluation of 3DPW HOT 2
- About the learning rate HOT 1
- 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
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.