Extract train/test images to data/train and data/test respectively and
put the trainLabels.csv file into the data directory as well.
Install python2 dependencies via,
pip install -r requirements.txt
You need a CUDA capable GPU with at least 4GB of video memory and CUDNN installed.
If you'd like to run a deterministic variant you can use the deterministic
branch. Note that the branch has its own requirements.txt file.
In order to achieve determinism cuda-convnet is used for convolutions instead
of cuDNN. The deterministic version increases the GPU memory requirements
to 6GB and takes about twice as long to run.
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.
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.
All these python scripts can be invoked with --help to display a brief help
message. They are meant to be executed in the order,
convert.pycrops and resizes imagestrain_nn.pytrains convolutional networkstransform.pyextracts features from trained convolutional networksblend.pyblends features, optionally blending inputs from both patient eyes
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
Usage: convert.py [OPTIONS]
Options:
--directory TEXT Directory with original images. [default: data/train]
--convert_directory TEXT Where to save converted images. [default: data/train_res]
--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
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
Usage: train_nn.py [OPTIONS]
Options:
--cnf TEXT Path or name of configuration module. [default: configs/c_512_4x4_tiny.py]
--weights_from TEXT Path to initial weights file.
--help Show this message and exit.
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
Usage: transform.py [OPTIONS]
Options:
--cnf TEXT Path or name of configuration module. [default: configs/c_512_4x4_32.py]
--n_iter 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 --test_dir is specified. [default: False]
--train Extract features for training set. [default: False]
--weights_from TEXT Path to weights file.
--test_dir TEXT Override directory with test set images.
--help Show this message and exit.
Example usage:
python blend.py --per_patient # use configuration in blend.yml
python blend.py --per_patient --feature_file path/to/feature/file
python blend.py --per_patient --test_dir path/to/alternative/test/files
Usage: blend.py [OPTIONS]
Options:
--cnf TEXT Path or name of configuration module. [default: configs/c_512_4x4_32.py]
--predict Make predictions on test set features after training. [default: False]
--per_patient Blend features of both patient eyes. [default: False]
--features_file TEXT Read features from specified file.
--n_iter INTEGER Number of times to fit and average. [default: 1]
--blend_cnf TEXT Blending configuration file. [default: blend.yml]
--test_dir TEXT Override directory with test set images.
--help Show this message and exit.
- The convolutional network configuration is done via the files in the
configsdirectory. - To select different combinations of extracted features for blending edit
blend.yml. - To tune parameters related to blending edit
blend.pydirectly. - To make predictions for a different test set either
- put the resized images into the
data/test_mediumdirectory - or edit the
test_dirfield in your config file(s) inside theconfigsdirectory - or pass the
--test_dir /path/to/test/filesargument totransform.pyandblend.py
- put the resized images into the