Skip to content

A PyTorch code for the classification problem in SIIM-ISIC Melanoma 2020 Kaggle Competition

Notifications You must be signed in to change notification settings

Alhasan-Abdellatif/SIIM-ISIC-Melanoma-2020

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SIIM-ISIC-Melanoma-2020

This repository provides a PyTorch implemenation of the classifcation problem in the Kaggle SIIM-ISIC Melanoma 2020 Competition, https://www.kaggle.com/competitions/siim-isic-melanoma-classification/overview, (It can be modified for other problems though).

Using an ensemble of models produced by this code as well as other TensorFlow models, our team managed to be in top 10% and win a bronze medal in the competition.

The implementation uses a 5-fold cross-validation method.

Running

To train a model, specify configurations in config_file.py and run :

python train.py  --save_folder config55   --dev_num 0

where save_folder will be the name of the created folders to save best checkpoints and predictions.

(Some updates might be introduced later).

About

A PyTorch code for the classification problem in SIIM-ISIC Melanoma 2020 Kaggle Competition

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages