GTC 2020: Opening Up the Black Box: Model Understanding with Captum and PyTorch

GTC 2020 S22147
Presenters: Narine Kokhlikyan,Facebook AI; Ludwig Schubert,OpenAI
Abstract
PyTorch, the popular open-source ML framework, has continued to evolve rapidly since the introduction of PyTorch 1.0, which brought an accelerated workflow from research to production. We’ll deep dive on some of the most important new advances, including the ability to name tensors, support for quantization-aware training and post-training quantization, improved distributed training on GPUs, and streamlined mobile deployment. We’ll also cover new developer tools and domain-specific frameworks including Captum for model interpretability, Detectron2 for computer vision, and speech extensions for Fairseq.

Watch this session
Join in the conversation below.

1 Like

Hi @nadeemm, hope you are well.
It will be great to know more about this popular open-source ML framework :)

Thanks for watching.
You can read more about PyTorch here : https://pytorch.org/
and on our developer site

1 Like

@bayangp0, specifically about captum you can read more here: https://captum.ai/
https://medium.com/pytorch/introduction-to-captum-a-model-interpretability-library-for-pytorch-d236592d8afa

1 Like

@nadeemm , Thank you :)

@narine.kokhlikyan, Thank you :)