I'm working on an image classifier to identify pinball machines by their backglass art. I've been using Turicreate. I can't find any comparisons of the libraries (turicreate vs fast.ai). Does anyone have any resources that compare/contrast the different solutions available for image classification?
Annotated notes to Fast.ai's lesson on Image Classification
11–15 of 15 posts
Re: Annotated notes to Fast.ai's lesson on Image Classification
#12I'm working on an image classifier to identify pinball machines by their backglass art. I've been using Turicreate. I can't find any comparisons of the libraries (turicreate vs fast.ai). Does anyone have any resources that compare/contrast the different solutions available for image classification?
I only learned about Turicreate after watching the CreateML video from WWDC. It's on my list to play around with, but no comparisons so far.
Any feedback on using it?
Re: Annotated notes to Fast.ai's lesson on Image Classification
#13still more marketing from fast.ai on hacker news
Re: Annotated notes to Fast.ai's lesson on Image Classification
#14I'm working on an image classifier to identify pinball machines by their backglass art. I've been using Turicreate. I can't find any comparisons of the libraries (turicreate vs fast.ai). Does anyone have any resources that compare/contrast the different solutions available for image classification?
I only learned about Turicreate after watching the CreateML video from WWDC. It's on my list to play around with, but no comparisons so far. Any feedback on using it?
I'm not experienced enough with ML to provide great feedback, but I did start getting segfault errors when I trained on too many images. I have multiple pictures of nearly 1000 different pinball machines, so right now it's a lot of trial/error as I determine how many pictures of each backglass I should train on and how diverse of angles/lighting produce the most accurate model. Right now I'm at about 15 different pinball machines, each with 20-30 pictures, and I get around 85% accuracy using my test set. I suspect/worry I won't be able to make a good model that can identify 1000 different pinball machines, but my patrons have asked for it so I'm giving it my all.
Re: Annotated notes to Fast.ai's lesson on Image Classification
#15Earlier quoted context omitted.
I only learned about Turicreate after watching the CreateML video from WWDC. It's on my list to play around with, but no comparisons so far. Any feedback on using it?
I'm not experienced enough with ML to provide great feedback, but I did start getting segfault errors when I trained on too many images. I have multiple pictures of nearly 1000 different pinball machines, so right now it's a lot of trial/error as I determine how many pictures of each backglass I should train on and how diverse of angles/lighting produce the most accurate model. Right now I'm at about 15 different pin…
It might be an idea to train the same data with fast.ai and see where it leads you. If you have the data in the right structure, it should not take too long. Let me know if you have questions... :)