Pinned
Learn:
- Practical Deep Learning course.fast.ai
- Deep Learning Foundations course.fast.ai/part2.html
- Computational Linear Algebra github.com/fastai/numeric…
- Intro Machine Learning course.fast.ai/ml
fast.ai
369 posts
fast.ai
@fastdotai
Deep learning R&D: fast.ai;
Education: course.fast.ai;
Software: docs.fast.ai;
Book: up.fm/book;
@math_rachel @jeremyphoward
Joined October 2016
- We love hearing these stories about our amazing alumni! :DReplying to @jeremyphoward and @fastdotaiThank you so much Jeremy, it's hard to express via twitter how much your course helped
- Chapter 4 of our book (covering the foundations of deep learning) is, for most people, the most challenging. It covers a lot of math and coding concepts very quickly. This series from @strickvl is an amazing resource to help you understand how a neural net really works:This week I wanted to really make sure I grasped what was going on in ch 4 of the @fastdotai book, so I put my study hat on. 🤓 Writing helps me understand so I split the things I learned into separate blog posts. I reimplemented the methods with the Fashion MNIST dataset.
- We just released a new version of fastai that's now compatible with the latest @PyTorch 2.2. h/t @benjamin_warner Either: "pip install -U fastai" or "conda install -c fastai fastai" to upgrade.
- The new `fastcore.basics` provides a lot of great functionality, but is *really* lightweight (only 0.02 secs to import, and the entire `fastcore` has no deps other than python itself)
New #fastcore release: v1.2.4. github.com/fastai/fastcor… 1.2.4 ### New Features - move basic functionality into `fastcore.basics`, using minimal imports ([#149](github.com/fastai/fastcor…)) - add `anno_dict` and `empty2none` … - New #fastai release: v2.7.0. github.com/fastai/fastai/… Breaking changes - Distributed training now uses Hugging Face Accelerate, rather than fastai's launcher. Distributed training is now supported in a notebook -- see [this tutorial](https://docs.f…
- New #fastai release: v2.7.12. github.com/fastai/fastai/… New Features - PyTorch 2.0 compatibility, thanks to @benjamin_warner - Pytorch 2.0 compiler compatibility, thanks to ggosline - Better version support for `TensorBase.new_empty`, thanks to @benj…
- New #fastai release: v2.0.18. github.com/fastai/fastai/… 2.0.18 ### Forthcoming breaking changes The next version of fastai will be 2.1. It will require PyTorch 1.7, which has significant foundational changes. It should not require any code chang…
- New #fastai release: v2.7.5. github.com/fastai/fastai/… New Features - auto-normalize timm models - PyTorch 1.12 support
- New #fastcore release: v1.3.27. github.com/fastai/fastcor… ### New Features - add loop functions, thanks to @willmcgugan ([#363](github.com/fastai/fastcor…)) - add `walk` function ([#355](github.com/fastai/fastcor……
- We've just released fastai 2.2. This contains some fairly minor breaking changes, which should only impact you if you write your own callbacks, or use custom RNN code. The main feature is improved FP16 training. 1/
- Anyone got a bit of code that would make it easy to use the Youtube Data API to upload whisper-generated captions directly to Youtube? Feels like this whole process could probably be automated pretty easily! :DLet's transcript some youtube videos, what more useful than the courses videos from @fastdotai Colab -> colab.research.google.com/drive/1wep_ZJK… Transcripts for fastai course 2022 -> github.com/tcapelle/whisp…
- New #fastcore release: v1.3.21. github.com/fastai/fastcor… ### New Features - remove fastai-specific pieces from `Config` ([#334](github.com/fastai/fastcor…)) - in `untar_dir` create a directory if there is more than one item in r…
