Vision
Repository of Various Test & Implementation of Vision models
- AutoAugment was used by using the work of https://github.com/DeepVoltaire/AutoAugment to train image classification models
- trainer.py used CutMix & MixUp to train image classification models
Image Classification
- EfficientNet
- Vision Transformer(ViT) : https://arxiv.org/pdf/2010.11929.pdf
- MLP-Mixer : https://arxiv.org/pdf/2105.01601.pdf