# Multi-Label classification using Chest X-rays
Using dataset from [Kaggle](https://www.kaggle.com/competitions/ranzcr-clip-catheter-line-classification/overview)

First attempt at Pytorch

At first, tried running on Kaggle GPU100 - very slow

* Kaggle notebook [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yxmauw/cxr-multilabel-clf/blob/main/enet-kaggle.ipynb) 
* Google colab notebook [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yxmauw/cxr-multilabel-clf/blob/main/enet-colab.ipynb)

## References:
1. [Debugger cafe](https://debuggercafe.com/multi-label-image-classification-with-pytorch-and-deep-learning/)
1. [StackOverflow](https://stackoverflow.com/questions/71404067/using-more-than-1-metric-in-pytorch)
1. [Debugger cafe - model checkpoints](https://debuggercafe.com/saving-and-loading-the-best-model-in-pytorch/)