News for hackers. Stuff that matters.

A comment on Pythia: Open-source framework for multimodal AI models.

Re:Pythia: Open-source framework for multimodal AI models by gjstein on Tuesday May 21, 2019 @12:34PM (#19971777)
The project pages are notably lacking images or interesting examples. Here is the most recent paper showing what they use this system for: [1] Toward VQA Models That Can Read [VQA == Visual Question Answering]

[1] https://arxiv.org/pdf/1904.08920.pdf

[ Parent | on HN ]
Re:Pythia: Open-source framework for multimodal AI models by colesbury on Tuesday May 21, 2019 @05:18PM (#19975161)
It has example images with Q&A now:

https://github.com/facebookresearch/pythia

[ Parent | on HN ]
Re:Pythia: Open-source framework for multimodal AI models by apsdehal on Tuesday May 21, 2019 @06:52PM (#19975945)
You can also try the colab notebook available at https://colab.research.google.com/drive/1Z9fsh10rFtgWe4uy8nv... to test the model in realtime.
[ Parent | on HN ]