Anyone have any recommendations to learn about one-shot learning?
Thanks for the shoutout for thai2vec! Working hard to migrate to new API!
6 Likes
Thanks, tried those! For some reason the conda installation doesn’t install fastai package. Had to use pip to install it. However, the imports did not work at the end. Will try again after the course I guess.
Any ideas if v1 will be used at some point?
Regards,
Theodore.
Please restrict questions to lesson 1 topics. We can build new threads for new topics.
4 Likes
That doesn’t fix it for me 
Check out fourth course of deeplearning.ai. Its a good start for one shot learning.
is there a post for installing FAI v1.Can some one paste link
. i know it was mentioned initially but i missed that part…
We had one earlier setups check list for last version… any similar thing for newer one…
Thanks in advance
Please use the install topic or create a new topic 
4 Likes
Calculus / Linear Algebra.
BS in Maths should be ok
1 Like
Thanks. I’m actually starting the 4th course this week! WOW!
No worries for anyone that isn’t set up! Just watch the lesson for now, and work on getting set up this week. There are lots of resources on the website (some links may be broken due to Github outage, will be fixed soon) and the forums
3 Likes
resnet50 rather than resnet34?
Adding to this: setting up your environment and being able to run the first notebook is your homework for next week. So don’t ruin it all tonight and listen to Jeremy ;).
9 Likes
Also, you always could try good old cross-validation to pick the best working architecture for you. Or use an ensemble.
Deeper, more parameters, usually better performance
Will there be guidelines for extension (thinking specifically of users adding new models)?
I am not a developer btw, thinking more of step-by-step examples of a popular model implemented in fastai, which could then be replicated for other architectures.
1 Like