# Introduction
The internet boom leads to appear of many amazing AI applications that can replace the human in the recognition task. In this competition, you are supplied with the dog and cat images and try to train a computer vision model that can recognize a new image belonging to what class.

The competition is also a good chance for you to practice and compare the different SOTA backbones of Computer Vision such as:

* Transformer: ViT, DeiT, CoAtNet, SwinTransformer, MobileViT
* CNN: EfficientNet, ConvNeXt, ResNet, ResNext, MobileNet, AlexNet, InceptionNet, DenseNet,...
* Other architectures: MLP-Mixer, PatchConvNet, Neural Architecture Search,...