Plain PyTorch implementation of fast.ai notebooks

Part 1 (2019) Advanced (Part 1 v3)
41

Would this be the new link: https://github.com/fastai/fastai/search?p=2&q="new+methods"&unscoped_q="new+methods" ?

Best regards
Michael

1 Like
42

Nice, the new link is returning results instead of empty results previously. So the difference is, this is searching fastai repo instead of fastai_docs repo :thinking:

43

If I remember correctly it was mentioned that they merged the docs with the main repo, but I cannot find the thread now.

44

Yes, thanks for the update.

1 Like
45

Iā€™m interested in doing this as well since Iā€™ve got an idea for a webapp that I want to build but unfortunately, Iā€™m struggling with doing the following in Fast.ai (which can be done in pure Pytorch):

  • Online Learning: receiving a single labeled example from the user and training the neural net on just that one example (batch).

  • Regression: unfortunately, Iā€™m having a lot of problems performing regression on images using fast.ai.

Also, Iā€™m very interested in implementing ULMfit in Pytorch since itā€™s only available on Fast.ai right now.