Code release

[andresprados]

Code release will be available within the next two weeks, we expect to release the inference and the realtime demo before November and the training source before December.

[Shubhamai]

Amazing! Looking forward to it!

[ucalyptus2]

@andresprados any updates?

[ofirkris]

@andresprados is there a change in plan of code release?

[andresprados]

Sorry for the delay, we hope to have it ready before the start of the conference (21/11/2022).

[Shubhamai]

Thanks a lot for the update :)

[Oguzhanercan]

How can I run the inference code?

[nishitanand]

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.

[andresprados]

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.

[lucasjinreal]

@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?

[andresprados]

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.

I share with you the preview:

[Sparno1179]

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.

[andresprados]

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

[Kaktusava]

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?

[Xiejiahao233]

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.