Fastai v2 chat

[muellerzr (Zachary Mueller)]

@ai_padawan

How do users who have migrated to v2 feel about the current state? Do you find it stable enough relative to v1? Has it been easier to implement custom models? It seems with the mid-level APIs the code will be more flexible, and I’m really excited if that’s the case.

It’s relatively stable, (I’ve been doing all my work in v2 right now) see my comment here:

I just started to learn fastaiv1 for one month, but should I jump to fastai v2 because it is newer and forget about v1?

I’d recommend the v2 study group I’ve been doing and Jeremy’s walkthroughs to catch up to speed with whats new, I made sure to go into great detail on the major changes. It’s relatively stable, there are some bugs with the last bits of the library, things get refactored every so often so you need to keep track of nomenclature changes, and remember it won’t be officially released until July. (this was announced recently)

(which also answers your other questions somewhat). The study group I run shows many examples for custom models and mid-level api.

Said study group: A walk with fastai2 - Vision - Study Group and Online Lectures Megathread

I’ll also add I’m in the middle of implementing Mask RCNN, and getting the databunch working was trivial