This is a Keras (2.2.4) implementation of BTS-DSN, which is a Neural Network for Retinal Vessel Segmentation. The original code is written by Caffe.
keras = 2.2.4
tensorflow = 1.12.0
python = 3.6
-
Download VGG16 pretrained model.
-
Prepare the training and testing set.
python prepare_dataset_hdf5_for_2D.py # the source code for generating training dataset data in hdf5 format python prepare_dataset_hdf5_for_2D_test.py # the source code for generating testing dataset data in hdf5 format
-
Run the training script.
python deep_supervised.py
Run the testing script.
python 2D_new_run_test.py