Haiku basics (neural network library from DeepMind)
In this video, we will go through basic concepts of Haiku which is a deep learning library created by DeepMind.
Official repo: https://github.com/deepmind/dm-haiku
Official docs: https://dm-haiku.readthedocs.io/en/la...
Code from the video: https://github.com/jankrepl/mildlyove...
Chapters:
00:00 Intro
00:35 Cloning the repo + setting things up
01:52 Parameters: hk.transform basics
06:00 Parameters: init and module
14:13 Parameters: init and dealing with randomness
14:50 Parameters: apply in nonstochastic context
18:23 Parameters: apply in stochastic context
21:40 State: Buffers in PyTorch
24:17 State: hk.transform_with_state basics
31:46 From Haiku to JAX: grad and jit
38:47 Outro
If you have any video suggestions or you just wanna chat feel free to join the discord server: / discord
Twitter: / moverfitted
Credits logo animation
Title: Conjungation · Author: Uncle Milk · Source: / unclemilk · License: https://creativecommons.org/licenses/... · Download (9MB): https://auboutdufil.com/?id=600
Смотрите видео Haiku basics (neural network library from DeepMind) онлайн без регистрации, длительностью часов минут секунд в хорошем качестве. Это видео добавил пользователь mildlyoverfitted 01 Сентябрь 2022, не забудьте поделиться им ссылкой с друзьями и знакомыми, на нашем сайте его посмотрели 3,510 раз и оно понравилось 94 людям.