jovenwayfarer / human_protein_atlas

Human Protein Atlas - Single Cell Classification

Human Protein Atlas - Single Cell Classification

This code is my part of the solution of my team for HPA - Single Cell Classification.

Data Preparation

Download competitiona data, external data (thanks to Alexander Riedel) and cell masks for the train data (thanks to Takuya Ito).

To create cell tiles and corresponding csv files run the following command.
$ bash preprocessing.sh <arg1> <arg2> <arg3> <arg4> <arg5> <arg6>

Arguments

• arg1: directory where cell-tiles will be saved
• arg2: competition data csv file
• arg3: external data csv file
• arg4: competition data images
• arg5: external data images
• arg6: path to dir. with hpa masks

Train

To train models run the following command:
$ bash train.sh <directory where cells were saved>

Metrics Visualization

Metrics are logged to wandb.ai.

Weights preparation

To convert weight files from PyTorch Lightning to vanilla Pytorch run the following command.
$ python convert2pytorch.py

Inference

You must upload the checkpoints of trained models to the kaggle dataset and create a submission notebook. An example is here.