adding source codes

Author: Yifan Peng

.travis.yml

@@ -3,25 +3,6 @@ python:
   - "3.6"
 install:
   pip install -r requirements.txt
-#  - sudo apt-get update
-#  # We do this conditionally because it saves us some downloading if the
-#  # version is the same.
-#  - if [[ "$TRAVIS_PYTHON_VERSION" == "2.7" ]]; then
-#      wget https://repo.continuum.io/miniconda/Miniconda2-latest-Linux-x86_64.sh -O miniconda.sh;
-#    else
-#      wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh;
-#    fi
-#  - bash miniconda.sh -b -p $HOME/miniconda
-#  - export PATH="$HOME/miniconda/bin:$PATH"
-#  - hash -r
-#  - conda config --set always_yes yes --set changeps1 no
-#  - conda update -q conda
-#  # Useful for debugging any issues with conda
-#  - conda info -a
-#
-#  # Replace dep1 dep2 ... with your dependencies
-#  - conda env create --file environment2.7.yml
-#  - source activate eyesnet3.6
 
 script:
   - py.test

CONTRIBUTING.md

@@ -9,6 +9,5 @@ This project adheres to the [Contributor Covenant Code of Conduct](http://contri
 DeepSeeNet is maintained with :heart: by:
 
 - **@yfpeng**
-- @qingyu-chen
 
 See also the list of [contributors](https://github.com/ncbi-nlp/DeepSeeNet/contributors) who participated in this project.

LICENSE.txt

@@ -17,4 +17,7 @@ fitness for any particular purpose.
 
 Please cite the author in any work or product based on this material:
 
+Peng Y, Dharssi S, Chen Q, Keenan T, Agron E, Wong W, Chew E, Lu Z. DeepSeeNet:
+  A deep learning model for automated classification of patientbased age-related
+  macular degeneration severity from color fundus photographs. Ophthalmology. 2018.
 

README.rst

@@ -85,7 +85,7 @@ Besides grading the simplified score, we also provide individual risk factor mod
 
 All models can be found at ``deepseenet``.
 
-The pretrained models can be found at: 
+The pretrained models can be found at: `<https://github.com/ncbi-nlp/DeepSeeNet/releases/tag/0.1>`_
 
 
 Training DeepSeeNet model

deepseenet/data_generator.py

@@ -1,16 +1,15 @@
 from typing import Callable
 
 import numpy as np
-from keras.preprocessing import image
 from keras.utils import Sequence, to_categorical
 from sklearn.utils import class_weight
 
-from deepseenet.utils import crop2square, cal_chunk_number
+from deepseenet.utils import cal_chunk_number
 
 
 class DataGenerator(Sequence):
     def __init__(self, data, *, batch_size: int, n_classes: int,
-                 preprocess_image: Callable[[str]], shuffle: bool=False):
+                 preprocess_image: Callable, shuffle: bool=False):
         """
 
         Args:

deepseenet/deepseenet_adv_amd.py

@@ -5,10 +5,10 @@
 from keras.preprocessing import image
 from keras.utils import get_file
 
-from deepseenet import eyesnet_risk_factor
+from deepseenet import deepseenet_risk_factor
 from deepseenet.utils import crop2square
 
-ADVANCED_AMD_PATH = 'https://github.com/yfpeng/EyesNet/releases/download/v0.1/adv_amd_model.h5'
+ADVANCED_AMD_PATH = 'https://github.com/ncbi-nlp/DeepSeeNet/releases/download/0.1/adv_amd_model.h5'
 ADVANCED_AMD_MD5 = '0adbf448491ead63ac384da671c4f7ee'
 
 
@@ -26,22 +26,22 @@ def preprocess_image(image_path):
     img = crop2square(image.load_img(image_path)).resize((224, 224))
     x = image.img_to_array(img)
     x = np.expand_dims(x, axis=0)
-    x = eyesnet_risk_factor.preprocess_input(x)
+    x = deepseenet_risk_factor.preprocess_input(x)
     return x
 
 
-def EyesNetAdvancedAMD(model='areds1'):
+def DeepSeeNetAdvancedAMD(model='areds'):
     """
     Instantiates the EyesNet advanced AMD architecture.
 
     Args:
-        model: One of 'areds1' (pre-training on AREDS1),
+        model: One of 'areds1' (pre-training on AREDS),
               or the path to the model file to be loaded.
 
     Returns:
         A Keras model instance.
     """
-    if model == 'areds1':
+    if model == 'areds':
         model = get_file(
             'advanced_amd_model.h5',
             ADVANCED_AMD_PATH,

deepseenet/deepseenet_drarwi.py

@@ -5,10 +5,10 @@
 from keras.preprocessing import image
 from keras.utils import get_file
 
-from deepseenet import eyesnet_risk_factor
+from deepseenet import deepseenet_risk_factor
 from deepseenet.utils import crop2square
 
-DRUSEN_PATH = 'https://github.com/yfpeng/EyesNet/releases/download/v0.1/drusen_model.h5'
+DRUSEN_PATH = 'https://github.com/ncbi-nlp/DeepSeeNet/releases/download/0.1/drusen_model.h5'
 DRUSEN_MD5 = '997a8229f972482e127e8a32d1967549'
 
 
@@ -26,11 +26,11 @@ def preprocess_image(image_path):
     img = crop2square(image.load_img(image_path)).resize((224, 224))
     x = image.img_to_array(img)
     x = np.expand_dims(x, axis=0)
-    x = eyesnet_risk_factor.preprocess_input(x)
+    x = deepseenet_risk_factor.preprocess_input(x)
     return x
 
 
-def EyesNetDrusen(model='areds1'):
+def DeepSeeNetDrusen(model='areds'):
     """
     Instantiates the EyesNet drusen architecture.
 
@@ -41,7 +41,7 @@ def EyesNetDrusen(model='areds1'):
     Returns:
         A Keras model instance.
     """
-    if model == 'areds1':
+    if model == 'areds':
         model = get_file(
             'drusen_model.h5',
             DRUSEN_PATH,