Speaker:
Shagun Sodhani, Tech Lead, Meta
Abstract:
This talk will focus on using functional transforms in PyTorch using the torch.func module. We will walk through usecases where torch.func improves the use of PyTorch APIs. Common examples include computing per-sample-gradients, vectorizing functions and creating ensemble of models. We will also talk about gotchas to look out for when using torch.func.
Watch video Torch func: Functional Transforms in PyTorch online, duration hours minute second in high quality that is uploaded to the channel Toronto Machine Learning Series (TMLS) 31 October 2024. Share the link to the video on social media so that your subscribers and friends will also watch this video. This video clip has been viewed 55 times and liked it 2 visitors.