The basic image classifier model is Google's Vision Transformer from Hugging Face, pre-trained on ImageNet. It recognizes 999 different animals and objects.
Features
Done
Use UI Library instead of pure HTML and CSS💅💄
TODO
Provide input management of images and labels📁🗃️
Let users download their trained model⬇️
Allow batch classification of images🔄📄
Have more user configurated settings for the models🖌️🛠️