Skip to content

This is an competition on kaggle and is the big home work of the course: Practice of AI programming. The website of the competition is [here](https://www.kaggle.com/c/siim-isic-melanoma-classification)

Notifications You must be signed in to change notification settings

esflfei/SIIM-ISIC-Melanoma-Classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

SIIM-ISIC Melanoma Classification: Identify melanoma in lesion images

This is an competition on kaggle and is the big home work of the course: Practice of AI programming. The website of the competition is here

Requirements

  • python 3.7
  • pytorch 1.5.1
  • torchvision 0.6.1
  • pandas 1.0.5
  • efficientnet_pytorch
  • Windows
# You can install efficientnet_pytorch by:
pip install efficientnet_pytorch
# Or:
git clone https://github.com/lukemelas/EfficientNet-PyTorch
cd EfficientNet-Pytorch
pip install -e

Quick Start

  • Get data:

Download the data from here and put them into ./data

  • Training:

You can change the hyperparametrics such as lr, batch_size, begin_epoch, end_epoch, snapshop, etc. as you like in line 24 to line 30 in train.py.

Then simply run:

python train.py
  • Testing:

If you want to use the model trained by yourself, just change the path in demo_inference.py.

Then simply run:

python demo_inference.py

Results Saving

  • Training:

After every snapshot, a model will be saved in ./exp

  • Testing:

The result will be saved in ./result in the format of csv.

About

This is an competition on kaggle and is the big home work of the course: Practice of AI programming. The website of the competition is [here](https://www.kaggle.com/c/siim-isic-melanoma-classification)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%