Kaggle Diabetic Retinopathy Detection

Installation

Extract train/test images to

data/train

data/test

trainLabels.csv

data

Install python2 dependencies via,

pip install -r requirements.txt

If you'd like to run a deterministic variant you can use the

deterministic

requirements.txt

The project was developed and tested on arch linux and hardware with a i7-2600k CPU, GTX 970 and 980Ti GPUs and 32 GB RAM. You probably need at least 8GB of RAM as well as up to 160 GB of harddisk space (for converted images, network parameters and extracted features) to run all the code in this repository.

Usage

Generating the kaggle solution

A commented bash script to generate our final 2nd place solution can be found in

make_kaggle_solution.sh

Running all the commands sequentially will probably take 7 - 10 days on recent consumer grade hardware. If you have multiple GPUs you can speed things up by doing training and feature extraction for the two networks in parallel. However, due to the computationally heavy data augmentation it may be far less than twice as fast especially when working with 512x512 pixel input images.

You can also obtain a quadratic weighted kappa score of 0.839 on the private leaderboard by just training the 4x4 kernel networks and by performing only 20 feature extraction iterations with the weights that gave you the best MSE validation scores during training. The entire ensemble only achieves a slightly higher score of 0.845.

Scripts

All these python scripts can be invoked with

--help

• convert.py

  crops and resizes images

• train_nn.py

  trains convolutional networks

• transform.py

  extracts features from trained convolutional networks

• blend.py

  blends features, optionally blending inputs from both patient eyes

convert.py

Example usage:

python convert.py --crop_size 128 --convert_directory data/train_tiny --extension tiff --directory data/train
python convert.py --crop_size 128 --convert_directory data/test_tiny --extension tiff --directory data/test

Options: --directory TEXT Directory with original images. [default: data/train] --convertdirectory TEXT Where to save converted images. [default: data/trainres] --test Convert images one by one and examine them on screen. [default: False] --crop_size INTEGER Size of converted images. [default: 256] --extension TEXT Filetype of converted images. [default: tiff] --help Show this message and exit ```

train_nn.py

Example usage:

python train_nn.py --cnf configs/c_128_5x5_32.py
python train_nn.py --cnf configs/c_512_5x5_32.py --weights_from weigts/c_256_5x5_32/weights_final.pkl

Options: --cnf TEXT Path or name of configuration module. [default: configs/c5124x4tiny.py] --weightsfrom TEXT Path to initial weights file. --help Show this message and exit. ```

transform.py

Example usage:

python transform.py --cnf config/c_128_5x5_32.py --train --test --n_iter 5
python transform.py --cnf config/c_128_5x5_32.py --n_iter 5 --test_dir path/to/other/image/files
python transform.py --test_dir path/to/alternative/test/files

Options: --cnf TEXT Path or name of configuration module. [default: configs/c5124x432.py] --niter INTEGER Iterations for test time averaging. [default: 1] --skip INTEGER Number of test time averaging iterations to skip. [default: 0] --test Extract features for test set. Ignored if --testdir is specified. [default: False] --train Extract features for training set. [default: False] --weightsfrom TEXT Path to weights file. --test_dir TEXT Override directory with test set images. --help Show this message and exit. ```

blend.py

Example usage: ``` python blend.py --perpatient # use configuration in blend.yml python blend.py --perpatient --featurefile path/to/feature/file python blend.py --perpatient --test_dir path/to/alternative/test/files

Usage: blend.py [OPTIONS]

Options: --cnf TEXT Path or name of configuration module. [default: configs/c5124x432.py] --predict Make predictions on test set features after training. [default: False] --perpatient Blend features of both patient eyes. [default: False] --featuresfile TEXT Read features from specified file. --niter INTEGER Number of times to fit and average. [default: 1] --blendcnf TEXT Blending configuration file. [default: blend.yml] --testdir TEXT Override directory with test set images. --help Show this message and exit. ```

Configuration

• The convolutional network configuration is done via the files in the

  configs

  directory.
• To select different combinations of extracted features for blending edit

  blend.yml

  .
• To tune parameters related to blending edit

  blend.py

  directly.
• To make predictions for a different test set either
  • put the resized images into the

    data/test_medium

    directory
  • or edit the

    test_dir

    field in your config file(s) inside the

    configs

    directory
  • or pass the

    --test_dir /path/to/test/files

    argument to

    transform.py

    and

    blend.py