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
Calculus / Linear Algebra.
BS in Maths should be ok
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
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 ;).
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.
I hope we will have some remote sensed data examples. I wonder if this handles 4 band or multispecteral data and in what format?
How do I load saved weights/checkpoint and continue training from there?
Is the library by default will utilise multi-gpu in parallel?
I setup all the things in google colab and fasta ai libray is working but i need to use num_worker=0 in dataloader (in pytroch) can i do that in fast.ai
Fast AI library is really cool. I use Keras a lot but the simplicity is so cool. For instance, callbacks used in Keras 2.x