i-Mix paper implementation

This is an un-official implementaion of the i-MIX : A DOMAIN -A GNOSTIC STRATEGY FOR CONTRASTIVE REPRESENTATION LEARNING-using pytorch.

I got accuaracy of 72% on Tabular data as the one in the paper with SimCLR . More experiments coming soon.

Major modules implemented in the code

• SimCLR Loss
• Tabular Model
• Augementation for tabuler data
• Mixup
• Mixup with SimCLR loss
• Pre-training & Fine-tuning

TODO

1. Use other modalities (images , speech)
2. Experiment Moco Loss and Byol Loss
3. Experiment different data sizes
4. Experiment with imagea without augmentation
5. covert code to .py
6. Improve documentation