Comments (14)
Hi @Sparno1179, thank you for the support.
At the moment, the training code is integrated into a larger framework supported by our lab. I believe that in the next 2-3 months I should be able to create a simple training process for SPIGA. In the meantime, check out the paper supplementary, a detailed explanation of the training process as well as the hyperparameters used can be found there. Also take a look at the dataloaders in the repository, we have included all the data augmentors used as well as the configuration set during the training.
Best,
Andrés
from spiga.
@andresprados any updates?
from spiga.
@andresprados is there a change in plan of code release?
from spiga.
Amazing! Looking forward to it!
from spiga.
Sorry for the delay, we hope to have it ready before the start of the conference (21/11/2022).
from spiga.
Thanks a lot for the update :)
from spiga.
How can I run the inference code?
from spiga.
Hello, thank you for the amazing work. When will the training code be released? And how can I run the inference code? I tried but wasn't able to. The code doesn't seem complete. I tried running framework.py, config.py and pretreatment.py in the inference folder, but it didn't work.
from spiga.
Hi, the demo with an inference example is expected to be released next week (01/02/2023). In the meantime, the readme shows how to generate results from different datasets in the evaluation section.
from spiga.
@andresprados Hello, does the 3d pose estimated also sota compare with previously methods? How's the accuracy and speed tradeoff? Can it in realtime on CPU?
from spiga.
Hi, the demo with an inference example is expected to be released next week (01/02/2023). In the meantime, the readme shows how to generate results from different datasets in the evaluation section.
Inference framework and image colab demo are already released!
Next week I will add a real-time video demo that will include:
- Face detection.
- Face tracking.
- Face alignment.
- Headpose estimation.
- Python package.
from spiga.
Hi, @andresprados
Thank you for sharing your wonderful project.
I'm very impressed with your work.
I have noticed that the training code has not yet been released, and I was wondering if you could kindly let me know when it is scheduled to be made available. I am very keen to explore and experiment with SPIGA, and having access to the training code would be helpful.
Thank you.
from spiga.
Hi @andresprados, thank you for your amazing work!
Do you have any updates on the code release for training? Or maybe you can post the training process as it currently is?
from spiga.
Hi @andresprados, thank you for your excellent work, I am very interested in this.
When will the training code be released?
Or I see you said that the training code had been integrated into the framework of your lab. Can you provide a link?
Thank you.
from spiga.
Related Issues (20)
- Onnx output and pytorch output are inconsistent HOT 6
- Fit FLAME model to Landmarks
- Performance improvement
- RuntimeError: Found no NVIDIA driver on your system HOT 1
- Importing retinaface causes all torch tensors to lack gradient function
- showing only the face with highest confidence HOT 2
- How to convert to onxx/tensorRT? HOT 1
- Running on CPU without using GPU. In case there is no CUDA compatibility. HOT 1
- On the issue of converting ONNX HOT 1
- 3D Pose Estimation
- Problems running in a thread on Linux/Mac (with solution)
- Have a problem in colab, UnpicklingError: invalid load key, '<' HOT 2
- UnpicklingError: While running in Local and Colab HOT 5
- ONNX Model Availability HOT 15
- Unable to generate an ONNX that works in ONNXRuntime HOT 5
- Live demo on HF
- Dog Face Cases (requesting the training script)
- Head pose estimation Only
- sort_tracker and retinaface not found HOT 1
- How to test an image by model? 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 spiga.