From bea0ec26cccc42b9c408fe02154a88f49ddc1b1d Mon Sep 17 00:00:00 2001
From: Zongwei Zhou <zongweiz@asu.edu>
Date: Fri, 5 Feb 2021 09:57:11 -0700
Subject: [PATCH] Add downstream tasks

---
 competition/.DS_Store                         | Bin 6148 -> 0 bytes
 datasets/.DS_Store                            | Bin 6148 -> 0 bytes
 figures/.DS_Store                             | Bin 6148 -> 0 bytes
 figures/superbar/.DS_Store                    | Bin 6148 -> 0 bytes
 keras/downstream_tasks/BraTS/DataSet.py       | 372 +++++++++++++
 keras/downstream_tasks/BraTS/DataSet.pyc      | Bin 0 -> 11286 bytes
 keras/downstream_tasks/BraTS/Patient.py       |  88 ++++
 keras/downstream_tasks/BraTS/Patient.pyc      | Bin 0 -> 3179 bytes
 keras/downstream_tasks/BraTS/__init__.py      |  14 +
 keras/downstream_tasks/BraTS/__init__.pyc     | Bin 0 -> 409 bytes
 .../BraTS/__pycache__/DataSet.cpython-36.pyc  | Bin 0 -> 9871 bytes
 .../BraTS/__pycache__/DataSet.cpython-37.pyc  | Bin 0 -> 9869 bytes
 .../BraTS/__pycache__/Patient.cpython-36.pyc  | Bin 0 -> 2817 bytes
 .../BraTS/__pycache__/Patient.cpython-37.pyc  | Bin 0 -> 2815 bytes
 .../BraTS/__pycache__/__init__.cpython-36.pyc | Bin 0 -> 426 bytes
 .../BraTS/__pycache__/__init__.cpython-37.pyc | Bin 0 -> 424 bytes
 .../__pycache__/load_utils.cpython-36.pyc     | Bin 0 -> 3136 bytes
 .../__pycache__/load_utils.cpython-37.pyc     | Bin 0 -> 3134 bytes
 .../__pycache__/modalities.cpython-36.pyc     | Bin 0 -> 2280 bytes
 .../__pycache__/modalities.cpython-37.pyc     | Bin 0 -> 2263 bytes
 .../__pycache__/structure.cpython-36.pyc      | Bin 0 -> 1181 bytes
 .../__pycache__/structure.cpython-37.pyc      | Bin 0 -> 1179 bytes
 keras/downstream_tasks/BraTS/load_utils.py    |  93 ++++
 keras/downstream_tasks/BraTS/load_utils.pyc   | Bin 0 -> 3394 bytes
 keras/downstream_tasks/BraTS/modalities.py    |  92 ++++
 keras/downstream_tasks/BraTS/modalities.pyc   | Bin 0 -> 2530 bytes
 keras/downstream_tasks/BraTS/structure.py     |  50 ++
 keras/downstream_tasks/BraTS/structure.pyc    | Bin 0 -> 1337 bytes
 keras/downstream_tasks/BraTS/test.py          |  32 ++
 keras/downstream_tasks/BraTS/test_load.py     |  31 ++
 keras/downstream_tasks/config.py              | 375 ++++++++++++++
 keras/downstream_tasks/data/bms/fold_1.csv    |  95 ++++
 keras/downstream_tasks/data/bms/fold_2.csv    |  95 ++++
 keras/downstream_tasks/data/bms/fold_3.csv    |  95 ++++
 keras/downstream_tasks/data/ecc/test_cv-1.csv |  40 ++
 keras/downstream_tasks/data/ecc/test_cv-2.csv |  40 ++
 keras/downstream_tasks/data/ecc/test_cv-3.csv |  40 ++
 .../downstream_tasks/data/ecc/train_cv-1.csv  |  75 +++
 .../downstream_tasks/data/ecc/train_cv-2.csv  |  75 +++
 .../downstream_tasks/data/ecc/train_cv-3.csv  |  75 +++
 keras/downstream_tasks/data/ecc/val_cv-1.csv  |   5 +
 keras/downstream_tasks/data/ecc/val_cv-2.csv  |   5 +
 keras/downstream_tasks/data/ecc/val_cv-3.csv  |   5 +
 .../lung nodule segmentation.ipynb            | 489 ++++++++++++++++++
 keras/downstream_tasks/ncs_data.py            |  32 ++
 keras/downstream_tasks/unet3d.py              | 123 +++++
 keras/downstream_tasks/utils.py               | 289 +++++++++++
 47 files changed, 2725 insertions(+)
 delete mode 100644 competition/.DS_Store
 delete mode 100644 datasets/.DS_Store
 delete mode 100644 figures/.DS_Store
 delete mode 100644 figures/superbar/.DS_Store
 create mode 100755 keras/downstream_tasks/BraTS/DataSet.py
 create mode 100755 keras/downstream_tasks/BraTS/DataSet.pyc
 create mode 100755 keras/downstream_tasks/BraTS/Patient.py
 create mode 100755 keras/downstream_tasks/BraTS/Patient.pyc
 create mode 100755 keras/downstream_tasks/BraTS/__init__.py
 create mode 100755 keras/downstream_tasks/BraTS/__init__.pyc
 create mode 100644 keras/downstream_tasks/BraTS/__pycache__/DataSet.cpython-36.pyc
 create mode 100755 keras/downstream_tasks/BraTS/__pycache__/DataSet.cpython-37.pyc
 create mode 100644 keras/downstream_tasks/BraTS/__pycache__/Patient.cpython-36.pyc
 create mode 100755 keras/downstream_tasks/BraTS/__pycache__/Patient.cpython-37.pyc
 create mode 100644 keras/downstream_tasks/BraTS/__pycache__/__init__.cpython-36.pyc
 create mode 100755 keras/downstream_tasks/BraTS/__pycache__/__init__.cpython-37.pyc
 create mode 100644 keras/downstream_tasks/BraTS/__pycache__/load_utils.cpython-36.pyc
 create mode 100755 keras/downstream_tasks/BraTS/__pycache__/load_utils.cpython-37.pyc
 create mode 100644 keras/downstream_tasks/BraTS/__pycache__/modalities.cpython-36.pyc
 create mode 100755 keras/downstream_tasks/BraTS/__pycache__/modalities.cpython-37.pyc
 create mode 100644 keras/downstream_tasks/BraTS/__pycache__/structure.cpython-36.pyc
 create mode 100755 keras/downstream_tasks/BraTS/__pycache__/structure.cpython-37.pyc
 create mode 100755 keras/downstream_tasks/BraTS/load_utils.py
 create mode 100755 keras/downstream_tasks/BraTS/load_utils.pyc
 create mode 100755 keras/downstream_tasks/BraTS/modalities.py
 create mode 100755 keras/downstream_tasks/BraTS/modalities.pyc
 create mode 100755 keras/downstream_tasks/BraTS/structure.py
 create mode 100755 keras/downstream_tasks/BraTS/structure.pyc
 create mode 100755 keras/downstream_tasks/BraTS/test.py
 create mode 100755 keras/downstream_tasks/BraTS/test_load.py
 create mode 100755 keras/downstream_tasks/config.py
 create mode 100755 keras/downstream_tasks/data/bms/fold_1.csv
 create mode 100755 keras/downstream_tasks/data/bms/fold_2.csv
 create mode 100755 keras/downstream_tasks/data/bms/fold_3.csv
 create mode 100755 keras/downstream_tasks/data/ecc/test_cv-1.csv
 create mode 100755 keras/downstream_tasks/data/ecc/test_cv-2.csv
 create mode 100755 keras/downstream_tasks/data/ecc/test_cv-3.csv
 create mode 100755 keras/downstream_tasks/data/ecc/train_cv-1.csv
 create mode 100755 keras/downstream_tasks/data/ecc/train_cv-2.csv
 create mode 100755 keras/downstream_tasks/data/ecc/train_cv-3.csv
 create mode 100755 keras/downstream_tasks/data/ecc/val_cv-1.csv
 create mode 100755 keras/downstream_tasks/data/ecc/val_cv-2.csv
 create mode 100755 keras/downstream_tasks/data/ecc/val_cv-3.csv
 create mode 100644 keras/downstream_tasks/lung nodule segmentation.ipynb
 create mode 100755 keras/downstream_tasks/ncs_data.py
 create mode 100755 keras/downstream_tasks/unet3d.py
 create mode 100755 keras/downstream_tasks/utils.py

diff --git a/competition/.DS_Store b/competition/.DS_Store
deleted file mode 100644
index 58f8cc64eeb4bdbf21a169969e3bb85679ff4206..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 6148
zcmeHKJ5Iwu5S;}VmS|E^?iF%_B{C<-1xT<2MJ%TPYD*McfCHq+9q2h3Z$3ncjFD)N
zKyRek=bf47wO`@!h)7yIwsVo0h}3XJdC_HTnpYp$Swt#e(tB*~=F8i@+m0%y1In$W
zm6bfm>I?oM*Y!=a-t=qK*H8Pm=iTf3)iJm0+i&yR`yW5s^iwlK1*iZOpaN9j?<#<v
ztyW(+a-{-PfC?NG(C<TrE0(~)(LNnmYy<%6Z@d|<ZI%FL4FF5v;D`t;ITh&C6eC7*
zI^sF%O5ot=bV+tH?h_}cm{5|Pj(E0mNyU*X6`%sA3Y`0Prv3jKJ~98FlDMM+RN!AJ
zkg8_cEbvOvTSqUay*9&d;Gc$CE5~B37-+2+8*RmxM|D}RkuQORqtOvJI*>mCstb(@
H{DuM_<EkmJ

diff --git a/datasets/.DS_Store b/datasets/.DS_Store
deleted file mode 100644
index f2c77599ff1659058e5d78a209bb937dc5954dd5..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 6148
zcmeHKOHRWu5S@VvMPkz>OJ5-y)}~5N&<jAR1eFrfF1q(U*z_t~ixqD^AO$QTu|NgQ
zNcJ0hK5<?Y+e1XWIBZ&?IT1Bzf-Fi!WV&iPbLSb5HAhR={X@IDABSBf(J4;J+ApZ5
z13l3l)z?3<4`bJ@`*Dr9X1m=#zaC$1KIa(5&9^?g$3Ml>DSo?HQ!o$=1Ovgq&ltd&
zEz(>XMjs3W1Hr%t1F}CPG{Njx40Y>3rzHSTuF)#crIwJG<d_|cAuJHKP@sjfml$l}
zm{0DP9gCrb6MON&{^a-Kh4tykpVXZ=8%7@t1OrnB&TTlC^M8q7rds4rLt+#R1Oxw!
z0iJcMZh@Ebv-QjC$yuAwZqY=<uZRMHKDh*7Ap6Lb8qJ<WhhKIqhLT0*H5?ch0VO25
JVBi-RcmuU(D|7$=

diff --git a/figures/.DS_Store b/figures/.DS_Store
deleted file mode 100644
index 5008ddfcf53c02e82d7eee2e57c38e5672ef89f6..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 6148
zcmeH~Jr2S!425mzP>H1@V-^m;4Wg<&0T*E43hX&L&p$$qDprKhvt+--jT7}7np#A3
zem<@ulZcFPQ@L2!n>{z**<q8>++&mCkOWA81W14cNZ<zv;LbK1Poaz?KmsK2CSc!(
z0ynLxE!0092;Krf2c+FF_Fe*7ECH>lEfg7;MkzE(HCqgga^y>{tEnwC%0;vJ&^%eQ
zLs35+`xjp>T0<F0fCPF1$Cyrb|F7^5{eNG?83~ZUUlGt@xh*qZDeu<Z%US-OSsOPv
j)R!Z4KLME7ReXlK;d!wEw5GODWMKRea10D2@KpjYNUI8I

diff --git a/figures/superbar/.DS_Store b/figures/superbar/.DS_Store
deleted file mode 100644
index 5008ddfcf53c02e82d7eee2e57c38e5672ef89f6..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 6148
zcmeH~Jr2S!425mzP>H1@V-^m;4Wg<&0T*E43hX&L&p$$qDprKhvt+--jT7}7np#A3
zem<@ulZcFPQ@L2!n>{z**<q8>++&mCkOWA81W14cNZ<zv;LbK1Poaz?KmsK2CSc!(
z0ynLxE!0092;Krf2c+FF_Fe*7ECH>lEfg7;MkzE(HCqgga^y>{tEnwC%0;vJ&^%eQ
zLs35+`xjp>T0<F0fCPF1$Cyrb|F7^5{eNG?83~ZUUlGt@xh*qZDeu<Z%US-OSsOPv
j)R!Z4KLME7ReXlK;d!wEw5GODWMKRea10D2@KpjYNUI8I

diff --git a/keras/downstream_tasks/BraTS/DataSet.py b/keras/downstream_tasks/BraTS/DataSet.py
new file mode 100755
index 0000000..dcf72c1
--- /dev/null
+++ b/keras/downstream_tasks/BraTS/DataSet.py
@@ -0,0 +1,372 @@
+#!/usr/bin/env python
+"""
+File: DataSet
+Date: 5/1/18 
+Author: Jon Deaton (jdeaton@stanford.edu)
+
+This file provides loading of the BraTS datasets
+for ease of use in TensorFlow models.
+"""
+
+import os
+
+import pandas as pd
+import numpy as np
+import nibabel as nib
+
+from tqdm import tqdm
+from BraTS.Patient import *
+from BraTS.structure import *
+from BraTS.modalities import *
+from BraTS.load_utils import *
+
+survival_df_cache = {}  # Prevents loading CSVs more than once
+
+
+class DataSubSet:
+
+    def __init__(self, directory_map, survival_csv, data_set_type=None):
+        self.directory_map = directory_map
+        self._patient_ids = sorted(list(directory_map.keys()))
+        self._survival_csv = survival_csv
+        self._num_patients = len(self._patient_ids)
+        self.type = data_set_type
+
+        # Data caches
+        self._mris = None
+        self._segs = None
+        self._patients = {}
+        self._survival_df_cached = None
+        self._patients_fully_loaded = False
+        self._id_indexer = {patient_id: i for i, patient_id in enumerate(self._patient_ids)}
+
+    def subset(self, patient_ids):
+        """
+        Split this data subset into a small subset by patient ID
+
+        :param n: The number of elements in the smaller training set
+        :return: A new data subset with only the specified number of items
+        """
+        dir_map = {id: self.directory_map[id] for id in patient_ids}
+        return DataSubSet(dir_map, self._survival_csv)
+
+    @property
+    def ids(self):
+        """
+        List of all patient IDs in this dataset
+
+        Will copy the ids... so modify them all you want
+        :return: Copy of the patient IDs
+        """
+        return list(self._patient_ids)
+
+    @property
+    def mris(self):
+        if self._mris is not None:
+            return self._mris
+        self._load_images()
+        return self._mris
+
+    @property
+    def segs(self):
+        if self._segs is None:
+            self._load_images()
+        return self._segs
+
+    def _load_images(self):
+        mris_shape = (self._num_patients,) + mri_shape
+        segs_shape = (self._num_patients,) + image_shape
+
+        self._mris = np.empty(shape=mris_shape)
+        self._segs = np.empty(shape=segs_shape)
+
+        if self._patients_fully_loaded:
+            # All the patients were already loaded
+            for i, patient in enumerate(tqdm(self._patients.values())):
+                self._mris[i] = patient.mri_data
+                self._segs[i] = patient.seg
+        else:
+            # Load it from scratch
+            for i, patient_id in enumerate(self._patient_ids):
+                patient_dir = self.directory_map[patient_id]
+                load_patient_data_inplace(patient_dir, self._mris, self._segs, i)
+
+    @property
+    def patients(self):
+        """
+        Loads ALL of the patients from disk into patient objects
+
+        :return: A dictionary containing ALL patients
+        """
+        for patient_id in self.ids:
+            yield self.patient(patient_id)
+        self._patients_fully_loaded = True
+
+    def patient(self, patient_id):
+        """
+        Loads only a single patient from disk
+
+        :param patient_id: The patient ID
+        :return: A Patient object loaded from disk
+        """
+        if patient_id not in self._patient_ids:
+            raise ValueError("Patient id \"%s\" not present." % patient_id)
+
+        # Return cached value if present
+        if patient_id in self._patients:
+            return self._patients[patient_id]
+
+        # Load patient data into memory
+        patient = Patient(patient_id)
+        patient_dir = self.directory_map[patient_id]
+
+        df = self._survival_df
+        if patient_id in df.id.values:
+            patient.age = float(df.loc[df.id == patient_id].age)
+            patient.survival = int(df.loc[df.id == patient_id].survival)
+
+        if self._mris is not None and self._segs is not None:
+            # Load from _mris and _segs if possible
+            index = self._id_indexer[patient_id]
+            patient.mri = self._mris[index]
+            patient.seg = self._segs[index]
+        else:
+            # Load the mri and segmentation data from disk
+            patient.mri, patient.seg = load_patient_data(patient_dir)
+
+        self._patients[patient_id] = patient  # cache the value for later
+        return patient
+
+    def drop_cache(self):
+        self._patients.clear()
+        self._mris = None
+        self._segs = None
+
+
+    @property
+    def _survival_df(self):
+        if self._survival_csv in survival_df_cache:
+            return survival_df_cache[self._survival_csv]
+        df = load_survival(self._survival_csv)
+        survival_df_cache[self._survival_csv] = df
+        return df
+
+
+class DataSet(object):
+
+    def __init__(self, data_set_dir=None, brats_root=None, year=None):
+
+        if data_set_dir is not None:
+            # The data-set directory was specified explicitly
+            assert isinstance(data_set_dir, str)
+            self._data_set_dir = data_set_dir
+
+        elif brats_root is not None and isinstance(year, int):
+            # Find the directory by specifying the year
+            assert isinstance(brats_root, str)
+            year_dir = find_file_containing(brats_root, str(year % 100))
+            self._data_set_dir = os.path.join(brats_root, year_dir)
+            self._brats_root = brats_root
+            self._year = year
+
+        else:
+            # BraTS data-set location was not improperly specified
+            raise Exception("Specify BraTS location with \"data_set_dir\" or with \"brats_root\" and \"year\"")
+
+        self._validation = None
+        self._train = None
+        self._hgg = None
+        self._lgg = None
+
+        self._dir_map_cache = None
+
+        self._val_dir = None
+        self._train_dir_cached = None
+        self._hgg_dir = os.path.join(self._train_dir, "HGG")
+        self._lgg_dir = os.path.join(self._train_dir, "LGG")
+
+        self._train_survival_csv_cached = None
+        self._validation_survival_csv_cached = None
+
+        self._train_ids = None
+        self._hgg_ids_cached = None
+        self._lgg_ids_cached = None
+
+        self._train_dir_map_cache = None
+        self._validation_dir_map_cache = None
+        self._hgg_dir_map_cache = None
+        self._lgg_dir_map_cache = None
+
+    def set(self, data_set_type):
+        """
+        Get a data subset by type
+
+        :param data_set_type: The DataSubsetType to get
+        :return: The data sub-set of interest
+        """
+        assert isinstance(data_set_type, DataSubsetType)
+        if data_set_type == DataSubsetType.train:
+            return self.train
+        if data_set_type == DataSubsetType.hgg:
+            return self.hgg
+        if data_set_type == DataSubsetType.lgg:
+            return self.lgg
+        if data_set_type == DataSubsetType.validation:
+            return self.validation
+
+    @property
+    def train(self):
+        """
+        Training data
+
+        Loads the training data from disk, utilizing caching
+        :return: A tf.data.Dataset object containing the training data
+        """
+        if self._train is None:
+            try:
+                self._train = DataSubSet(self._train_dir_map,
+                                         self._train_survival_csv,
+                                         data_set_type=DataSubsetType.train)
+            except FileNotFoundError:
+                return None
+        return self._train
+
+    @property
+    def validation(self):
+        """
+        Validation data
+
+        :return: Validation data
+        """
+        if self._validation is None:
+            try:
+                self._validation = DataSubSet(self._validation_dir_map,
+                                              self._validation_survival_csv,
+                                              data_set_type=DataSubsetType.validation)
+            except FileNotFoundError:
+                return None
+        return self._validation
+
+    @property
+    def hgg(self):
+        if self._hgg is None:
+            try:
+                self._hgg = DataSubSet(self._hgg_dir_map,
+                                       self._train_survival_csv,
+                                       data_set_type=DataSubsetType.hgg)
+            except FileNotFoundError:
+                return None
+        return self._hgg
+
+    @property
+    def lgg(self):
+        if self._lgg is None:
+            try:
+                self._lgg = DataSubSet(self._lgg_dir_map,
+                                       self._train_survival_csv,
+                                       data_set_type=DataSubsetType.lgg)
+            except FileNotFoundError:
+                return None
+        return self._lgg
+
+    def drop_cache(self):
+        """
+        Drops the cached values in the object
+        :return: None
+        """
+        self._validation = None
+        self._train = None
+        self._hgg = None
+        self._lgg = None
+
+        self._dir_map_cache = None
+        self._val_dir = None
+        self._train_dir_cached = None
+        self._train_survival_csv_cached = None
+        self._validation_survival_csv_cached = None
+
+        self._train_ids = None
+        self._hgg_ids_cached = None
+        self._lgg_ids_cached = None
+
+        self._train_dir_map_cache = None
+        self._validation_dir_map_cache = None
+        self._hgg_dir_map_cache = None
+        self._lgg_dir_map_cache = None
+
+    @property
+    def _train_survival_csv(self):
+        if self._train_survival_csv_cached is None:
+            self._train_survival_csv_cached = find_file_containing(self._train_dir, "survival")
+            if self._train_survival_csv_cached is None:
+                raise FileNotFoundError("Could not find survival CSV in %s" % self._train_dir)
+        return self._train_survival_csv_cached
+
+    @property
+    def _validation_survival_csv(self):
+        if self._validation_survival_csv_cached is None:
+            self._validation_survival_csv_cached = find_file_containing(self._validation_dir, "survival")
+            if self._validation_survival_csv_cached is None:
+                raise FileNotFoundError("Could not find survival CSV in %s" % self._validation_dir)
+        return self._validation_survival_csv_cached
+
+    @property
+    def _train_dir(self):
+        if self._train_dir_cached is not None:
+            return self._train_dir_cached
+        self._train_dir_cached = find_file_containing(self._data_set_dir, "training")
+        if self._train_dir_cached is None:
+            raise FileNotFoundError("Could not find training directory in %s" % self._data_set_dir)
+        return self._train_dir_cached
+
+    @property
+    def _validation_dir(self):
+        if self._val_dir is not None:
+            return self._val_dir
+        self._val_dir = find_file_containing(self._data_set_dir, "validation")
+        if self._val_dir is None:
+            raise FileNotFoundError("Could not find validation directory in %s" % self._data_set_dir)
+        return self._val_dir
+
+    @property
+    def _train_dir_map(self):
+        if self._train_dir_map_cache is None:
+            self._train_dir_map_cache = dict(self._hgg_dir_map)
+            self._train_dir_map_cache.update(self._lgg_dir_map)
+        return self._train_dir_map_cache
+
+    @property
+    def _validation_dir_map(self):
+        if self._validation_dir_map_cache is None:
+            self._validation_dir_map_cache = self._directory_map(self._validation_dir)
+        return self._validation_dir_map_cache
+
+    @property
+    def _hgg_dir_map(self):
+        if self._hgg_dir_map_cache is None:
+            self._hgg_dir_map_cache = self._directory_map(self._hgg_dir)
+        return self._hgg_dir_map_cache
+
+    @property
+    def _lgg_dir_map(self):
+        if self._lgg_dir_map_cache is None:
+            self._lgg_dir_map_cache = self._directory_map(self._lgg_dir)
+        return self._lgg_dir_map_cache
+
+    @property
+    def _hgg_ids(self):
+        if self._hgg_ids_cached is None:
+            self._hgg_ids_cached = os.listdir(self._hgg_dir)
+        return self._hgg_ids_cached
+
+    @property
+    def _lgg_ids(self):
+        if self._lgg_ids_cached is None:
+            self._lgg_ids_cached = os.listdir(self._lgg_dir)
+        return self._lgg_ids_cached
+
+    @classmethod
+    def _directory_map(cls, dir):
+        return {file: os.path.join(dir, file)
+                 for file in os.listdir(dir)
+                 if os.path.isdir(os.path.join(dir, file))}
diff --git a/keras/downstream_tasks/BraTS/DataSet.pyc b/keras/downstream_tasks/BraTS/DataSet.pyc
new file mode 100755
index 0000000000000000000000000000000000000000..cb9d78c1bfbfe41754e41c6b9d249e6c86a65927
GIT binary patch
literal 11286
zcmd5?S#uoK6}~;AZAOwuw(%ltLL)+u1Bj)H3b-8bB5W2#p?VY>6ijC{)3RHhnI8A;
zv8|My6qpJ;<O!0eB$dkY3-Xe`kiU@1W8PAE<1H`b`_Ac2vcM9A6qftWUC%xD?Duq6
zKb@}s^RrJcw@v!5ir>?C>>p5cj9EqLm`=rX9kYsx)+=VUn$<_l>S$IUGpplLubS?J
z=}nl`3FC0hi0RhMN?NPuwaL6TWmZD$Hf=fpRx_P3^MNsUjd^=@pXrR7pkdYlW+LyM
zAx_QtI#K;Siu(Dm8=Q0(TS==KBz63v_59P%KK<+qZvD(Kxf;bM-PfbOyBM?*{LF83
zq;lFOt^RrxcNT)q@I<}7ay7K>I$*hjIJyyb0_%38RwwLVaieuNxf-}<<JL;k?O-Dt
zB({#VZh$I>hxiHm?n=<NQGC7|-E@0VC+OORdiWXsEzdi^G#O!Wz0=bcyS|(79D@6B
z4e00GsG$2S9t%pC0Q3P3>SW6Y;D&GjR9YP|0f<%++Ms_-n$@fc;$d_oYfg~DTvd~P
zr88Cm?6~w#ret27k_okJ;k5CZ^OL}%%>(eEtenGRe~sd{V{RMc<7kdaDr|04$-uh~
z|8r=>+(thtqb3<+Wn&~88aKDAG6d`Z3UlO?tV|ln1uIk8(6mYRNl$~KhNC1iY$~+H
zbhG`O-JB-@m)oQ<ktNbiJoaG}3ik3L^G?Owam*dT85n+2G1tei6jO{AT#6$Zv+xWK
zhn2#vK`RM^e&UCnVyd0Nun5T0sU$88HZ7TZsuQ-8cGMfZbOJ3)Xf-o`06)nzicS~@
z?Iemf{a$MT>R?I~CqYMqr5oBrD%XNdn@nNQFE+Qb-nYZ}MtGyu_1pGFLWH}(jgbBR
zu$N7@DtnuQKq|{oKS)M7rx#-jsoCI)O=_hrY;usT9DZlrZ@1c4fg0zZZ*`#shs*Q*
z^<lTW=~HVkiJ$_Y5X8{PgyI8&`C-2k+zR4(GDJ|ZL3iEbvE_LAW;~3L2ioRiBR>J|
z_aS#O!A-D5nE3v2)Gg67PR%)n=YUhI*6^!;ZSsNC${zb2G(I$9Y#j3o5o?MRq$5G2
zVm^YPL857UxYqsyMcqyRH3!`=fsud-p?z@ea1BVqBqWiGR<G6VW_@d$ZpuUVwZ(c4
z;pCtdw|Z{>q`LxB1G=pRF)d5b4SHaxrFo$d5?B~Y;ua1H<Ai+*AaRfkW577$_Jf;S
zP`Mc<SKX-J-Bc)ppdGG<L8r7+m;^nWgA&!@LCGl!f^|`(s&klnLxKpIW})(1bcd=U
zJQYfLB(Z1_6h?-QqC<GO8?AW`lQXR$KAsemr+EVQ2u#GQtQq6zgl18vWTRr=9k*1y
z6P`VRm6m5V<A)s~0#W9k=kQp{B;`Sc!GSPv*!~tpPP!$i6j?{67pzV>m`Vt_mM^#z
zVrDxUC~v}!U07IfZA2duu1jZ6fNe%Y_hzfV1HaF4aq6Z@Tjo0`BPM{QN1IfTL#cx<
zvom2xVj%Q9Cy)qc;$E6Oj&2e}!iH-#6CX~SP4-sk3mhF+YAq|{XfeG83N>sr8-Cbp
zT?y>&(Ica1!d}L&<?&3V;fy==9XR(W1`8}FOnh9Lie5h(+k)YKED;R7M^M`vRy3#Q
zvC7i65vys%iIT}Kk*0s6qBtSOfrmK)wJO>bv|)X!ba3!@(6YNiNV?IyllYUmzB<-%
z6aUfN`q;o0!U7Xk-E2%2?s)O?lj8QO<_^5_h}oEuNuzYbr`VpBHh`ghJu;X2=gqBi
z1V>o==(ZOxKbL{PGW0gg?NKv(XH49&qM-u<<?e`auK&ec>f~No{D-~Tf<YGwi%!v9
zfRn!Ti$04iq-}~`e;^Bk-XPiZM0jNNAq;sm^d27LiDM;!;Sz^|6`w%3G|S>1!5Gm2
zbvm<{DUz3256*)N8FX9iV4loU14FH$pr!b*Ne*k%qZlTfoI>&FA-5PM7^C~Bn#kA^
z;i}h~ab_xqoI{mbW!{-_j#Q6l5=2^1E!&*?G>Tgf3mXteUVeavnLJT(am+>Mdfi-N
zSOyW1xG{BK?_ptX9+sec);+Vdw9SSfAdaJ++X?M8^<|lDiPkm{wb;Uhoh&>L<DD?-
zx8hCMw0@GhDFRPd7fxnb;sDPDE*?)J5y4743_NmGjTY^@(DOd@6HaG4yo*JudE+zi
z{Nn8?6l9cW-U7_F2Cgt$*Pu0X)IZg-!w~ZK9YdR-#H^TWV<tW&gq2`%wh2+9K5Fy`
zdPA8U=zzqs8>6CJSPOj`GaKWw{I8-!=z&^FKNei8m{}+&z#zat<O`AE*!CGy*^DVc
z3ftkf1f*bUN5!%t9xgW#6%!d%LMSw}lkoS;0aRPrK4AJs4T3zVIxu(#C(}tXggWI&
zj(ZA?rWkDr__v9T1QjjUA{gQ2NrU4;a7r?wAx=62(V)gU*$PBMSvXaarZ-b~Dsgfp
zL)4OsWxm872Wzv*VaJ_&%+9&}D8X$mun3?QmggV93{icF;xE!Zyb{MztTuz{o31b7
z(Q@?baR=`N3b8}$FdK<jly20PU$`#$Mbsz4m<6+Htmx@Hu~<h4f*K5i;xXPx*nN)`
zny0{u^%3zG1@WHYbXtJUx?myk^nEl#Rw8mUb`FIZZ#W054QH}C<xE!?7tcA5RlZf3
zhLt&3J&NBpLmEEZN3`WpR45JjPbY+%y|igiv;qf3^Ug)f^E7@+Q`XwupcShZ&5ic%
zT`3K1CyoYs_4p-Ps@5=uHAOTthl1!yOi)Cj%~aY4sn*&9rB#`ht10cI_*@-4g+_*d
z6+k=&n8KHgi+*<hk$Z`7D;p{qs_$dj{n)`^>SH`|J!EJw=`cK4p5MnkCs6o)ztszT
zUj)_n5eE*tXet$tVS>kdtXez}Cy3z@U3Qbf9=Rpn#AEENa&wwBZd@QIwH>2A39%o<
zWJ{G9t4uX&^+vrh-WaPLXiU}~t&NGZOE0=@%#nXIu4nPsX~;pKIg10PqyLe)sDAm(
z1rr&PynvxX{z8*P$Xu{rk{9fsl%{5i(7Y#$!O8V3sj*KcPiD=AG^euWj5MdS=6-4J
z%bEwI*~pp)r8$!|A27io)7hUj4>Nnh3sjr*p+@i#Y25^!Aa_t5n)0VaR3(RkTc&-4
zHUe%46Ck3<q4eLUflep?NhVimiZD6WCW1wTgIIexUCV5Xbi%~Lx6!d-7?B_Nw=p4(
z1}cGMj3`Etr>SRInMu>1Vtfwwg0;W~+Y=l3AFUuqrxmy$tsp<A6-mT!G6X<-4wm+X
zDS5zj;CXcGL-!2jSRKxmAIU05v&w8%c`&OS%PPmS%0pS@TUq5{R+?g_mP1sHeH}$p
zuEd*ZmJc=^jtA*Nxi`;ARLC?0;<z~%i9hXLLvF+RaTFzUZmSQcvk6-_C$|073m4>f
z>B5D17vM#AMV~`>O6DHh>Md*%BdcZ18Ec`(*iw9wW^l^edM{#9LWNw1(f66D^o#gP
zd_tsY9yrvi5=m`Da78p^eu1cX4WD>QhUS%9?O?!NbsmD|5Sy}1@8e6BL16h;uUyee
z7ZoB*TJVCcrdjP4^HAs(!>Nm9R$KE%H0DLGt^inBA!ZMtr9s=1PRwj9(_2~oiN?<_
zP%WHvX-;V`++P!VUmgKbht0r9AGa*^k-i0rrQ`9UP~LOv;d$#2@H=#;hbmyHgOt1l
zQ+j14i-44vHG*;B70JU2$y1o{ovk+=#P9If7f_hW6s{3dm18JpoulxYQzKJw`|^j&
z1%Hn@$M~zg=~$b7b&GGkj*bM1EM608YoW81)I!0@BI%28Hhx09ZPhe&9s*<bo{`>>
zymwT3FG=rc-a96}J?TXv78WbLtk7HLk=_L))>>O~TS%!fJ$O%~nNyad8f-4&de@Xh
z&kFinq~{Q{<)HJplQ}r9X438{X7Z3*fi4AzC5ze1dOv)PbfH3Qh3&n;e%g9fqAF_C
zA^uW@D4>N5mqG{%|9x02K!DcYFx67_%=jV15aXq%%~*_2?roZAXt2Y}0umrgX7e$!
zkezyQkvs!%#;xUUMY0OUT)MtwM&K{5)lK}WaU2J$n{V|qSn0js&j6m2aV5)5l7t0U
z^p?paW}dth8t1|MlkPAHyWvln)}+b6Zw@nO%^5dYU*Nh0(pz{Vm(lWN^PW9&FdnJ9
zJWqA<e#An;a>}{dG{H=47Sr)`+dJ4H?;2NjxrmWFUqCHK$@ys5?}+i<b$BZ<{tghL
z$Y!G9R7EilA{?A3;_&|u3mKB+bh?;30?~tli8&v(&&cj>WeTqVWQoE;&O+vMGSd{6
zZEM-)E3G2}vM6>>S}yq)9wjX<J-a3?!m+QQ9f%~#+CkA;7MiHgT|~P?5;}mg<M3jR
zi+uH1+uNDB<Ue@y%(z*6GtPX8Cn*$7&Rp_}r8C2<?DfoCG73ZY#b+iPDB$*2D46B}
z*)`vT3ZiQ5ktmr%ns7x0R|Xv#%PR7kn{)8SQipIK(F$H&Y6WjnwSvf5D+rjif`C~o
z@(z=55HRPC?gzjw*TF?x?X0}6(fG-Q>L8_=y$RBcNIpAPOupR9dzUrED#RCU6r(3X
zC|r398+vcESY^Syndh_k35ynsH5P3ajFr8B#X5@JtKw<Qo*|1|RLp1|d}t7|J@BB@
z;zLI%ENh|yLT!L?nQG=<3#3bL5ckdj6Eo+Qru5*-wmGh4?<An(vW2~(VHfYikTPO`
z4bQLdRo!#VizNADR^v7yk<gRO@_x)>Z(2$fKS6RZ1mOLjzI(PX_utTii&*3b*NA$n
zG2bH{hB*DRyP*RmwGe>v3#R+a!JAAfZ<mAZLLgU>EGV&$W4mp_kc}Y~p1!Uxi-f37
zP8n|r>-R_sO3{lX1#P3g!=g}>-azI;@wF4fi-3Y<o^u-!3TE$21~DUFi43=}>DezN
zLvF`k!qh@0;IF?|gtACg(6D9`n4E|CK&HeoPKou{2%(^4S=*?JhmtEU-(Yw*&?T4P
z;Q-NQ;N3)f_a={*r8jsIMw(>kfig4mQ!HR`%PAh0W@fhXgWQ8PFNSK5N$~tWUVKX8
zk(Rs17Z*F@5nqyn_#Q3n(f<fraU3EZII;2GL9u)M$c?wYUi|3OG)fWtF7F9HO2@lj
z0zVkA{O<Mn+~x&9ow3kw8BNK+^7|lIq`lFy$h#o#0spyYp6>x?i5+sBy*oU|o(QYR
zrb!ySeAt341(OeLBOm(^iVsWQ@Ib1u<|9e?^JAX!XJK4OVL!-)yu*j0ikDyJD^y*G
zw_j<cN+8H+Al3kw7_YhoGFX@QWAu~q2V|n5<dpYA6p{!CEt&NuntI(Q&SG$w%oAOZ
zi+z^jk%;yzKRW#UZ^~klgj>}R>nl{*la!XGKx}ud_da{@q)Nx;jvIKC{y_#7=_9<D
zID#(k9E(L3!cch)F<|o*7F`w*3%R$zU>WZ;3%StH)oZ9kv*gh_dLW?@D=Vhe`x%=*
zM<JQWcDH41FTmHE9YIJj$EcoRXUxxI_&0d$w^58$4m?rY-`L-nX-wj!#cX2&e>ME!
zHAeQQP<e+Jb@KgA)W&NT(J#uz07>1Jg}kGxpS|J3tih(o2tii#!?o60&=n%1?x9~l
z>l3yur0)|YR?;41dxvd&qZQ!O#q@*01-#zDZ5!Vd+ES;yU}8GNdS@_GUdf0%(y-s-
mS$9JeQJ_=$2I-|57TKdH@J<Je#b0FxAIr#JWvqJez5fEE5<H;*

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/Patient.py b/keras/downstream_tasks/BraTS/Patient.py
new file mode 100755
index 0000000..88afaab
--- /dev/null
+++ b/keras/downstream_tasks/BraTS/Patient.py
@@ -0,0 +1,88 @@
+#!/usr/bin/env python
+"""
+File: Patient
+Date: 5/1/18 
+Author: Jon Deaton (jdeaton@stanford.edu)
+"""
+
+
+import numpy as np
+import nibabel as nib
+
+from BraTS.modalities import *
+from BraTS.load_utils import *
+
+
+def load_patient_data(patient_data_dir):
+    """
+    Load a single patient's image data
+
+    :param patient_data_dir: Directory containing image data
+    :return: Tuple containing a tf.Tensor containing MRI data
+    """
+    mri_data = np.empty(shape=mri_shape)
+    seg_data = None
+    for img_file in listdir(patient_data_dir):
+        img = nib.load(img_file).get_data()
+        img_type = get_modality(img_file)
+
+        if img_type == Modality.seg:
+            seg_data = img
+        else:
+            channel_index = modality_indices[img_type]
+            mri_data[channel_index] = img
+    return mri_data, seg_data  # Load segmentation data
+
+
+def load_patient_data_inplace(patient_data_dir, mri_array, seg_array, index):
+    """
+    Loads patient data into an existing mri array
+
+    :param patient_data_dir: Directory containing patient images
+    :param mri_array: Array to load the patient MRI into
+    :param seg_array: Array to load the patient segmentation into
+    :param index: Index of mri_array and seg_array to load into
+    :return: None
+    """
+    for img_file in listdir(patient_data_dir):
+        img = nib.load(img_file).get_data()
+        img_type = get_modality(img_file)
+        if img_type == Modality.seg:
+            seg_array[index] = img
+            continue
+        else:
+            channel_index = modality_indices[img_type]
+            mri_array[index, channel_index] = img
+
+
+class Patient:
+    def __init__(self, id, age=None, survival=None, mri=None, seg=None):
+        self.id = id
+        self.age = age
+        self.survival = survival
+        self.mri = mri
+        self.seg = seg
+
+    @property
+    def flair(self):
+        if not isinstance(self.mri, np.ndarray):
+            raise Exception("patient %s MRI is not a numpy array." % self.id)
+        return self.mri[0]
+
+    @property
+    def t1(self):
+        if not isinstance(self.mri, np.ndarray):
+            raise Exception("patient %s MRI is not a numpy array." % self.id)
+        return self.mri[1]
+
+    @property
+    def t1ce(self):
+        if not isinstance(self.mri, np.ndarray):
+            raise Exception("patient %s MRI is not a numpy array." % self.id)
+        return self.mri[2]
+
+    @property
+    def t2(self):
+        if not isinstance(self.mri, np.ndarray):
+            raise Exception("patient %s MRI is not a numpy array." % self.id)
+        return self.mri[3]
diff --git a/keras/downstream_tasks/BraTS/Patient.pyc b/keras/downstream_tasks/BraTS/Patient.pyc
new file mode 100755
index 0000000000000000000000000000000000000000..cbb0dd1c13efc794dd4415b467dd3debef14a234
GIT binary patch
literal 3179
zcmd5;>yF!05FR_XjeCQZt+ZUtWoZCut3?8#P@!IyLMs{}?@Cn{RmQbXcD*=uYM)da
zY4;CQyaKPl!|{&?fbSb8*#H%-P$in=OlFSfoHLhi&baaW8SnNlzuk{z_G#e%Dn|7k
zNFuTe>PX^B=E$x)=Nq!yRK6iuOLnLMt_`j!kFlsDNlTd(N!pTtb}0TNa&NcG-L`vO
z9`Y54cQegQ-~TqUsmZOk6<J81T;9CA`I+xso7nxL?EANi+}|>h#b56rQRZr8qkLGD
z$%aWLA9(2>_zZducC;iP#-tsLCdLhn>SquuasX=`u`bMUj@7qgR}LewO*w*%j%?lE
zmg9!lmK?O@sKKd&4vjx<id~t_9Jl1CCAKREp8ViSnaEL7u+hVHv8VWG?HG%(r6Wge
zxq|7tWL+83dxp9C6~y!L`KE{xKk}<I-^+|Yt|M`&^3zeYXZ$3xk*9k7aa2a5xkAVX
zVUi*|TWM)xTa;5jE^-^CId)oJ%|rU7v6C|I`#X~{PFYfnd^_COF?m&#%hPv)TlLvo
zjbOmy{b+0kz0-`N3zCm@+Kk3_ib#lz$~06Z#8PBX<i;`sSz1}xY3X&IKG265d`2)u
z_Ka0eEVrdFDv~Hmu_K?}nF|^*vu9tz<Xj_6^CXQ;)#D-hWEQ(cXmk%+#aO9OnY|Ms
z9qolfz)vlMpc<UC)3LE<uxq>@<+;gtk~!>QLX=cA<9ZqGY+s%McVj%YFJqE^h0A78
zvw8(YI_I6XbHQ14PP^xvuIo8xotSZ=pA7E}jA{aMm=mXSFn+JN0|s5<iC_dI0Y;z?
z@X{GVtvv%Q!MIHT0&4*8m4{~pKjZ-#YsdJ*69BOxM;&63&+nohwtLKIbrV&yz+^Rt
zn&QAub6faP?wdp8lL$j#{irOX>3@OeEJig<t7UvMU%GAIzsB8t9Luo!c7IVFKG8{o
zmKQR&PhAM55iS}O87`B*@1SY!`?r{FzZlZPdPn%3_>27)7M-l0R~JFAHVt~rYtSYk
zJ_8k5C4onBiiDUCh_hPxEVxA>sV6Ee&ed{L8v|l3I8SncgaA`yDtR(I*P!zccmmnu
zEQ-xK9_ljj6r#>K$8*{MsaEg|<S~@=L%3eYsP2In-1xXhTT4HY$4%L7h|xB|s~_#7
zrJ}2y0AgFk#$4>EsQrV=D-vw?7`&K-gZR`E*#tufi-cf+axgWb!Dx|i1^@@r!N3Fo
zyx9&0JsPfeSDI+i<ASZPg-Q7+eH3LniL7g8^nAUoDw7R^*RVEto#YLYH%XYlr^TI#
z4-x0ohT-SnE9PIE?(7@WGL8m@I`}D=`T{_&g0(DoSE`R#@F-O{b<mQFh|-Ua<a$xC
zr@69LH<m&59yXZQ*LqdgO6BK;^&>x@jK<TtY&TNqN$n+VO3{JXRbx{-$B1kC^W+4K
zUmnJ0%;M2_Xjp@{xDCd?U5<?WFpJVsal?d)yXstY{!jNAb#*^@8{CQ0!8;V+C1KK^
z-ARqu=GRzLy%-+Spy%o#8<yRS&EUoHk#+N2ebg*|yz^HN2l~pYmqi%n(a40MWzmFu
zVVPtQ142CTK~!s87GqP|X~1d>)=Azcxdd`jEXqCcz7Af6Vjn~Ai?*}cIoIa5UdyAk
zHp4I}V%WmNwYCE_pDhRPTG0cOY5URFBYk7pn7uxwrdpcR#xSvIRt2kA8n9WY1<zut
b`g^60!xsd8#ZK04oW`q;=Xj0oYIpTd+{2Bv

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__init__.py b/keras/downstream_tasks/BraTS/__init__.py
new file mode 100755
index 0000000..18605d4
--- /dev/null
+++ b/keras/downstream_tasks/BraTS/__init__.py
@@ -0,0 +1,14 @@
+#!/usr/bin/env python
+"""
+File: __init__.py
+Date: 5/1/18 
+Author: Jon Deaton (jdeaton@stanford.edu)
+
+Brain Tumor Segmentation 2018 Data Set
+"""
+
+import warnings
+warnings.simplefilter(action='ignore', category=FutureWarning)
+
+from BraTS.DataSet import *
+
diff --git a/keras/downstream_tasks/BraTS/__init__.pyc b/keras/downstream_tasks/BraTS/__init__.pyc
new file mode 100755
index 0000000000000000000000000000000000000000..440c753f47d7a7e729d508fd4224ce8a925ca53b
GIT binary patch
literal 409
zcmYjN!Ab)$5S{F{RYH64;(3p&hprVADI!%$4?TEkK`2NFn{-XtO-eG0^z29YlivIQ
zoveZe@@Dep&EzHN=ZG)gKb}kYU44o(+Tof&0c;2vs03;T8wQ%eE&-K->VfKmPT>s_
z78L`id$1<qDnE+-fq*Yet*4m~#u^l2yg%@{L}IRrNin&}_<f5n&QG(Yv)Norq>%4a
zm&^i6yLDcTwQA2efAG@SY~41_XDeMb+M+~54VM=*iN;Ezk()1Ck2s*)Wf|*TYAWlz
z#$#ejGEg~x$Qd0l!g(GajnTCb%9TQN!dL07u~on!6@qE@wceT<wZ{<=ixyk2pMEqQ
qLk8EYaWq0ca+1IwgcCY;g5uw2bl2QAPPMhZi{3)CJxGS^H2DT9S7hD*

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__pycache__/DataSet.cpython-36.pyc b/keras/downstream_tasks/BraTS/__pycache__/DataSet.cpython-36.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..ab15cc89de1f624057b05a08b3484d6ab539f142
GIT binary patch
literal 9871
zcmcgyOLH98b?(PJ8jZo=N$??xYSEIVp&dX{Y)59XXi}s}OQsOVKt$C<a(gh{AbKz_
z-tHlZsX<;~RkVmVPGyy(vdJb@S?4$S2Y8dtGArjNXyNkroqkLY2vDi0Y)tj()A!!K
z_uO;OyYa^h3-;TWt3Qw4(X{{33V$Www{V3|06eX!dAetG^`<U&qiM>$)GW)r(yZcc
zcCDV(v~-Rwb?0`HyPe+W(|c`43$*6Kea$O-mFJpQIX0SgJXJjlPnN%UY&MrXV_R#?
zjsMlY7j*sW&fQkj+V&$GcRYP}^WDvN-*@cWqiBDit~(zM`p#Xy72)=F#}njM7`6I)
z1LbY_-l$>QJNrTC>|rivs0L30&kvpMpydVqN6ui+iS~Wx1J&Buc04Q;`cY`(UB?H?
z?h$T5-`Vl|;XvK%4xT!_f#-L_4f{7>j<(g%<5Kk4>*20nYqKf)GlAT~6)FH<1NXG1
z;jMdyXFk`#!;)8it~E<OIN?>FYsY%C0^IWE1g`?Oy?MbcujVaa>>S$a-lDYG-jcVB
zws~*GTgAPGzBTWh^euQgICwrL%Uau`U2t!!%|qoM?<DOGu5ce<qE9qei}c8t=pFMI
zgdDS_G%*0nQDvfaO43rDm}s#)4RB7N9T1-vyyo$(1=*e!)swgGVm7ocdKw5SZQX0@
zSdf3DfRt?G3fBQR)93Zij3fOBbWDtYFdmn-wSU)C8J!I?Ha6ag^&qx~ttjyOksEl@
zBjC%2o4tOt>FtG^<3az?Q$N_e-EMh)FKBOm?0X;Hc0ZOgbMO0oKMcan;b^xTv|VrT
zv>!&wZ}nW9{6V-Wa<G{S+{W<mOZ$cww4?T*H@w*(r3OGn8^1MW?1t+G{UCDPjT_xT
zyVVVEZWP{GiWj^<`R!<+4&7dB7*`-gk?+N&ZV*Os>A*h><C;6&R2VO~;Yd9Rp0v7d
zJA4wGUB8dE{-~FY3L$WZLq9INJr#twh5n;3p3A$NtJ4|0J-6Lz?_<IByx-j$b-RZy
zRRHaCKBo2+bSs_*Q?VJ(f99)3DK3S6cTde@$IaRdNefgItQxtbV|ol~4r600W5{JP
zj7O{K6@3L)O|O_0+>_sU^%N$y$zc9bKC&ykf``A;_Qd==w<bEJ>d1(+iSdQj(T`~^
z%<+HQPWrb!>;@6^8d^_Eop7`ZVxh&+z`;|m)$L|&yN6E7d*{Quc0R-PVN11oPXD^I
z1M2_=?fQzw!0-A!2wzBxK)WGxp(|1?2m$N~)|pPC{Ai>w$8D$YKb;}vX%Ou@gMRlg
znPup=gT27_3M&PX-wX4pa<w6Qs5Yy(!V3VRHcLl37y(7Th$~T?L~V3AzJ{SH7#bUa
z*U;4^pvjr>xRed>9<EHZ-z=O;!njif+fXD!Edex4nX@@xkYc!mKvCc`I%HLmk4iG@
zx40(f(5fr?c=?4@^DWb2aNBoqg`^he&Qqs})5rgu^XLH-if6>rot|lWRH-QNc=8t>
z1{m2M43k3$yl`V<!wCnp@4=ol_GGfd!N_^q>YsA3cldJZLJCXfD}eC}AXqH|%y6DI
zEzuSe>wXtc!hX#f*9(k5*XdlKK7a>s%?ER8iP(0+6HS+Pa%KyQuVEal3pL#hdaXx(
zcm@?ET9O}-3=2RrZ0M+^j~5HXaK!1<Pz+OQEVUwMbApa@7@-`1vzDg?yNCXea?0gT
zEYALX@hXOJoCw5!0O8_$dZeG%j^JzrH-H<F*(pt6G=4!BRF)?reWFvVs_0oavZ6WQ
zc4t0ue0R0a9XKKLs5B{cYUn9X%o`f;1>hCpkGCFb{qH<`FS5{5KZY^-{0(`djOWEk
z`J#4IiIyf@fh~CFxTI^3|N0@03kPE`Vkn3Et)bsoRx2RCIS1al($bulV@e)kqd$zx
zes35Z%1J6=<9WQH$Z|!cP_(ac1<qpRhfRwUc`$jg366=_CHDKGh(M;F905B&?6%r|
zqnaqM&GSu(u*vQOS7dfvP2W_MjyTtIsQ3xvFNgd9gHpR+(`!auuNxKPGOYiKxu)Ct
z_<TXCin5s>FgHfq-{wT$1bB7{jMTtr7&>731ls=zWbCm8rlQ3)BxE$lf0L`;1IT>n
z+<x%jgnl9rRD+)51>r&B5Hh_T>~`R$!>M_=J~iKr0fIrlr4C^)`cZ1@IeGf_)Kc$k
z!5qE@n$_C`JS`}qSU)oF1ixY{o8V{YOr*bB)0gxa=a`Mjog<~6rc*TF*FX?3fk6jV
zwH`s<C;B=Z<lo|sR^y<euJKOqu&qTVnTHSyK^<F;5YlzZkait1Ug=aZ`Y$2brOq6m
zC;EYL5!!(u&T#E${zQ9C+NmW7`(TRx6IeaR7G-|wzyh@bGtgAkQ+&C<6s<rv^v?|G
zG2CSaoTL-_mbmnPJaL@jF<VXuPs?CFi3FzyS~$DJf2Si5)+CNRdjqaMixmo|{F8LP
zL=q%LfJ@HBC4XgnIU5;x&eb==t4@CqA+_*Bga#X1ja5;+*#3k{`9q}!O0=|DO<xn0
zgjvpGDsNA{ibGTs^|-tTU5ya-4cbi;COb9}x5QR9xL^q`VtCVp-m15VEx(}SjY>iA
zL>w8z#)h{SmnF<QA&nxk0fvNE0ko>E*GyZtO-r{8MsFAN3&t9Zb4{<COSq3$3Ywhq
zHdo>qw@vxS+0t!8Z6#eW1e#(K;jBuDB`dePeoIX^d4|KVJvA66k?r4;UMhqJ+fvcT
z=L$4UN9AN?wnbFu+bLO*4zXX0M2SR6D2R+Pp+ZS3L{j1nYByt^csV-|Hw&?w3vvKi
zd#3g8V)RKqbKPI!l5mFZF8R$`#%v-iKyO}WVBK%^eAkU_*F}&r>JqQH?&DFboAfBg
z+=}4=EDKoVEBFqvMz6Dj$0{aTT_YwU@f~6$s6b>Mo=A|#!wVToScbi5*)_XXtyQd*
z+Pw7*t0E(4sPjJ)*ezUP43MY2-~9iiy+~;#@kMGpmn6PT8*P&KqHP|yB)`CC(qFW%
zd*>w;t^>c|T@-u~_$BWZ!Iywv_Fffy8Tb|NHNjVaJKpPpuL8g7eM9gy|D5-R_om?M
zl3u?RS4Gr{xiuNbOQh?!KoEW~M!SNT6_RvpgzJ%!7-rY(e>#B@ptp}+Gb$Y$f*CUI
zCdWnP37#e>x6q&;8%L!GCc0z6P+~Ovo+&x{oaE(p--_lvgN8rN$Dwk_#|i5Kk%a?a
z61XgIC7n;}ta_%*xK?OM);K34*9D#zctPMrftLinBJi@nR|Q@X#V&9C#se3|A8kvD
zbC?!dm?+bsI+6!n^|Evl0mW4ZwU?xM7fEU8s=*+->a_YWwTCbbSDWUK?%!{k5ANS@
zycXL5d;zOHZP-a<@^Srk7((bVw-{a|&c(^qCWwjG_F(*6)`Q%sH;;`0@@g2d{kYT_
z1pVf`J6#_+HrI~le)z2I4>>z>WyD+oCg(%Nl>{&@x%-bE0d@iFZkholW(wNNj2><A
zaxz-_+evb6Pn$3hlgL1e6A5-H?ayrjDg#+!|5|~PsZS{k$R<ZR5iiQ*z_Pa&WsO3^
z+LRRLZz=T`i;K)|Y$c<&FnlGWeA?D1i!+LA#RF;D1tyos<EBN(O&9EuB&sxR|AH%g
zA3!rK1eTVu0=R;B3F%77f|HUT!cE>+^cCKd*0gWDbQi+5?MHdpCJ(A+Ji|}1M6R>-
zL}w#Z#|{j21-`*Vz6E{ml<>TPXH=@>xs2zVcrK^U6+Ca@xw4HomBIh`mw6a*A0>&_
zOjQ8I2o_Xc2xD@Nu{ViiWEWD_*g>0v!p5W1Di5q)@NJem{)jaYB&!G~e8ei#bao3l
zzzys-&T>x-<gDr@8_S7ko0M#mf^AO)Kl5>~VBm@4Vg?fZ3hg0N9IaXx?@SM!T;uud
zATTcX&I}q@a1#4@3kY}z&K+3l`r#$<#PrOtm7TI@{DRd;4awMANsB56wt8PjaKQrf
zw)UyK367iNf6F<(lT~TRk|~#yRDtE3yo@6}%Ok&UJEJJ*24fa@sIa)_a~9&qXm5k>
zZE$14Ysn~z8N&-}<kKK2ROBL#;y!NTRbfJeATboI9j=~Y1=L?~_-6p|GRx&#gXrF1
z)c3^vogO{O=>NhSAtM>hvULN;Qi2xMaUU;`{%vT8EdF~vnmhUa5i6(0ROEGfI5~e$
zj>rP|0_W~wHwoufPcc{Vg<@mTk|sQK`F0!N46d>Ne{m&TLvTF9wImb<*QVO>6|B=v
zm1_M=sYddaOErrKnY{dnbTb=7D42Q<DZK5nU8Li4VlUYl`@h7M><r=P%+7K}#pHjW
zEqzFW(=DYg@WhswF28I`>@UNbe8rY9`OKE+1H|?)YLUu90-02^%0P%{46q~+AHaZD
z1mYtYa7*BvKwIFv!0hV?$JC`|G4%)^=SpxF5ql^V;Up|@AWJCgz+y{dl9%SAbIsTq
z^!>bbtFfd+55$a!YzQ|$BEx=6@POba1b;?APp7sCb_o8Q;1hy}1fK$&p$|+PmdIiU
zh*r*hFKmeXX8mriAE)GGwE8A4;r#c2h}EZlypz~`53w)!R%|ytdIBRYbihl{)^DkI
z@b>uiJA+Xd#dKul4E5mrlJ6<bo$XJ^%r`@%o5F!x7_L4hc!_#Yks916i_gr~=*#N*
z_?661o?@0~r0Ng8H#yi_AQti7)E-Gt^^$%1c;Ves_L+Tv-6+nL@s!`FPTwp;iu54!
zBJ~-^`Mv1$<7`@)M;^a*;!Lv+RPxf#Yx&8FfOGfi2LvzKF;D*c+;I&^QuR*HHW$~a
z3;w<BQqi-F8z(k6J-1V~D2jXwuYKhf_c7>$Q@5CuVHpWem!gQw>@zorEEwc!`9^Y%
z@@ZFEJFFt&BXRNbLs@J|Tw?K5?cw#fG8!U4^3@|eoMBX2==w3qwSe$MP;1i1>nAiV
zO+Zek^a@_gDZKy;CbxsMI5QwH6ey>dV&sx6ZTfjukzHqyMwjqYk|xC_F#`n?Fv~-F
ztFK3$Sl<IIskY80iCq2k1W9W-uL{Ay*Q13_KnX2>dNwUQ)SsP6OTml(UuZ#UC4v6Q
zQ!6E&>NeJjtNen_Jn?J>rMWb+TkiyA(=?D=!ho+wmAFn)rMd)Xvk4TD6<DxyCPnFh
z7ZOvt5&7mj{S+QSy1zha=q@gCfcZA4xD?b?zVse|d?>zlr1O;yzMTV_Um$BehH9u%
z@p<+Wa!JX)KEM>H8i!=~9pFg)IDK4V9R**sOm<A`hIEyRJ7g4BK|ndamdhnZPBrd~
zkIOkP8%AulyP<l_2{}KsQ*fyXP$-AlGBg(jQ!%p)VuP)%#(Bl)Lj4H=s|ZQC^ykFB
zPrx)vtg(`iS%OT4If@~GqJK<+1zHK!BA`(a<0eK;_4wEai09kgRv7kt{F9QG=#DUF
z3WWaa82V4R!Z!d=Uj3G}TwAU!)#g!Ly;!sGo5K&~*6gSFMq@dyy7=dnw(H8_#FZiH
zW34bYhF)C8e=7_R6(?*~`@wE&*Y7q>Ao9Jix$pu1)oCOB6wzEv9#J|Qweimiesd{l
zKzSJ%8UE8I%vz+l%{(|%{9c`e=anQT6{-pa0NEus7+W`zLiJ5Pg_i(IsN7iizH1pZ
MLcvOA{jW6RccjSaIsgCw

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__pycache__/DataSet.cpython-37.pyc b/keras/downstream_tasks/BraTS/__pycache__/DataSet.cpython-37.pyc
new file mode 100755
index 0000000000000000000000000000000000000000..b0fb3eb6c9dd27e905c2165c8f8d47838afd007b
GIT binary patch
literal 9869
zcmcgyTaz2db)Fl5!2pZJUby5^6g8r52JK)amF>t3!|*23lBtdD-AD>zX^ce=xU&mj
zz@7ogMPZXT%c{s#_KRJ9N>U-K{F16X=QrdB<R#-rKiNM)53YRY%mo7oOS_`7u{CFU
zx_i1$pZhtpH<y+y1wZS@wNJx073J6Tkp2ubuHy<G0tlt02vul3wWac1Yw3J9S_Qrr
zTP57}p4m5Brb=^-UU@gZTgknW+^f5ar?i&tDxx5YPZUu+(ONY;m4t~W(_KE%TXmuB
zD2?*?->o}d&%I*bZinq1H?(la(>J!>+Is69+qy9d_kDTAe%~M1x7~J#+gA<*H?9X^
zd(iczXu4w5u&mvEFR;5<%N|Pqp(otH?)h!u4er~1*ADkx`=)H~?$`nw1#TEvc-MB(
zq~Q^6-oV~<2Z1l|^!!J5-xqE#Xj;Dkag^<b8X4gO(Z^lA+@Y@Yr=xKlS0Djg1=Leo
zn%EGU(4VNFp&<%Sl$POw5~B1(IZ<0hv`tawb_s1uRJd)5s#wC@GWu#_nfokJ7c1zi
zh*hzMdlh5r;tY>12^ADP8xhIcJEJ{NZ@WWGr61ktx`iv)2bic6#Zf{v)F$dv{TUEB
zp&nzR0T#mIL^&|Hr!>*gV+sYZ%+T_vUEy|B&|6D<JSD8fZ{5af=v@{H5Hhy!bX06e
zKOzocv4bnv0HBpVsr^7ZR*!+lMEkk+z}Qj#Ly-jxHuOkqz8R@rWDVP)=MF;06FkD;
z^Y3l-2jNz8&<(c6{^0&2*W0?$X$!aSb+$fm#d|lL5147rU3cIHUa%$nM}r`gZoBV*
z=ZC=-OTbnlYR%!%=hju>b;6F{A6{z^jv7Ew8NV?lY147MffqVX^J>rUw0ps|X6~JO
zv?M&~c0yksIsNu9DnfojS42k73&O}abdQ3l>P(LlL`zOEk`KLy?Vi&K9!7f49iVS8
z>Zh{;h}zN6jS5a*dI4^Mdq0TE*>G!Zx`OCBopxs*8*XIdPIuJn9XTZY=r6li+Lh3%
zr~-20Fv5N8%7zgcf!piK3QpXr&Y-kJDuP`@hwzv(K$bB#GE;(FAc7H76}70Y;;O1e
zy@-4KH(pyn#10Xdek2*`6<ox_KPz1}JWtGtO7e89g~~+xOgT_b$WZ9xUs-nY+Zpz}
z5E>1ACrs^Nv<GCNzoBpAso(DP(!RYTJE6V(-fb&e;mWWr+kJa*#omQo0D<;gNoK(9
zxqXOTK(>G^2Cs#oP_`iiuq4=Lx`=eck;ED|?1B4e29-x%xNrM|-ch{D(Cv6#&lS0y
zywL3j*;1Lp5P3*p)^G*q09aw_$0`T`72d=Zt4ypgDzmSl$s(pknkO2nJdb9~Gh&w{
z`~NnsRJ32qaU~|)Lc!J~p&{!44V~AFDmf{JGw>t{e2NF}%JNZ+SN$sONoy#jRdu}b
zg<Z2FldYg*-@+9Tw%|K)os640{@08~_n=V3BjWCqrwOYPQ6TnYFMQ--X2&1KOz=d|
zY&Pw{C(G`2xwFrU9r+{sQG2j}vA5{u#Chbl%yt0bmw>Qb2AH8dS+iJMbnN>LJTdtd
zb6m?20z-?bK>7e0z$qV=Wu00(cz&urQ&jFJ%4}ovb<BfxAx(F@e*3-~oPvcxmgKJp
z4HH1oEa<4Ij+b-D(2T{{kQgS|m~wRy9%nE^z6@~M_GH2CU_2l>rS0c7r}1p_5~k2R
z7Kr~ugEsG~p?X$1hMVEGhPD>!2gU?O<EP|&3jCxcPvp)@GJM<%&9IEN^|TVZyxYnr
zHr$VXY)p)UDn<$u{i=fY652&-KiK|A8GQZm+o6e`+6j!&C$I7w1w1cL3Y*GtF|1E$
z2kOB)Cx)s#_{WdHE-*%;SfLQ?w})<HMXmz<RvEN)xF@PGo011@FpLUre;6JyCnb~d
zEZ&era!E=d$-YKKIE#@Rv`kt^z~n_bD8^zJ+wV;lfmA<f2JHN>*Y3ED5-V@ZBL2qv
zwk#rd+?GV_sFb`ZNjj!_4i%p>{><cin3UN4s#?`*YE3I@7hwHY^>x)!$7gd=m6y$o
z!Ksn!&_b^RJU$OXDj+lr9m&^3eWrd0S$|-HsOWJt4i@$Ck22M}2bmA-8~5(b=_f)!
z>Gy5n1&6UiNcGm=JAj)Grsm<w)O=G6;Q52LJc7L#go&-E#gn(EmU?#^=FkSt@-hM9
z78H@K9}#bkUXhtD@F@mk=`U5)x;o<=(>a-QB<Uy9$r|uKXdqMqfeuS@BZRz9)D1Yu
zf5IKT+F?;%raO6u9VOH!Fr5gl5YAE0F@m{+0;FAqj290|nEm&VY~!Fz&lB}f+k|!?
zeA65&tjzUSxu3KI0Uu1!f1y>&TFbmX>A(_c1y&$aRZH3{gL=3M-B5p^@rdTEP^d|G
zLf>MS{);(wvd3)O0X!{*@o@||WoV9fvHwnHAgqZUdHM!ieHts|xcuE@y;u@BIe<&f
z#3g%Wd?B6b3H#D(!6kd(he#^i0HHy1yRpWK7g-;YQobvtFIh`lrQ|hMNtop<rV?HG
zBA6(@0uU9t(A5xOpWkWeFxiogxFs^v$vI1~Nz--ct)$SjwekfWZxnNa$Kps%H_}8m
zDsY%LCygw!9;O7B0F;uYR&`6YbW^o7ir&tt=d^Vg=c-!M>$s0sbDEscHdEpmw@va7
z-X<=J69tW-&NdOw%7`slq0@8Qa(c*99EK&NKa3;WpAf$6Heg$d>iA3!r|GN=EwU{-
zE>@kdC1`~z#C|<wC1NEZL8KTHDirrZBstz7?WUL~T1gq=q#<@|i5Zagr&|AY%$}!n
z6Ma9!#o-LOyZCR`GNub*1M=oI3akh1zUw%V<v0jZMm=g*9p}NQ-HS&g#oY2G09Y1~
z$d&LNHuVul<tqfp4@)|EY@z;~T7*yz$t*nKAdi?AP$*$)*0O0;t!k-SG*_z?^A)qm
zGddW|enj2txPk~EOL$-Z|0KLfW;x|WQe2Kx-j;<vPI=K+L7UTFv}Y1u^lyl>oCMd<
zJ|{N0y^QvG@dCH&XkQR7a(e~si{d42ucB>>m$|)$_9gKOx7Xb>;#Kh)w>LPkej_Te
zsO7V2A{<>TUB5#E;RnTN7ZI~Ul1{W>Bh+HU?C67!Cr|>64lt^R#)-x)jptpXd0}CK
zrwIxzWYABvV<Uu#erm!{8qX*%*Eu^cb4G3r%&;OfGW<y<4wXYDPO!!h`8V2ihARwL
zll7E?HKFs0>$#qIk25@TgW*|*=NN7>JkRh2h8GyV$nYX7c47NB0#q2kzr!icQBq=|
zM423_&3Vuzk*1RfC@$Hky2RakNJ;}o`hIxHZVzB;k6;=uwe)Y_z1!07-M!m*DY88H
z0;=<LU?-8uN3|P40HMd)Y<Q74=NFf60hwsM3*+ZdCCHh2^GNfNSHp<yN5+Bg4O$gv
zx<7Jk+B+)0`?%u{X?5hvh`Bs0P7g(g6TrxD_V3>Z>;cxCBm;`g6ttHzdh|sr@oXON
z#L2le?ZQMX!V^teh+F5A@ysTmGLR<rFXb?q`jp&+baA8;(K0WNR{Hib?~&_RpQ1wf
zTY~*&ev{dQt)}?qrmv=$Px~5$IMA%-84_7JA{#{GmPwEfowG-rsFG>>H(bFx0E%WJ
zur#$*z*WRcNLLIKPKy5!Zqj{KU8Q^6n~aU?w;^mhZkUyAvY=|lGkhOgWI9`mbv9HF
z^g~Tvgm2K1Z$Y0A3_LgSj2aa`7w~)y&xPc<i05rQ7k3b+Qt&_iSr$gzMM<JPQx!ll
zf(j~M2xBse(P$jW@F}>gv5P(%g^l}*Di2h>ptq^q@n=*6L9&W)!bPkyO=q`}15oZ4
zrMV|2(yH<XbrxdL)=9E;5^QTK_^FS30TbugMHxu=-{=o0#ZgK%_Ri#?<7-?=8G(73
zcc!3$!eq9e*U<p&K)FLxUO76?o|rr{Y~?{gXg{Soq=IB@-B7~fp(Wo@krPnqc}Mw}
z-vq_=@h>xq@1|86BFU7>ajHP&oUDw)G|M8tui2x}>v>};@Q}jdo~@aSAH!~w-fPmq
znAV(8<THjZ?2#>lq)-wS!HV~BW3LJm!U(aUpxWWu0xKXXagYu`v_ggQZ9lx@j|PIx
z-{R<rXa6tW2q=<KOiR_k76V#T!+pF&`0qeNc=JChYi?!dN35I}Q<m2$b29qQ&qxFK
z9Od4_X=2K)EihNnxqN5dlEyULqqn;Nr%;W?e~T-o8iL~)s>Pu&s5aG(-$OcOp;W7<
zN;Q(VOsc7fkjl$<2ye;;5eg=rg9~pi^|N&RkXp|<8I6CAD?S;*(V3HFii*YmL`R|u
zLVBdc1<oC*O*5WzBpNTkn*5$4Vey$Gkq=<oLs1J?7Gg+AHB}i1A{qlU7~<0x+C_%=
z{Drp3u*}e6SYeoc7oj;d?paPe!UvfW+(yJ6a78!{3v9>|$~v&v+!^Pk+3ZX+w*7&d
z^=>!nlJ$Vi2+Iaj^8+H-Hi5q;Kp$M>E`h%x@F9VZ2z*T7Zwa&r{2jn4`ap?8ok(n>
zp%gOT3md|Jvwk<zj|Djy7MbQ`-^2r3ebSFNW1BA!`+{!yeqE3!(2_z2yad_$ZTU9d
z9>09cAN5d7M^;Xu9-LqNJ;lDY^C1!QwE*cRQ-F9azf0gbvP6p1po3ayP_{<Ctfr1%
zNDbuzvpgeJI$mR``cs{a8B04N-kaJZ4yvAW&V9V_)`D}UpI)2!wNjeWH>$;ly^7@$
zMrK9oQ`q^<a4|b0Gxf;hH|BVn4xo~kd|t~q%L2}vy$KYa$64b1x9G%GG~%jv!rM$-
zr!M%9c1lT}W!#uM;FNC*j>wAq2OaScYu{XW#JCJgk??dY5|PE{yo_}+wR|<^BY)K8
z-ltSWG@hyX&kqH*C6PhJQ%O~&s5lxTKyu{)9!@bTWOu(q=u#9&96_x~9dFEOT9SY)
z#`Gdy%rHI2<zg6$XJmM}ABF<u6rGJ+oTW`a&q^ZKDX87Y(Dw<oA{wz7$eDmy8j`pA
za@eu;^|6us9>6Im5mi5)LuoyuRW2C#a=4Hakc<nZMW^6GO#Sp!TykFg55Xl=pK_o-
z&ov|VRJXBLRH85Flqa4}pd^<@b}QyEo2G$8B~18oSh4FQtmKfu>0|;%L<($pa4JU0
zgqg(Dz_L0n{^mRV6dt0Y`kC^KKZvsf%#J~k4C&Asy+mG-KNMd+RzrL{eTr}Afcj_1
zTAx8Rq>+D~{e)~tKG(Zg0#)OH2!01`q<*9akwJA7e9_WrfJ$HdS(CpiOFAJTUPM4S
zzMRP=W==Kkl#k09EgM>-cY1*w(bBX&#E;u$>L8&UrrVHC=1j%RHi!+jw;N~Wx9F`a
z1pa~mmrFa;B5%cs5nE&VLwalzpfE>L2q4Kn#=!zv2`LDWQDEc7Mom7TM+p#BI=yxf
z^j-XW5+WYzX5vf%<Nuc!_!nHks{kmke$`y5u2k#Q3W}?nRTF<@{Gr^M{z-bHu@aRW
zNBAAbVdg}|A?jo8Aku~+D&W5rhDY*s%xjef-d=mp?X`3?_<Lb%=_dV?Q#1J#(OQll
zQ92uS@Xrcvs~&ftyo`(t|6>!RJzU(TJUEb4fQiHNVjPn)R*Mc8nOEaN^))(fa2~)w
U<;KMKT~n(P<d&h={z1|H55d9kyZ`_I

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__pycache__/Patient.cpython-36.pyc b/keras/downstream_tasks/BraTS/__pycache__/Patient.cpython-36.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..c01c91b7f0fd9177de8291ad4513e41b9108e4fe
GIT binary patch
literal 2817
zcmcguTW=dh6rR1Ww@yic7NryzpoO{*u~LMDOof^fQi`Zm(TGZx&~~yjPS#!TZf3@9
z9N8}<ulx`AOY_Q8{{l~(GrrUcAf!HYtT}UbuIHQcoiqMoZ7sQZEqZz-A>>c8QasS_
zLRGsUIO!4YaJO)Ju5G=Z53N@Od)V(4A+$aZ&PXrfA&;Pq?-L&L#u?#_Q@7XP?qkwQ
zPVOhWc_BLV5!1OSb+W@We0|y8YHxi-lkJf{tYnA&P?dB?Fb&Pk0k_IsrCHgpB;OQ#
z)Jk50QKZ{)jB_h<P=^vh^`U+XRXqiv$-vQI?{Cf&Y@fQvyV{$OQ)h?#(wTbN9|RNc
z)ER`QWa{e(^=U8(bUbK0bLGy&pSnj^butMy$TXbz6K4|MAxBrA5YXH{;_*&?Pbich
zE5<3KDlZQTLF*Z|&lSyw>_AY?G)wHfPR%46E+(Wnkn$V=@8nWsx{_m>Ri$Qm2|KN>
z#zQ(%=#eZtbZ=C{DJv5h)&0#qQL0L=c0c^-!R%~Y4ObPYLspA!>w<C1+5}=)>#=DJ
zWuDpr6BW7AV2<(1eBby5fHLuc(AG}VL~U4cR^+fOez?#)B@WE`Vj#^+o@YX}BC|ff
zhb2rC<5>v07sI02wsAf@Nc+GE<AG-ErykeBtYwF+EJcAkisL_sybK=w>q&c9>NfAI
z_DNM9ybyVNJ7Zi7^Q`?)@CVx|*d+>;-WR1%xoX#={UXm&UcD%lmVyma&D1m1z9-q<
z<My0|oAuaSLb&Ow$?Hg?cR`S->G;k?_{DDGgl_CK9r+&gXUH}zG1LI6W!}%A96!=z
z&a@rimNRfCJ}}J#rUlwZ9T*krU=RY+I+I}HPCVdNa+ClML*QEkea^(2M12?gpForW
z-(0o}WM5KFEtq88O!HD#l$BH*gCCJVaNU$i$;Pk4zWG(mSg2O%i(a(bcIY<lPT^R*
zJ*p3v<flkJG-!1pI{kka!lWT&28bbu{_{InE_CPvqy(+{h;X(e;O2C>|I(sY>leY(
ztx92S>b7Eu8AGD;WCI1HKq4=oXrfp{aS;T}d<&YMjTH-^*I1rq0&A4KgtOm9@eT?k
zj-~8OT!Bxs@ehsxx$A;u;sy*WBpgXB&z!`G9Uqt`H=r-Wfki>i-GyrNvLHPNa<j{u
z+~wYx)ANKs%fqKmF96-<V$eg-Z8ioy0zKgu&L9)^V#}*F6U{@Rn}zd(uyvtYPJaRl
z@R6hhm`YM)CP{(QAU$9zNqtU$pH8<G7&qs}gS=;AHImQs=d3Uu_{m;pD>S|mMPI%T
z8_H`aK0xsy3VYue<ttYfr*K8NPSdZUU!jAD6V87p>x=kZOj<q#_#}8xt?{3Mg5ijd
z0feBdu4#C@;5)biSMV!p@H}iF0Iz#;eL?&iYDQv3%Suy5%h9kN&*EuQ;sF3A$sy<C
z%an;32K0`JN^V(V8s8mfqDCfLz%5691movv5%dd|%X=`Q?B%;ifs?fbI6L~rkiDEC
zlOLm@)-4E0A_3&5DA05N0mRi?-^1uCie!O8Z@oDPNZVHUS`d7&Q*_UPXs&<|Zw>|$
z_%&g;`u5&A5U)IOyXAMGv>FDYt7JowrY1@8Z66h=H`DZJ#ERL7q_B^PYgyGo>an~I
zpAsWV-b8T=#jBXL8s<8A6+{QBjoH{qqGpIc+uuq|l){^w!C`?7D>;vwe4p)$!lq=i
zZr|w5`9F(Xs6~&>q9dIb%D%!jMcRG;%@7mcnF0F-V@qK=_q`Zia;RQ>IllZiRj0OE

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__pycache__/Patient.cpython-37.pyc b/keras/downstream_tasks/BraTS/__pycache__/Patient.cpython-37.pyc
new file mode 100755
index 0000000000000000000000000000000000000000..60c99e94f32b777e161404bdb0707d8620b6c5ea
GIT binary patch
literal 2815
zcmcgu&2Jk;6yMozZ=I3?ElMdcKnrybu~G>MnF=)}q!hJQp%IlV!7|+$C!4N!otbeP
zN9zm8g#-UXdxL*zuAKTWaN@o3N38%t>Y-!Jo451%es6y7jc={2Bo371*Rwxe0PRow
zm=_O}n^4s@2=4S8PPki;o@-mL=R@li!4CF&MF_3WgA=D0@sLN*#<v|F^Tvt88^><1
z!QBT=D>=HIZ0CjO(ECj1qSVP2)A03Kd!xPaIZZZ4dasfl`fXLxEx|N2SNFM9ZYs^n
zekJ+3;G<UZ0*rFHEn>*EjGzuBg6c#43aa`Ugm(6c277-a6R>^a9&T%|c8<xG^J8b?
zY5!SJd(X+U@VPVbbyR!DWD?YYj`tgnUAa~J6ZhbvPU>LInS`}plRCWN99(?pfadlQ
zk9YKYLZRHP7^jS?yxc7W9Zs=*s%So7yMl72Sz_mPhD@@-d_sx?DbE4$RxU-RD><fF
zRce-(u+#EtJftIq9?7ypcSb`vWoaU#y1%|7N>$0_?t9<gnVyZS!Bv6UV?)txoiT1X
zG=Ufl_1H89GEeP*iHcllFvoah{>b<RfHLu}(AG}VL~T%UR^+fOzBkuAC3el~d?3wB
zo@YX}BC|U4!vdy>@hk-0i(%1p+c+QWrhVXq@jx^7Q;&zjtYmwvEJcAkio-t~c^+=`
zukYG}Qn%O3zG@#;<?d6Fw>LA!#URhx_XNMQnSx=WQ0Z+^3YDuiub!4lOTh-IX6mtO
z-;!+SL3_r(_2Jl@L!jxhv8za+w?Q~jllbH;{9-pDp&OGXk?%l%hCIU(Lk*x>&iw$&
z;eGAQIJO0>BG25~2ab8bu|WH^4;%~YPzU=VaI8}YwOf0@s^lO628O`22>M9v)luKY
z{)Z4>z%-X_1I-s?Q*#d43#NIgE6PeL4&eroI^bx^q-5h);oZy?Q~s%C;^O_;Z98-m
zcc*YHdXMV81??%)4h>pfh}ZqU3t`d#asosT#Qo_VEDJjH4w8XZeMC6j5pZ+5*neTs
z%k}fH=~kt%Hg#LE#9Sfq@?--Ara^fIMH9seinAbK<{QxTY?N34y~g4!6Ii3<Ih_3_
zinmZ8aV%M<;sSh{wSRC7Xgw@gCa%D+Lc%$T<rzsxOnhLPT!X$02j&GicN413$inFn
z$jUBna+iB2q~{5Lnt_i=F96+UVbDX+Z5{?a0zKhpP9O*NV#}))6U{=Qn}xH3uyvtY
zPJaXn@X<*fV5*ZMGo2JT4blUqI;qbc;3w&}0^{b~c#!c-tVZ%l{)83AgL|^>Y=y>G
zqUg(aVMBQd#d|2;M`8Vq@xA1-I0YBwI!(WTer4Y&63%`{tMmAsPg*<z_!xLlt?{3L
zg5ikIz`l3vs!JN4E%**DfD3*>4IYLy1mJa#F3*X7MNLVpXjy5>XgL}T$J2OPmv{hx
zNpi^c_$FmyiUDuOL?yQ@F^#VeGciOaTfi+MKY;Pmv<UhI%jGQ?QP%k`Qs8K14$h9g
zHe@fR$mEA;sJ#}1B#{8}V-$FE{{h6+8{fd_GKyr5LT|i22uRyj_(~9buv2tTfoLv)
z5U&pg68IHixcd6eDG)Dj;(E*PLTNP&L|4fMB27(_;;TL?P;aK`!H5;p5lLYm6AxuI
z6jG1nW%!gBQSvH^YbajEtkp2r$%`O5P;Jb{B#D|K{%n6MF;SZGDucrU8&+}_H~Ay>
zNE9|Dn^pTpuh0Hd<U-ARY!)5qyioQPwkgu?`)`Jr_{J32ml#_L)4A`(@RCFI;`8zO
FzX2<2wP64N

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__pycache__/__init__.cpython-36.pyc b/keras/downstream_tasks/BraTS/__pycache__/__init__.cpython-36.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..db93739e01cbb8da81e0936a75db2a116c807d5e
GIT binary patch
literal 426
zcmYk2&q@O^5XQ6Hf6HQh0uOtVu7}1df)o)erJ_(TEhxRjxS6i0yGcp1l=dBb5ML=*
zPriZ&aautP%s0cAWPZb(w%c*%p!M`k2>HPHJ9VtCFzg|UATuHY5f;HLfM5}d8q`Gn
zEey79qo_}b2qz?MZfrb~1@sffq>_%Y?s6RuxkKlS_Gs@si3gQ?(Wal=X_X9tJ4~I0
z*cDgSaW&UQbU{>U9A6tQRWhwgZITJ(B`C+8#1ALO*a_Qmv|ap(1Co2+l)2Id($F_~
zwteQK49U4R>ooAeQQGh=#)Qro^U;bMB~@<yo|WaYfVnIj7~dXMt}^iOdpm361k*`(
zOG3~)F)@;M^7Tkd<*1ljy3s0Mfuw_s3n*nq#~^M8Y^((omfe5?D=l4C&xOnozf#s2
h;3ae1zFN8?(0}Xl(M736RlsG0Fxy0_hf%N}{s6yefaw4L

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__pycache__/__init__.cpython-37.pyc b/keras/downstream_tasks/BraTS/__pycache__/__init__.cpython-37.pyc
new file mode 100755
index 0000000000000000000000000000000000000000..163bff5a8205f63d53a5978034432e6f4dde1203
GIT binary patch
literal 424
zcmYjN!Ab)$5Z&Ew>$150hCPYvp|OG>MWmHdQK$!75PC3#&2&xOO-hobw142i5Am0B
z_2e&j5N9ib19>xfle{;~b&|v$M*P}+`o{dxT>c`&Vu;5aA#iWuai0gJzwp6d1-u0<
z9=-*B!?w$C?(tyeWu2XgC!&NwN~w^-QrcT@<1w?yoRdE3U!?J<w$Dlr(mN&7F))ki
zc*Xa{&{!syO7kA@I*a3L&4f(nb)|GVgQ5aynHBiq>=czymLYB9PaM#@cO6kkr6CJk
zhvm&P7v<<&D80>m=bvP4cR(puIi)VzFfD~Fj5{=<T9>dCr3LMhNo{KlkH6hTf)mVV
zy~YWR-aXx{YY$%!q>`5O<kFCxlEnrD8Rd*aC2}$aemkO5#i2Cx1|%3^2v-|vtOiz5
e%gl=*du{S>Q7*cy6t7FTiqOV%5W*nxyTK18jeej2

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__pycache__/load_utils.cpython-36.pyc b/keras/downstream_tasks/BraTS/__pycache__/load_utils.cpython-36.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..73ec922c0e852bf381e24b98705f23d8cebf7c8e
GIT binary patch
literal 3136
zcmaKuTW=dh6vuaV*Y?^?+)zS#p@=C68cQW^1xS$<g{GHORBeQsLLs!6>CQM=XT9sr
zjGM;Vyfl^QE025xJ_cW7UU}*}PdstXtat4cgsnNdvvWWH-<+Ax=jR*C7i&LPPdUz?
z&dkq)_v?_<4KUo<aX8^_Om>KUx;q~Cxc|!8@p*+;;aTBL9`O1rvQy;^ehR+S_#B^y
zXTaTUr*(RKyRjL?qC-bIidEwl)A0Uf`&#?jDs60x^j<1E^lqBaTY_nLEcdy6xvn%z
zda2|qf{$8_H!vM%D<t@Up9`rD=_Vv~70h8%JAINl$K;4Sa*}hz!M}Dnd|QIAFUb#1
z;(qUFFC)hUCgzTRYf$*zOBq*`Q8kj!qvtH9H@Cl|J(#gA?F^Y@gR-z2s^=a0a8J-7
z(|c5>RKt7G0`oC+m$#Hck7UxJ->`%;MPcD=6Z#VLAi}25t{gJLg$|gG(!{nMe|%fY
zR8lDzkCNSK#bTrm{Y15V;|{qAuoBM8)Nj8C#Sl9&O(_x>svD;9XppFuYvzi<Y}KI1
z{qD#By!ZD`dywch@2U1UO?D4N)ZPdg7lSBl-xvJrjqd%Fi&%B<h(xGJwTGjpaTIoW
zdXOj$GZ=I=Q~RoYL$Zh4ZFEA{>b){NH1jrFj0nIvssYBSx}-^}<P4FREu}??eMnZ?
zd+?GueW38X!`*#XUPS(QW!KA`E=jJGWmPEa<Ym0J>)X;M$R9urk^_)AAbWlMmv!+2
z>mVz`#7Q*m&0@eoFRQFVk(tJ-hm=V{!!!XGXpv~!6ANXk6y;H`C&2BRV$08z&?@I3
zCy4iQZX`SSHxVcy?a6d-5{p9Zyq|(6q)#D7Q=*=Z^pvV%IfE3Y6p5V1H|W(j9vI_B
z+<0tP$Qph^Pw&*FP$EQf#vgv0>?fcqtkR-Gqol;oQs<e9+G9guYLglgyJ!*P@}6ZW
zH@G=v1<W}}Y7UH3Yl7ZQvfws}E!hllKKR2PO3C|>(IC1e$F2eiUlPa>o4aUpUf=Im
zaHp%Qx{A-2<i!`->(}u8mh<G(BiQ4aEAM7rQq8=6aO~_?<r>uR`}NGpykiJV&(<CR
zR2T=?1MrP?@n)3RP=LE1*Udmw34TfCA&Rb9l;Cb;bYC1EKxD!?k-n@b?zP4VwTpJS
z=+kZ>LMXvxxCd=#8%%o4s~6qRR<>l|I21y~Y|D@-(NzMF)X{SYt=oC`HppNZjF*>1
z`Y>-d3sOIg62VVIGrRhk<zl2NW;B^}x#%l2>cNCY3BN)iJP5j#CSt`7v(;*tMx-K$
z4=f3V@gPo^=7v&2B4{?i88=nN$53i2kpeH7ckry(O7$l8nb)bsu-UMz5~l}38XxBj
z!LMF=)zl{QGtHCUFg`BkEh^1o4|MKg3B<=j)n%YgEr4+v0I54i0&jsVVsN?y-$FcZ
z@K=R|RNsW8eggA<q`t7sO{iRX>>asB-jV;}qs#|NFC0~}N=6`Ttpb^qel>HmiY0UP
zk@IZ1r1Q)yoxq-z2SMOer30b&0Lc^V$u!j+`T*<<zEhL{=#f-_N_+@R$#k^4H;WVY
zoKt9FgP4f=+d-#&ln53mZI0sj1VqcdNGg4)mA9Opcta7|pk%kqgd96OoOZ|#@|2{L
zR&Z)swlFf=5R6kQ=&H$g!ToX(&3kB;z!?94#ryIs<}ZS2RgI7SFg`Z5-;EF4C{w{D
zDM_&=o`BP+Wlm4|z*hV#C{|4{P94zjmPmsHWQoYj@TEMpJjh@O!>3vWqn+2YA<X;5
z>DfEft3X5edJUoK*gYcoZ7PGX1s4}L!y8j&{D<|(9XLU9=NHa}Y<}TDY~iF)`H@xb
zgA*8(UpsW8lm>~JQjzOkXt;sFOh~wdNqQKG*xo#PC&p%=vh^EAKIB4`dX~f4PD{7o
zv4bu_t*j66mezM)LwrZpTV$){S><LlBZlx6ksm;l8C8O{m<^tCw*Dh_1<4topG1b0
zwKxq~tk&TruTzeX`xa%{hNLcl*@cmxoH-&HflCEAUHKXL)qUpUTnt$O(|~{_wL)g$
z-sG-aHRSDs?eE4K4jrb0;re6j8HcGl<M;n#LPfn+^(|nHH(<kj?Km;;1FqPRfe8wI
z?eYs(*b^0N+O;6Fc%q(z6II&wWV2N_wJzMr!frR;4b`E&drF+1y=2*Q*G4o;uWdMk
hzugEpjtSP_`Y?*cItDx|obLuCaD(|^p>Z}?{0CgPRA~SJ

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__pycache__/load_utils.cpython-37.pyc b/keras/downstream_tasks/BraTS/__pycache__/load_utils.cpython-37.pyc
new file mode 100755
index 0000000000000000000000000000000000000000..c0f368793f25766f6f9c490447dc4f468185cd02
GIT binary patch
literal 3134
zcmaJ@&2QT_6c;7gmfgh7x~^aAFm}V%8tCE{*nq+avZfy?R<yy;bnBM2HCT~Ol*p1x
z()lptOH*LoamU@#<Nl2O8@%q+^LFZK?@^KLbi-_j5<eav`F=nC9&gOfHXQgherZ0f
z9&?;Ou~Pgz__z*_x&Z}u)*Mc_8<RC+-|m{nJ?_7B)_h*!Rd`o;lLx&1lB`vEgCB#I
z8lT~_@D8}U>a>oJZa0>rSaj%6N3m+$Vj8}`YF}+%y+#{LL%os84!xTu^p;>6UY9nx
z{kX0)OM0o~^MVgsjW@6yXC)-~f}aad6`q^$s4GzHHMMg<GUqiJlSfW+hB)}wE{C>L
z&OUiTesmJ|2S<Au*(b0tcl29>!tY+nxT1`zq1=wPSxj%PeouR_V%yspFv<F5XE#*a
z9r|!X&;ipMRHszKcVU6`7^cfDrO-o}bm+G%;Y?B3I9rCf1l@_y6zocu5pJ~4bd)C6
zcJ%3ODN{+MU_46JCj$#l9r~GS`Nkb^6W}0Rm#N?04aEQ_F-<8FaMcadc-T)=%QZ8F
zGdnaWYQH-&fatw_*zPB~J)iVcdz2>YJ0fZ?g^Y`S6t?dR{>@VNe#%9xx_3k(RHWKG
z-AR-N-~Fy;YD=|mNcM2Gjoa^9q~`~FX4X~<UqCfSS>{z;(j--Kf=H~Epdz?FJQmb@
z@R2#2z`wH&ceh-59+}50>t5z`NpiXDt3qEV@8h*~-}W{E_y9(b9Qw=w!0V&GZEzph
z&{zNt!$Z^FGyymuWieF<FVi@5k1{D}m?p4yEfQ^KVxdfxqCD#L1O!}DwERK|t#StB
z+~K{PF_P{4n+pgY?a8!%ln@2Z`8)-akar3hG~v>-p`P%m*iJu%B}F3V;Tw$V8xIQO
zM%;L8UC0_XVWijUQYaB3XGR}?muw|~D(updhDJ$AJj*xFRMZ9=2va*8A#sWpF)r^}
z7Ue}98f68FGw`SxD4bdo@NSYhw@GZza)|4}AI^YdE##Z<p#gMF_FV-Kz93K|wszju
zyiNb0f@fS^(bdeJ>fJB3cTmH&Th5cu$8fqcSKiIMq?&mL!E0x$Di<``)iWpaUV|h(
zUw8zhLIq$CAT~C{%TZ!Q0M9+{n*pd2;*!ce1YNTz!E?yyme|_?O~NsezNjdkvc?g#
z3%eZj$uyu1N-!C2fbF!w;f(q4V*2U9mKo@Wf=EnThD?dB5<p2EZG)(;=F?kw!9MVp
z_eFXyx0@!?W*Q}eAJH+p`>E}sMinbMTy(kV%QWi2f`$pdOhFd}T}cx$Z{4i48m1Ac
z2=sv^p)elkglR4*B_tBfN}F+0WqcG-Q;8Hr$-IYIVkOnfIA=bl7Q<n~zDk_#2x)v=
zGss@OjH;;}uFo`&M#K2HnRi%ePWAxjF7|*j7N}kV)~PutoCc88ogslYM^2(RU4XU_
zGY$SQ+mspSDOCQCsk^|r1CS!i%K69M*d2RgfA^Ej2bP{2SF%b*K(?*{Gb;zx%*`s6
znb#gU&o7niJTc8q;GTsCiNL8!`$BI3C691Vrm61G2T)GYcS0o~^iV3GO1uZ0lId`L
zW13DlbIw9bHqb=G-#VSlQBts=((*8lkC5n6FOo`MXyulZTsIJ*6(xIQ4w+-!L!LwK
zAfJ--&<gUU<rXTlm0(;_!LFKoAHpwBV(|eMr=T$Y4vV+sX{?`zqE$6M#>4n%YTJzu
zyiultTT+tZNX&f`)iTE?{6H)IHFT>c6iywe;hiE45|C3wUWAr1Yk5#X3B$L#28DKB
zO-q>fv(vM;r<Z{S`FaJU*muVyzei;tTl-|}W_VYsjQ+3@xdRy_4}K9`sODD<q%C9`
zm8Y!o92}uR+1jB?B{ayG2`h5k3k;V~%!GvNm!x}<i0z%Dcf>aXlx^Hl`H&Z?#Itl~
zCoRK*X$RFEv9dALkd6=BSD^36^%hxac^0`T%!nbpMdU|dGKEU85VQU>&K7@y_P^k9
zMrRL|VSXV_Ll&z=_{hhU{_)%*EUWOSb5N{<=O-t|BqIlKv4tGsXXID+xsPixWFCqJ
z2$s|eISV%?cm9eY?<TgljRkZarv1U<W1Km^h>kw|j|COuTGe+5YrH-i<a@`3K^$<$
zhV)HP;A^*Egu-T29BKE0oW+cK1~RI&_GGzLH??k;r(w67pN8td-Z~{N&t9@@-nEKm
m*=r4_=x+}K`Z2)*Tpxz9SVXb2!1-=K0ymfq<{GDilm7svU{&e>

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__pycache__/modalities.cpython-36.pyc b/keras/downstream_tasks/BraTS/__pycache__/modalities.cpython-36.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..87fea629a3e4587a584d6c8fa276f529aa505bf9
GIT binary patch
literal 2280
zcmaJ>OK%%D5GHq5)@m)svh#FN6g)JD6&Mzrwm@M7ZPGXiS~R}cK!R<HEw!X1I{Q#a
zDvk{K<ot`CdTh`AHGA#Jr}o@aXSjYSM$r{!IO22Wn{Vc`rKM>7<L1vx5g~t)xexx6
zM<C{RP=drnP~l~CA4fm)azFMd5qIK1tjXXui5oJA7oHQ*6ybX!Lg}CQaZ@%ALXZ|n
z1hNRy9ya177(;=xErIiqz?DVO2Hh4*su5oUD-;xTOQ0QzWzdVFqk?!@tccb3B<_go
z;s%T>;-<I-<Eps5N4g&!{Te+}ncQZ1DR`!=k|x^W7AC&vecs#pl0}avc2w$Z_FY-9
z9my>W>j%OakBsHTpwwbhib*$$p36dNl`@5sIkyV-@_sq7%#I`zYA}#m7M7`;4<)nH
zF+9fKa+UFZCgGIZ_KoKIdrWZ4nUU6PMyCKN>C%ec2NgUmCi&^#Fmw6~ssL09a`92H
z9)XxoK}ix*$c86q><bUj_v3~D<V7QHiiJ27O~4?m!WVV$Q~nB$M+`oEM(R2QEyr3K
za9kC`E0MSuSUH%3ujisO>>@CC-+u<j*7vtI*!}~MttU@6*t3i)y}@`P*q$8b@S<~|
zyXmf&pJK`s_W)LzjtZ6XEStiqGhF+Cx3c#POUvS|EEHVh&fAiW_*=l)G7j#sT;_eL
z(Rn*khDnH+^<~N@2KN|dY^kL<Ps@2i+*NqKC?Tnu4S+rDU}D^*z?8{wgfARIrY~Ho
z{XfOjoO-ByP<jEa2B_U`s|u5(;JHkaDoPUI;v_@6og{B2JUd%yCW$ChnD*=z$b%}d
zTdAxX1B9*ejU4_)^i8}P)jx4BFKkZ?Oz)^HhKEx19;aN$T&2AiQhfV3fvn5SB*<E$
zOm95tXDWp!4hv(o<auJbd2M=*kiE<L*c?xF6CPLtF>O#`Goa@`x1u{Rt5;C1qPmXi
z2C5KM3l(;Z6cND>@jxa&0Wl9iz1y(lfS!;Y@)P^fJEq4#;hA@fSnt3;2xjDjzFyGL
zjP8*)(Muvcps|1Shs({5v{L5^Vsc!)tToIuuk$s~WnOaxp^e<R?J?IJX0bLC%<4A7
z&cJX7E6)-==5|!?*3wRNvCa0Ovat&A_WCUah6VCXG68&I;@lsx!FJ06HX?5hm67hE
zBmb`1-0e21Yi9^g9T7~`P*&!q@=8+$_-qySITRsy)Ai%%(#<MV`7l8jssL9n8K7?g
zl2v;sEiwwb+w^M$7?VJntMmp9ss04)i#%WskdZDA_rb6Pu|B4X9DDEX%qZlebL`Lj
znP=(DKcNrFo7I<OhWOK?zg$31fI1eyhXUhc28|FPF9fy@&V~vK@(Nss3d*l=M>&H)
zp<bbOh0-#G0-RppYCcF)z0oGHZ=3DRZ$4Y8lVLtg){aWCDRa0MoExK4bNqk?;i?(Y
zc8+7$cI)mI*C;qN9e~<RbiJyXDPzG02V*y=7U%qe!UX=9ii#>g>uO>;^NC5opYH*1
zgLOe#Arw?ZJ5*yAPqAm<ha-wh4_02Co*7*un1J1Gy}#>e28(fcp7pCQuYB+_`t}3t
zH|`m#?}EMC^)-^AR!9lB8yi;lx?YB%>bS13nU!256RR>HDK=2;<Kkk?PBY>_%2uvb
z;>@@OEvh#EzfHu^Ww+6{-E-%mB*>*y8V9&T$N4)Kp=*GS`Qbx21&#D8Y&d2eRN#eP
Z+YkH@q|<5Bw!c8@Ulg8=ez+7a{|m&5X7T_4

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__pycache__/modalities.cpython-37.pyc b/keras/downstream_tasks/BraTS/__pycache__/modalities.cpython-37.pyc
new file mode 100755
index 0000000000000000000000000000000000000000..6bdb314b484c8954ae60296af65579347f459832
GIT binary patch
literal 2263
zcmaJ>OK%%D5GHq5)@m)svh!+AWq}5X0z-m>7ATCM&BIC1qVdHB5^Ns}dPzxi_Mwne
z92xQ{x%4;mk{sJ}f6ZQd@~J)d)ETa2D@M^3W=L^{<na4u=HbdpMBs~lx%4y6{=`4?
z4=wjW%<rHCiHV@X%jh1Ce&*$V>{B9wI1mjPTqiN;c<Ct-OQQLXh^F-4`f*b>4?>U@
zNCdJB(jGSA6&OR|EW+7@vkGSyZPkb`IS&fDCD1z(xUwu(RS>U=j#zs~;*MAsmtkBJ
zSHx8q*TuD6(!GB4A$p=RxyABQ@Jv}HO|;D|EPUDjqQChSiylnusMK5RyRu;0l3N&V
z9|$+OZ!9kcr4~IYCfz7{DhsJq$`mf<+$!+p`{l$kJCaPO!9Z$RSf+A5l*~@Ya2bEi
zRmS%-3A>!zL(TVgnc$W)BdzI0Cjcqw(u&>z6+A8`dDlPr8`g9H>f~2vJ;8Yja`sV}
z-3KwBgOVhsK#M16><bTQ@Z$#1u_PLCQ!K@yXaX2v6+Wv`nDQ5}J!0_TeNxwN(Q>S%
zffuM^c;QLzF{~Uc;MjN1H0<n!?!5neCA+=1xxx1Cf^0r|yuqGiT<HzQ3&D2fFozpm
z0NtKDVsVKnQ``c4WjZQU%Cl?=yG{Y#2jG>xWmsAkuVta&7`NY+Y{Xv!;FfU+kL5Do
zml}h&BW0L`7qfkt@`*to!;CGp6mx#&%($a)e^COvnhhY0*uliOLm_1*!x7$a2$Y|N
zRL6gU)SP&zd{BA`XAMw0-BuMQNx^fOBvq6okd%`Q=j|kUHR0K*rI{q6Okvrxn;>_q
zz;33pY77vz$~SWO8_`$sXjK2~_4C5^d&R)?kIG_rC{_PK%7x5T+J7d+w+|AaU1lc1
z{58t-MR`~lt0m79%gsyEcRATVFOlAOs+(~14G_}?6*dDp|2d29z^YzDwT|jCsw=2M
zR4r84G*ZL@KSTmCcm!hZf_k%I$$R>NY?GhZkKQpohUA@j*NF8F{P)3(e4sCvbTp&8
z<W=;X2oDn2Kl;P5vMsIDxq`>IEIltb<e1k?4Ro2;*@2)&Zr|3JYYwYeo(b}~#jrUr
z^kC&F#ba(qwYQdbqKhrI2gQx~kEhpnDVSJDyGbS>lbD#tBR1GhS%4#E%%L*U9dzX1
zG`*c}qq=m8@YJP%sT#`4+*Dp^ssOL8!hH_q2hnu>Dmo9d3RON#FoY^V>pA!O8X#G<
zhtgs$VS}4~g8(B5q`6M7(2(j+VSdH~_K`Cl?!X^QX5=kBrivVUZ$6n(;G=Ww&-|HZ
z>CAsi?~zyQ&&dq&r$>Le2R(w+u>d}l79TU{g#dXWuxW5MR8Wc+;5t-Lc!k@_89Wp!
z6{=P!EmJ7H=^3u(BbsVQn}FXI+g@}&wbW#okIC9rDfVR!$3k#p3~C`ipf$KUMzmev
z*tnhDo#I*qhjs%{yM?Y-H8W)_#Nc4;2G#OHTu_pbKc=Fh3UGFjn9d?G3B>a~0B*1@
zNGpVbifD)GoA58iZh;?;D6UMf@@jf!^aeo!cDl8H*VCVYu?pv`U%Ywkqnk0dAHd(Z
zYpA{j^PTQxy^3daT=n;|l8a<wRR+n3EmHevT&}awj5s7;E7vM<)3^mqsGk0RJBXw6
zuA;BI>*gURm@}y~4p@hRi)-N}uEn_w5AVS)Xq8`MV==cu1zza2{lE`FI-NFc`%AR`
MMd9h_hb!Ugzu4_$y8r+H

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__pycache__/structure.cpython-36.pyc b/keras/downstream_tasks/BraTS/__pycache__/structure.cpython-36.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..b8ebdd0f17d822f0738be549dfa033fed7203132
GIT binary patch
literal 1181
zcmZuw%Wf1o6!ojRE0s<Yo*EE~ENN+!5&|TI5K4HY0YQWmB!=1;r|j-jr`i>4SE8WK
zDs0*F3w*}x=L@`@4M=>!tmfJsk}PoP9>1=ykMBKoXK5+Bb+h~7?*yTL(YeN8yar|i
zNK_z+C8=?Np{F&O(t_f!#%eZAiUgw}l8NkmMzW*mF)cc>E7Q-Y=t{DM1`D5FWE)kj
z9;{er+S0W~Wlx2J`Mvype*6APw%)p(#ynVg+31z0N;v3lO=KLbSts<UF>+POc98u5
zLTGb<J$t6xDfCxHm6m)2;d$9;Cn{a(aT&aRH4K9_Fnbd~A$SBTh{Oezq+pU3iDW=H
z0iqq>2VP>U-L}fTJ={|!oc$4jgb@YU9CUrkxfWB!xz9MCHnN4=x$klQu@&{n4&51#
zJ*@!}XMmQ^_C;Mu;i^V|L*@d6ityk2e5ze8M>hY|=<$K7^7T?kHLc40wURH^`Rhii
z+VY{&%2qbtYq#sF<gz)?kWVG1+zGpD^T$TK-O5i>yt;R2LLK{HHU&sAi(gzV!+S!5
z(xb~@Pr&R?fEjjZf_I5|b9l*-SuDMzU+58ehx8u|Il7yfyBLK}q9gJiY4R7E5s7ve
z%;Omp+_6bA>A*>L46_)o3-O#wXDGxzCP(zdhsxyCX90Y^{??~+>XU)b_Y+<quE>j>
z<Mq!eFLuI<MP7c!&hhGocoIRy(@nDkZ{7eQ^-EzDw@TZ}Rr|`Pv1%YDPoEEmp1v9m
zO~~b7F(xpcGeHpkVi5Oc<2IUB%V)+k#*@Z+wkO<<XOpJVW-<8P7%RuOjc}IRC^0T8
zqe|D9L(>C?dHAHbIQIdm03#Qi{8E?zImaEyvRE92t9WEsEW|Fj70dJWGohWy%q)i+
zt^-^Jvws30oDqUA;XclA5J#V6xOaxX_DI-^CkLtTau8n0xw!`CJyY-#njj^=9ObuK
pH$w8(Rke+|nWrk;dX7nyexT#ihx4E3Q3qx=17L7lkM!tr_kT#YCP4rI

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/__pycache__/structure.cpython-37.pyc b/keras/downstream_tasks/BraTS/__pycache__/structure.cpython-37.pyc
new file mode 100755
index 0000000000000000000000000000000000000000..5a979696bc603c1e5c4e3878d7bf6956f6467391
GIT binary patch
literal 1179
zcmZuxO>Y!881~ofP9~crAV7dP<k*#}jF6~=P*o)XvZaEkQjprtp_UnYH<QfTsqFy;
zZBB6Ez?~x;`!l%n3w-5Lr2c}Qc<s&Cp&t45*W=fZ-}must*jIXO7V91=cf#zFL7{M
z7<4wEx@aV-ki?R-xWdrVmdt2Hahzi<n`Kpo(HO~0_TC`bQ}i{hda^I`H>m1MvWrGb
zuO1iMO{?y&Id8k#cUBb-g@^GE<-PLGy|rSq^LxhLU;D-AwTDW0XujK*sk7m{&=X_j
zx{}?f_zHy3&IkwgNOv=6uTB~*`2^ha+GsBt-RNl@QKtn%X9KFc4Mrij1geO{6_uo7
zl2(~yKsW=Uy)Xn`Vz+zllz(<~sBGN(H5n3n6wJ=3A9BvMm?_Rf!THR{4o>G`!1-UD
zXirw?-gFvh3nudxXocd1Xd5YfWAxw1UIJIi{I^@qv@h57#Fej%p1xE~xmgRTW=&l_
zRr2vBe`=&^9Um*LT;ob<UTTP>5;N|FJ8<Qe70-6dv*4~D9@&_|Ayk)x$uUb`nyuqa
zVu7TixcUI9`xnd{d$f-ai2e2GiYN1wbV=XQWAYo)HyHBtps;r_il0Qs<PW6D?`TdW
zI#{w>b4ayk``L#c>|`Hdl>GI<pZED3Mc=Q<F+IUhnVn&l0Q3HTF}*WP0hoVIc!8`E
zFLr^~=QCdHgcnP^!kk^;)sOxpf?Vf2b_MRd4H6pG!YS^Qc8zadsF0_8fs6wEc{~pE
z$#`sIEJw>JfN7tNQV5r$tapsxHl3D_tTi?e;{rPrelM_n(`dUKakr+*^XFE0$6XQ^
zmyK1mH}=R50I+bMRhJhS5D75y5foP90LXdnL6Ft*Bp$^R!)hrt5mv1(=FcT|E-<?q
zPq+!@8dUc^7=#N#@D)771&-nvk^&FT?dckcYiZ{w4}H$1sX4dTVSiu>o}Z0U3ad$e
r>#Y%zcfM&|ip?Ta@ze`UlISCykpH-NHb3=X<l>)*!D$0BpsW3F44WlA

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/load_utils.py b/keras/downstream_tasks/BraTS/load_utils.py
new file mode 100755
index 0000000..bbc155f
--- /dev/null
+++ b/keras/downstream_tasks/BraTS/load_utils.py
@@ -0,0 +1,93 @@
+#!/usr/bin/env python
+"""
+File: utils
+Date: 5/1/18 
+Author: Jon Deaton (jdeaton@stanford.edu)
+"""
+
+import os
+import pandas as pd
+
+def load_survival(survival_csv):
+    """
+    Loads a survival CSV file
+    :param survival_csv: The path to the CSV file to load
+    :return: Pandas DataFrame with the survival information
+    """
+    try:
+        survival = pd.read_csv(survival_csv)
+    except:
+        raise Exception("Error reading survival CSV file: %s" % survival_csv)
+    return rename_columns(survival)
+
+
+def rename_columns(df):
+    """
+    Rename the columns of a survival data CSV so that they are consistent
+    across different data-sets
+    :param df: The raw Pandas DataFrame read from the survival CSV file
+    :return: The same DataFrame but with the columns modified
+    """
+    if df.shape[1] == 3:
+        df.columns = ['id', 'age', 'survival']
+    elif df.shape[1] == 4:
+        df.columns = ['id', 'age', 'survival', 'resection']
+    else:
+        raise Exception("Unknown columns in survival: %s" % df.columns)
+    return df
+
+
+def find_file_containing(directory, keyword, case_sensitive=False):
+    """
+    Finds a file in a directory containing a keyword in it's name
+
+    :param directory: The directory to search in
+    :param keyword: The keyword to search in the name for
+    :param case_sensitive: Search with case sensitivity
+    :return: The joined path to the file containing the keyword in
+    it's name, if found, else None.
+    """
+    assert isinstance(directory, str)
+    assert isinstance(keyword, str)
+
+    if not os.path.isdir(directory):
+        raise FileNotFoundError(directory)
+
+    # Iterate through files
+    for file in os.listdir(directory):
+        if keyword in (file if case_sensitive else file.lower()):
+            return os.path.join(directory, file)
+    return None
+
+
+def find_file_named(root, name):
+    """
+    Find a file named something
+
+    :param root: Root directory to search recursively through
+    :param name: The name of the file to search for
+    :return: Full path to the (first!) file with the specified name found,
+    or None if no file was found of that name.
+    """
+    assert isinstance(root, str)
+    assert isinstance(name, str)
+
+    # Search the directory recursively
+    for path, dirs, files in os.walk(root):
+        for file in files:
+            if file == name:
+                return os.path.join(path, file)
+    return None
+
+
+def listdir(directory):
+    """
+    Gets the full paths to the contents of a directory
+
+    :param directory: A path to some directory
+    :return: An iterator yielding full paths to all files in the specified directory
+    """
+    assert isinstance(directory, str)
+    m = map(lambda d: os.path.join(directory, d), os.listdir(directory))
+    contents = [f for f in m if not f.startswith('.')]
+    return contents
diff --git a/keras/downstream_tasks/BraTS/load_utils.pyc b/keras/downstream_tasks/BraTS/load_utils.pyc
new file mode 100755
index 0000000000000000000000000000000000000000..c86f754d61150296d5d96a9be1440f14f72e1bab
GIT binary patch
literal 3394
zcma)<ZEqVz5XWbIc{C|4P16(=(JiRLMQy6SKt&dP2u%YjD5}ndqLyH7ee2|$^PPLU
zPGTu}0j+><fZ*HkeRv1&;XiXeKNMAM)LZZE&Cbrw{AP9={C%Q&|F^%kTQvNu;P(z5
z7ov%X9-~zhRVY#P7@eYDp~nG50lk303`H~2nI$_%(JZ}y<UB=lGPpp|ymS^>Nu##F
zy6>T>ZpMkN>%NZ@SKTlk{ZFo4zjpmoU0v_{-7K%``&p_ttnv7%bt389ao(iuERWV~
z)W2Mf|Ha={OF<tS9^ko)$K60PSSC-@QFKJ~T+y+jN9iglrF@0Afzh)V{z*})=sO?K
zkz%n%jTO1y(Ns15zRpbKw9&4g@5lQl(RUl)>NZT5ul1hEO?ULM*>d}J{czXnp7Fcd
zXWFA*&fxb1>WZ1U_5D1p>jx%{jMMOd*@P~u4`QB*d7~v`-f`FXI7?-&`w-UM%kwPP
zxiwLo?u=#2#p?Q!tIa?TyCv#Ho*mE9Y@=Uf1&1x$W1aqO`IKVuW-Ckj-PDN_{1V1X
zBV?KcZ|H~`K9V$U8NJVQ^RRJ^x7U=AuJs1~1jc2gRPq)ETonz?1!`FZ>Wq@uas1d;
ziCqUB1P4Ee(z}3WuR?i^X#;1#YX_ksY9em8CgtWtt}&JacRMqsC|E$$7i5Ae0}nNg
z8oR>%gGO8%T6TlDf9MLGwI{<LAx;ue$H6t8MF-mCR=2X$#m?K*izd^`Gv{;^x7#+y
zpyruZo%ODWe?d;vE_lh!!T(9%aOrlQb*FJCLtN-7Ib!M@+dd}gY2S}&D!0?kU{Y)g
z3S;(s9H0?Q;s|*_WOi&g%O8Xvc2I7eZ80nE0^Yt!_tNYj#f}9Q9j7Dy1Uu2k3f!*g
zSwD~7P&8y1YrLqe7qwqcQOMfP;c<*3%`dAJpmVOWtXlkqO&p=~2VRi#h^t33SIDjK
zI!JLIL|Y7gTn+}*nW4@s%OmsMSLEl0eXa^bhhGx>(U~6(ZfxJ6W2qBIAhJhC0i}!F
zb{6P4(cT>8Ph<j=VjN2bY((SP6M6)chm|G7?j>@YaVnLCiwV2XfR!9x&hi1X<V~D%
zW*fa{2M4HlEED^WoMu9+QxKK&3YNxdP;i_zd21JQCnpRw7UHG)Nnrs_G69uma%Rgo
z+jJJB`*<HEyHTi@n#JF+UhysVgJRw!pPejDZ8TLJW%m=?<-%85G&Fj&=_@*J>vq;p
zqbu4bSZpgx?V2pJRpZ*?xwgbEPWhB*S%KO4TngN}b2ev$rEm&<ne&Ve*J>}kJGjoj
zgCRbfwlcrTYZdYgaf0+_36@Q=1E}Nayea9hHATtglo>@q_#bXbESdJ9Ol2>;J{9~K
z=xqa=Cd;E%myqyOcM1(vSJX=7v^p7_Rqv}+)#7}c!^0-u#p8ZN^X4gX_+SWhks=%0
zx9R(Ujw_r8$1`+zm5yd;WBU>vBa84)Nf9n4%~A*HRN-;Sf(P{IS$#4SPETe6I2RNc
zx=6dMYyB?ppW-~vGGEsr+KE&dV~gbJ=MGpV1Mr(?{hi%ObXjvjynv0e&aBCzV;v*h
zOKdm$Niqd&tsUpiU%Xt*93R#_+mgB}={clSmd7d0WH7sFHk^e6UpVH&MNSbmsU&#;
zAqx5I4EbOVPjbV-6;cjNvKKO<;aP50(bPD=@{t`R9abk&@&**0K+BtT;d!2e=QXD{
zuRDf~HAc5F<k%=$1ZTkobwVwv^Tion7UF<qo}vL|zoLDq5C`-N)XGKjXR#Xf7h<Tt
zfCP869jVkC+vk}w&;y2W1>o|0lV5+R(6gITg##2+S?f=%C64|AXKNADGG=%!u3(%h
zID=hrn2%C(imuUUU9XQK&LECqD{v~&Sm%0dbKFmJJ&0{07qRx#+6M55)46yvZf=Ch
zXgN_jx(4x<_&z0<D!35$*G`2!#2LsJXe147$<76eF$=}9%AX_YhJ0vBoL_lCTY$u8
ziRnI#%&jNrJ3JgQqO}?qyq74HdfGL;Vqq>uQgBghbMH74r25IaqNFQrTdtmE1jL}R
zeXlYtWbF++j%}p*6?IY7RE_Jq)YE1&%3954kr&K=Pp;AYpB4)FU9JrR{ieZD5x&P`
mA8^B(3oFoh69?hO)KBa!)++GNRhHCJW%0z~sioD$GyefJ&@L<h

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/modalities.py b/keras/downstream_tasks/BraTS/modalities.py
new file mode 100755
index 0000000..57b1ace
--- /dev/null
+++ b/keras/downstream_tasks/BraTS/modalities.py
@@ -0,0 +1,92 @@
+#!/usr/bin/env python
+"""
+File: modalities
+Date: 5/4/18 
+Author: Jon Deaton (jdeaton@stanford.edu)
+
+Generic information about the different image types
+available in the BraTS data sets.
+"""
+
+from BraTS.load_utils import *
+
+from enum import Enum
+
+# Each of the "images" is a 3D volume of this shape
+image_shape = (240, 240, 155)
+
+# Here, "MRI" refers to all four modalities taken during the scan
+mri_shape = (4,) + image_shape
+
+# The segmentation map is just an image but with pixels indicating which
+seg_shape = image_shape
+
+
+class Modality(Enum):
+    """
+    Enumeration representing the different types of modalities/images available
+    in the BraTS data set (T1, T2, T1CE, Flair, and Segmentation).
+    Segmentation isn't technically an image but it's convenient
+    to have it as a member of this enum because its stored in the data set
+    as another file just as though it were an image.
+    """
+    t1 = 1
+    t2 = 2
+    t1ce = 3
+    flair = 4
+    seg = 5
+
+
+# Iterable, ordered collection of image types
+modalities = [Modality.t1, Modality.t2, Modality.t1ce,
+              Modality.flair, Modality.seg]
+
+# Map from image type to name
+modality_names = {Modality.t1: "t1",
+                  Modality.t2: "t2",
+                  Modality.t1ce: "t1ce",
+                  Modality.flair: "flair",
+                  Modality.seg: "seg"}
+
+"""
+The MRI is a 4D Numpy array. The first dimension
+indices through each of the four image types. This map
+codifies which index in that first dimension is dedicated
+to which image type (for consistency)
+"""
+modality_indices = {Modality.t1: 0,
+                    Modality.t2: 1,
+                    Modality.t1ce: 2,
+                    Modality.flair: 3}
+
+
+def get_modality(image_file):
+    """
+    Determines the image type of a file from it's name
+
+    :param image_file: File name or file path
+    :return: The type of image if it could be determined, None otherwise
+    """
+    for img_type, name in modality_names.items():
+        if "%s." % name in os.path.basename(image_file):
+            return img_type
+    return None
+
+
+def get_modality_map(patient_dir):
+    """
+    Creates a map for finding a given type of image within
+    a patien's directory of images
+
+    :param patient_dir: Directory of patient images
+    :return: Dictionary mapping image type to file path for the image
+    of that type
+    """
+    files = listdir(patient_dir)
+    d = {}
+    for file in files:
+        d[get_modality(file)] = file
+    return d
+
+def get_modality_file(patient_dir, modality):
+    return get_modality_map(patient_dir)[modality]
diff --git a/keras/downstream_tasks/BraTS/modalities.pyc b/keras/downstream_tasks/BraTS/modalities.pyc
new file mode 100755
index 0000000000000000000000000000000000000000..c9e442aacea85770d0f03a2dd5c146224cbb9a79
GIT binary patch
literal 2530
zcma)7UvC>l5TCOXC%MLLnwFHH3hfK3i=srSARw!PwsDJ8K_2W#1w&<RylZ>I{c&&C
zZ7row@Ev&IiSNM2LIMf#48NJP<Fujz+dDVAH#0jkznO9M&wBj$r{A9TY4%yh^B$J}
z3&aq0K_fC1N+LRDu1ZOT(kgYU6qzmRE|IxGc8P9um-*4Hky#;Ir2%AD=|`d;h`#CK
zXoXH!g{}#Wg<cZ6PQzvD*2yiCDc`Qrfhi@{z?D)lxb>OVfvL|l54xAh!HLVVXT2-J
zvEGJotanwoOLWk^LS~cQ>TZy^Cd^eb*M-?6^A2?y?{fIRfW(hnVw)<>jZR!}*2gU!
zaPaZoM|=C9s`&mSjPjzX9_N{ASsn0boEl;7`Jl5wUYK2LCb#4G3!B-(^_AnpR0juH
zeUeXt3L~qG8w_k=v!Gn6hgOB@7?<hi+9moVvCtB+2ZcWFD5HZ`-Uh!LyT9>iL~u1Q
z`LJY{z&^|-srv(r`<V$Jg;kKR%2=l7c(dLEEWZO{kru!PT4B@yF@R@;0XLv2(FIZ~
z)b2EDto1eYV}%c2Xp1ti!j22;5su4-Z^S2&seEuDse2N$SLfl1y?+f^HIDap)bSmx
z{lkYl>QSOyv7>ZmRL2fe+$av*-W3xUkCgM-EhO9aN15yEB$+~MmhBUu;KD7h`g!);
zW)5aVKjdnppCkK0X}G6So1WN$oev}Dl|{tr#P;>Xvy4|h<b^eJu;ws{Db~+&KwYQ-
zYD%3>yck9OOok)A;RWzNcd7K>F*dHkq{@UrM28SH7)gP%*UNNjd%Y0jq}M~GP7>a(
z$kyb2@N6LLmybI^Dq+8G0~;D}{sJ5KcG$p!7Q|n}Rw{09(Ez*SX`AhBWBGNE+Da{&
zf7@IUZN9qA4z|~ruwxF3-iW5p!ST)P&>@z;5Aw1}f#@{iq0xG}L*G^CRYb3(8qX@U
zg(yy|bh<=mm@5%|U!$T<XAyOt)#(XpwbPJbeuXK?d&>q}q%N~w>TuCrjG`{F7!-M0
z;?KE^MXx#5g~lm&V~-JQDxL+3B~(5Gaje6rlrC(T6j@UpqnEkD*?M`G0~1hKlf<A_
zl$rZucGOXxL6B?Wh4WSndG`JTzk4Lj6)s~p%l%Y<_JW!VHuZvM?gdYFM9SerqwC<J
zoU(mMhZM&m6p?i4u*aT?B&+;4@PY9j+Q3!D^Kkk(_MVZZmF?(ev>FMfj3?LDA(sCH
z1b~)k0ZCK>z<l{WW7c}QMX#!KhF^u}7Z^Z#_t`c*!9ho6ng1OIBsGTx<|<%B8|tyb
z5CwRd;Q^!7(4lSLNc;<jCe1`uD<lYAjSe@iuzj@Y^c*4o8sMd1=s~WjS{H?9Z%SDG
z>#(<6p9i{zSvWUlr!G_)#)$Mhqa=>=#FzJCMaGH7XaX8?(2$1ZHcFfi@T7emd_x-d
z61WRKmQ9Sp^fLdApvjm04>UJm>LQvwxc(*1Ja;Uut)s2$(e<d$-prR^%2j!eDRA5_
zp*j-4+VA15M9|)1IWCWRz5EZSu0s4Zr#P5zap>6vijJh9%RjdBe>b^UrelL=R-3CY
zaCkDkc9UG2-XyrBY!)8dZ5}>>lUcTfA8E7#&#Sa>y~PewvE0efd+U6Y23ritHX9ZP
z=8^ZfRQuKol9HnKO~@<~BHY_1t|aj;Y+<&4#!h+`uT|p8MzvOrv9>lgqs?kPisf5h
MExCGit-f~UA5QmC<^TWy

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/structure.py b/keras/downstream_tasks/BraTS/structure.py
new file mode 100755
index 0000000..bca7b8e
--- /dev/null
+++ b/keras/downstream_tasks/BraTS/structure.py
@@ -0,0 +1,50 @@
+#!/usr/bin/env python
+"""
+File: structure
+Date: 5/8/18 
+Author: Jon Deaton (jdeaton@stanford.edu)
+"""
+
+import os
+from enum import Enum
+
+from BraTS.load_utils import find_file_containing
+
+
+class DataSubsetType(Enum):
+    hgg = 0
+    lgg = 1
+    train = 2
+    validation = 3
+
+
+def get_brats_subset_directory(brats_dataset_dir, data_set_type):
+    if data_set_type == DataSubsetType.train:
+        # Training data
+        try:
+            found_train = find_file_containing(brats_dataset_dir, "train", case_sensitive=False)
+        except FileNotFoundError:
+            found_train = None
+        if found_train is not None:
+            return found_train
+        return os.path.join(brats_dataset_dir, "training")
+
+    if data_set_type == DataSubsetType.hgg:
+        train_dir = get_brats_subset_directory(brats_dataset_dir, DataSubsetType.train)
+        return os.path.join(train_dir, "HGG")
+
+    if data_set_type == DataSubsetType.lgg:
+        train_dir = get_brats_subset_directory(brats_dataset_dir, DataSubsetType.train)
+        return os.path.join(train_dir, "LGG")
+
+    if data_set_type == DataSubsetType.validation:
+        # Validation
+        try:
+            found_validation = find_file_containing(brats_dataset_dir, "validation", case_sensitive=False)
+        except FileNotFoundError:
+            found_validation = None
+
+        if found_validation is not None:
+            return found_validation
+        return os.path.join(brats_dataset_dir, "validation")
+
diff --git a/keras/downstream_tasks/BraTS/structure.pyc b/keras/downstream_tasks/BraTS/structure.pyc
new file mode 100755
index 0000000000000000000000000000000000000000..7caec16e483463afcf0628f63598d6dfb0907d21
GIT binary patch
literal 1337
zcmah}ZBG+H5T3oews5=(z68J6k7r^anrH|y1`wzc!-p$IZDKY@Z(FWh@5t>QNt5yk
z|AX;I`A_`j571}!fTEGuc4udHc3z&D*}6aH{Qa*#K6mNz<6_^$((gfHq7JB_*r8NV
z2Mm5Lr49{U>bN9W_9*peSffr2a*dQrJ)G9*3(*D9r%s*X1`C}A`)LPL?EWo?zn7$H
zqp3|%c1>9*e<w1KpRcX2Jza15TctV9i;d=fo;7z=WUvK;*fN{iL|HE{;#C!wkNxBq
zJ_mt-Pve2?X63Mw?n3G%SuA@9CA)cMq9jYQzL|#t;i7hVq?I`wovP~+u$yfx-2_p{
z8)!fs1`o`@(DAqmz#Fy$j+bCj!gh(ngo_x|K@4M+GK+>vO5<B$n8zh@k%n&__xpBF
zvDet3Kz{b(S(GMmWRg4!a847VmmqEz(P4Y-x^k<hqmUyrD$OzLqWX6ElpXVWjip~8
z&9NXuG!S&+P@!nFLdK!-Ri}~Ag(J=#`j9;!4+TB(sn{YR1j>NpOwh+MszG!zO+`rH
z+on!~1`VdH7q+MNWsqqb<QoALB2;0aK6hzigQ9vjZDy>^_y5_{ZraRRn`dGI26N}o
zB^d7yF!R7-!FUxIw6g;9NQ}L|z|?IJ=-WX9^*ace+VSZ|T1l-kotWfI*;d>3@py4>
z-?UnGf7fb-+>>Aq#J0)$2<^CXU-qIDGkAwNOzA;x_VO}|cZ(t~>^L9fnL>kza&6_)
z$Q)Z{kSAGa$L1lleP!fP5g9GD9cmdTh3cBT7==8GRSxzxhpKL3!hpi?Rm17A3`|BE
zya+RclOE?HtGS$pY&m;>@ml+@S-ovcmtl1eOFsc2vEaC3Ma&6b%nDB|I}2iILa%fV
z>+JuA;p$5n=Upj7PQcbd;k}3K&hU|a8>?v^#j-R>s%@dGx^wW!OS0T8dD?cqtlsJ?
RE}!PtTSq2~&Z2w2@f*Vz29f{(

literal 0
HcmV?d00001

diff --git a/keras/downstream_tasks/BraTS/test.py b/keras/downstream_tasks/BraTS/test.py
new file mode 100755
index 0000000..3e5551f
--- /dev/null
+++ b/keras/downstream_tasks/BraTS/test.py
@@ -0,0 +1,32 @@
+#!/usr/bin/env python
+"""
+File: test
+Date: 5/3/18 
+Author: Jon Deaton (jdeaton@stanford.edu)
+
+This file tests the functionality of the BraTS dataset loader
+"""
+
+import BraTS
+import unittest
+import numpy as np
+
+# If, for some reason, you wanted to test this on your machine you would
+# need to set up the BraTS data-sets in some directory and set that path here
+brats_root = "/Users/jonpdeaton/Datasets/BraTS"
+
+class BraTSTest(unittest.TestCase):
+
+    def test_patient(self):
+        brats = BraTS.DataSet(brats_root=brats_root, year=2017)
+        patient = brats.train.patient("Brats17_TCIA_167_1")
+
+        self.assertIsInstance(patient.id, str)
+        self.assertIsInstance(patient.age, float)
+        self.assertIsInstance(patient.survival, int)
+        self.assertIsInstance(patient.mri, np.ndarray)
+        self.assertIsInstance(patient.seg, np.ndarray)
+
+
+if __name__ == "__main__":
+    unittest.main()
\ No newline at end of file
diff --git a/keras/downstream_tasks/BraTS/test_load.py b/keras/downstream_tasks/BraTS/test_load.py
new file mode 100755
index 0000000..4500d30
--- /dev/null
+++ b/keras/downstream_tasks/BraTS/test_load.py
@@ -0,0 +1,31 @@
+#!/usr/bin/env python
+"""
+File: test_load
+Date: 5/4/18 
+Author: Jon Deaton (jdeaton@stanford.edu)
+"""
+
+import io
+import BraTS
+import timeit
+import cProfile, pstats
+
+BraTS.set_root("/Users/jonpdeaton/Datasets/BraTS")
+brats = BraTS.DataSet(year=2017)
+
+
+def load():
+    subset = brats.train.subset(brats.train.ids[:10])
+    x = subset.mris
+
+
+def load_n(n=10):
+    for i in range(n):
+        p = brats.train.patient(brats.train.ids[i])
+
+
+s = timeit.timeit(load)
+print("Time: %s sec" % s)
+
+
+
diff --git a/keras/downstream_tasks/config.py b/keras/downstream_tasks/config.py
new file mode 100755
index 0000000..0d5b518
--- /dev/null
+++ b/keras/downstream_tasks/config.py
@@ -0,0 +1,375 @@
+import os
+import shutil
+import csv
+import keras
+import random
+
+class bms_config:
+    arch = 'Vnet'
+    
+    # data
+    data = '/mnt/dataset/shared/zongwei/BraTS'
+    csv = "data/bms"
+    deltr = 30
+    step_pixel_size = 30
+    input_rows = 64 
+    input_cols = 64
+    input_deps = 32
+    crop_rows = 100
+    crop_cols = 100
+    crop_deps = 50
+    
+    # model
+    lr = 1e-3
+    optimizer = keras.optimizers.Adam(lr=lr)
+    patience = 30
+    verbose = 1
+    batch_size = 12
+    use_multiprocessing = True
+    workers = 4
+    max_queue_size = workers * 1
+    nb_epoch = 10000
+    
+    def __init__(self, args):
+        self.exp_name = self.arch + '-' + args.suffix
+        if args.data is not None:
+            self.data = args.data
+        
+        if args.suffix == 'random':
+            self.weights = None
+        elif args.suffix == 'genesis':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT.h5'
+        elif args.suffix == 'genesis-autoencoder':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-autoencoder.h5'
+        elif args.suffix == 'genesis-nonlinear':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-nonlinear.h5'
+        elif args.suffix == 'genesis-localshuffling':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-localshuffling.h5'
+        elif args.suffix == 'genesis-outpainting':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-outpainting.h5'
+        elif args.suffix == 'genesis-inpainting':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-inpainting.h5'
+        elif args.suffix == 'denoisy':
+            self.weights = 'pretrained_weights/denoisy.h5'
+        elif args.suffix == 'patchshuffling':
+            self.weights = 'pretrained_weights/patchshuffling.h5'
+        elif args.suffix == 'hg':
+            self.weights = 'pretrained_weights/hg.h5'
+        else:
+            raise
+        
+        train_ids = self._load_csv(os.path.join(self.csv, "fold_1.csv")) + self._load_csv(os.path.join(self.csv, "fold_2.csv"))
+        random.Random(4).shuffle(train_ids)
+        self.validation_ids = train_ids[:len(train_ids) // 8]
+        self.train_ids = train_ids[len(train_ids) // 8:]
+        self.test_ids = self._load_csv(os.path.join(self.csv, "fold_3.csv"))
+        self.num_train = len(self.train_ids)
+        self.num_validation = len(self.validation_ids)
+        self.num_test = len(self.test_ids)
+        
+        # logs
+        self.model_path = os.path.join("models/bms", "run_"+str(args.run))
+        if not os.path.exists(self.model_path):
+            os.makedirs(self.model_path)
+        self.logs_path = os.path.join(self.model_path, "logs")
+        if not os.path.exists(self.logs_path):
+            os.makedirs(self.logs_path)
+            
+    def _load_csv(self, foldfile=None):
+        assert foldfile is not None
+        patient_ids = []
+        with open(foldfile, 'r') as f:
+            reader = csv.reader(f, lineterminator='\n')
+            patient_ids.extend(reader)
+        for i, item in enumerate(patient_ids):
+            patient_ids[i] = item[0]
+        return patient_ids
+    
+    def display(self):
+        """Display Configuration values."""
+        print("\nConfigurations:")
+        for a in dir(self):
+            if not a.startswith("__") and not callable(getattr(self, a)) and not '_ids' in a:
+                print("{:30} {}".format(a, getattr(self, a)))
+        print("\n")
+        
+class ecc_config:
+    arch = 'Vnet'
+    
+    # data
+    data = '/mnt/dfs/zongwei/Academic/MICCAI2020/Genesis_PE/dataset/augdata/VOIR'
+    csv = "data/ecc"
+    clip_min = -1000
+    clip_max = 1000
+    input_rows = 64
+    input_cols = 64
+    input_deps = 64
+    
+    # model
+    lr = 1e-3
+    optimizer = keras.optimizers.Adam(lr=lr)
+    patience = 38
+    verbose = 1
+    batch_size = 24
+    use_multiprocessing = False
+    workers = 1
+    max_queue_size = workers * 1
+    nb_epoch = 10000
+    num_classes = 1
+    verbose = 1
+    
+    def __init__(self, args=None):
+        self.exp_name = self.arch + '-' + args.suffix + '-cv-' + str(args.cv)
+        if args.data is not None:
+            self.data = args.data
+            
+        if args.suffix == 'random':
+            self.weights = None
+        elif args.suffix == 'genesis':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT.h5'
+        elif args.suffix == 'genesis-autoencoder':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-autoencoder.h5'
+        elif args.suffix == 'genesis-nonlinear':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-nonlinear.h5'
+        elif args.suffix == 'genesis-localshuffling':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-localshuffling.h5'
+        elif args.suffix == 'genesis-outpainting':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-outpainting.h5'
+        elif args.suffix == 'genesis-inpainting':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-inpainting.h5'
+        elif args.suffix == 'denoisy':
+            self.weights = 'pretrained_weights/denoisy.h5'
+        elif args.suffix == 'patchshuffling':
+            self.weights = 'pretrained_weights/patchshuffling.h5'
+        elif args.suffix == 'hg':
+            self.weights = 'pretrained_weights/hg.h5'
+        else:
+            raise
+            
+        # logs
+        assert args.subsetting is not None
+        self.model_path = os.path.join("models/ecc", "run_"+str(args.run), args.subsetting)
+        if not os.path.exists(self.model_path):
+            os.makedirs(self.model_path)
+        self.logs_path = os.path.join(self.model_path, "logs")
+        if not os.path.exists(self.logs_path):
+            os.makedirs(self.logs_path)
+        self.patch_csv_path = 'Patch-20mm-cv-'+str(args.cv)+'-features_output_2_iter-100000.csv'
+        self.candidate_csv_path = 'Candidate-20mm-cv-'+str(args.cv)+'-features_output_2_iter-100000.csv'
+        self.csv_froc = 'features_output_2_iter-100000.csv'
+
+    def display(self):
+        print("Configurations")
+        for a in dir(self):
+            if not a.startswith("__") and not callable(getattr(self,a)):
+                print("{:30} {}".format(a,getattr(self,a)))
+                #print("\n")
+                
+class ncc_config:
+    arch = 'Vnet'
+    
+    # data
+    data = '/mnt/dataset/shared/zongwei/LUNA16/LUNA16_FPR_32x32x32'
+    train_fold=[0,1,2,3,4]
+    valid_fold=[5,6]
+    test_fold=[7,8,9]
+    hu_min = -1000
+    hu_max = 1000
+    input_rows = 64
+    input_cols = 64
+    input_deps = 32
+    
+    # model
+    lr = 1e-3
+    optimizer = keras.optimizers.Adam(lr=lr)
+    patience = 10
+    verbose = 1
+    batch_size = 24
+    use_multiprocessing = False
+    workers = 1
+    max_queue_size = workers * 1
+    nb_epoch = 10000
+    num_classes = 1
+    verbose = 1
+    
+    def __init__(self, args=None):
+        self.exp_name = self.arch + '-' + args.suffix
+        if args.data is not None:
+            self.data = args.data
+            
+        if args.suffix == 'random':
+            self.weights = None
+        elif args.suffix == 'genesis':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT.h5'
+        elif args.suffix == 'genesis-autoencoder':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-autoencoder.h5'
+        elif args.suffix == 'genesis-nonlinear':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-nonlinear.h5'
+        elif args.suffix == 'genesis-localshuffling':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-localshuffling.h5'
+        elif args.suffix == 'genesis-outpainting':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-outpainting.h5'
+        elif args.suffix == 'genesis-inpainting':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-inpainting.h5'
+        elif args.suffix == 'denoisy':
+            self.weights = 'pretrained_weights/denoisy.h5'
+        elif args.suffix == 'patchshuffling':
+            self.weights = 'pretrained_weights/patchshuffling.h5'
+        elif args.suffix == 'hg':
+            self.weights = 'pretrained_weights/hg.h5'
+        else:
+            raise
+            
+        # logs
+        self.model_path = os.path.join("models/ncc", "run_"+str(args.run))
+        if not os.path.exists(self.model_path):
+            os.makedirs(self.model_path)
+        self.logs_path = os.path.join(self.model_path, "logs")
+        if not os.path.exists(self.logs_path):
+            os.makedirs(self.logs_path)
+
+    def display(self):
+        print("Configurations")
+        for a in dir(self):
+            if not a.startswith("__") and not callable(getattr(self,a)):
+                print("{:30} {}".format(a,getattr(self,a)))
+                #print("\n")
+
+class ncs_config:
+    arch = 'Vnet'
+    
+    # data
+    data = '/mnt/dataset/shared/zongwei/LIDC'
+    input_rows = 64 
+    input_cols = 64
+    input_deps = 32
+    
+    # model
+    lr = 1e-3
+    optimizer = keras.optimizers.Adam(lr=lr)
+    patience = 50
+    verbose = 1
+    batch_size = 16
+    use_multiprocessing = False
+    workers = 1
+    max_queue_size = workers * 1
+    nb_epoch = 10000
+    
+    def __init__(self, args):
+        self.exp_name = self.arch + '-' + args.suffix
+        if args.data is not None:
+            self.data = args.data
+        
+        if args.suffix == 'random':
+            self.weights = None
+        elif args.suffix == 'genesis':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT.h5'
+        elif args.suffix == 'genesis-autoencoder':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-autoencoder.h5'
+        elif args.suffix == 'genesis-nonlinear':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-nonlinear.h5'
+        elif args.suffix == 'genesis-localshuffling':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-localshuffling.h5'
+        elif args.suffix == 'genesis-outpainting':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-outpainting.h5'
+        elif args.suffix == 'genesis-inpainting':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-inpainting.h5'
+        elif args.suffix == 'denoisy':
+            self.weights = 'pretrained_weights/denoisy.h5'
+        elif args.suffix == 'patchshuffling':
+            self.weights = 'pretrained_weights/patchshuffling.h5'
+        elif args.suffix == 'hg':
+            self.weights = 'pretrained_weights/hg.h5'
+        else:
+            raise
+        
+        # logs
+        self.model_path = os.path.join("models/ncs", "run_"+str(args.run))
+        if not os.path.exists(self.model_path):
+            os.makedirs(self.model_path)
+        self.logs_path = os.path.join(self.model_path, "logs")
+        if not os.path.exists(self.logs_path):
+            os.makedirs(self.logs_path)
+    
+    def display(self):
+        """Display Configuration values."""
+        print("\nConfigurations:")
+        for a in dir(self):
+            if not a.startswith("__") and not callable(getattr(self, a)):
+                print("{:30} {}".format(a, getattr(self, a)))
+        print("\n")
+        
+        
+class lcs_config:
+    arch = 'Vnet'
+    
+    # data
+    data = '/mnt/dfs/zongwei/Academic/MICCAI2019/Data/LiTS/3D_LiTS_NPY_256x256xZ'
+    nii = '/mnt/dataset/shared/zongwei/LiTS/Tr'
+    obj = 'liver'
+    train_idx = [n for n in range(0, 100)]
+    valid_idx = [n for n in range(100,  115)]
+    test_idx = [n for n in range(115, 130)]
+    num_train = len(train_idx)
+    num_valid = len(valid_idx)
+    num_test = len(test_idx)
+    hu_max = 1000
+    hu_min = -1000
+    input_rows = 64
+    input_cols = 64
+    input_deps = 32
+    
+    # model
+    lr = 1e-3
+    optimizer = keras.optimizers.Adam(lr=lr)
+    patience = 20
+    verbose = 1
+    batch_size = 16
+    use_multiprocessing = False
+    workers = 1
+    max_queue_size = workers * 1
+    nb_epoch = 10000
+    
+    def __init__(self, args):
+        self.exp_name = self.arch + '-' + args.suffix
+        if args.data is not None:
+            self.data = args.data
+        
+        if args.suffix == 'random':
+            self.weights = None
+        elif args.suffix == 'genesis':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT.h5'
+        elif args.suffix == 'genesis-autoencoder':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-autoencoder.h5'
+        elif args.suffix == 'genesis-nonlinear':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-nonlinear.h5'
+        elif args.suffix == 'genesis-localshuffling':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-localshuffling.h5'
+        elif args.suffix == 'genesis-outpainting':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-outpainting.h5'
+        elif args.suffix == 'genesis-inpainting':
+            self.weights = 'pretrained_weights/Genesis_Chest_CT-inpainting.h5'
+        elif args.suffix == 'denoisy':
+            self.weights = 'pretrained_weights/denoisy.h5'
+        elif args.suffix == 'patchshuffling':
+            self.weights = 'pretrained_weights/patchshuffling.h5'
+        elif args.suffix == 'hg':
+            self.weights = 'pretrained_weights/hg.h5'
+        else:
+            raise
+        
+        # logs
+        self.model_path = os.path.join("models/lcs", "run_"+str(args.run))
+        if not os.path.exists(self.model_path):
+            os.makedirs(self.model_path)
+        self.logs_path = os.path.join(self.model_path, "logs")
+        if not os.path.exists(self.logs_path):
+            os.makedirs(self.logs_path)
+    
+    def display(self):
+        """Display Configuration values."""
+        print("\nConfigurations:")
+        for a in dir(self):
+            if not a.startswith("__") and not callable(getattr(self, a)) and not '_idx' in a:
+                print("{:30} {}".format(a, getattr(self, a)))
+        print("\n")
diff --git a/keras/downstream_tasks/data/bms/fold_1.csv b/keras/downstream_tasks/data/bms/fold_1.csv
new file mode 100755
index 0000000..a001c92
--- /dev/null
+++ b/keras/downstream_tasks/data/bms/fold_1.csv
@@ -0,0 +1,95 @@
+Brats18_TCIA10_330_1
+Brats18_TCIA04_437_1
+Brats18_2013_3_1
+Brats18_TCIA08_469_1
+Brats18_TCIA09_620_1
+Brats18_TCIA08_242_1
+Brats18_TCIA10_103_1
+Brats18_TCIA01_221_1
+Brats18_TCIA04_149_1
+Brats18_CBICA_ANZ_1
+Brats18_2013_18_1
+Brats18_TCIA02_314_1
+Brats18_CBICA_ATD_1
+Brats18_TCIA02_274_1
+Brats18_CBICA_AQR_1
+Brats18_CBICA_ASU_1
+Brats18_TCIA06_372_1
+Brats18_TCIA13_623_1
+Brats18_TCIA02_331_1
+Brats18_CBICA_ABE_1
+Brats18_TCIA03_199_1
+Brats18_CBICA_ASO_1
+Brats18_TCIA08_436_1
+Brats18_TCIA10_625_1
+Brats18_TCIA10_241_1
+Brats18_CBICA_ASH_1
+Brats18_TCIA12_466_1
+Brats18_TCIA01_201_1
+Brats18_CBICA_ATB_1
+Brats18_TCIA01_425_1
+Brats18_CBICA_AYA_1
+Brats18_TCIA02_608_1
+Brats18_2013_16_1
+Brats18_2013_24_1
+Brats18_TCIA04_479_1
+Brats18_TCIA13_633_1
+Brats18_TCIA01_235_1
+Brats18_2013_0_1
+Brats18_TCIA10_640_1
+Brats18_TCIA04_328_1
+Brats18_TCIA02_473_1
+Brats18_TCIA09_254_1
+Brats18_CBICA_ABM_1
+Brats18_CBICA_ATV_1
+Brats18_CBICA_AQA_1
+Brats18_TCIA10_449_1
+Brats18_TCIA01_231_1
+Brats18_2013_12_1
+Brats18_CBICA_AXN_1
+Brats18_TCIA10_130_1
+Brats18_TCIA10_261_1
+Brats18_2013_17_1
+Brats18_TCIA08_205_1
+Brats18_TCIA10_490_1
+Brats18_TCIA02_198_1
+Brats18_2013_20_1
+Brats18_CBICA_ALX_1
+Brats18_CBICA_AQV_1
+Brats18_TCIA06_184_1
+Brats18_CBICA_AXJ_1
+Brats18_CBICA_AVJ_1
+Brats18_TCIA10_276_1
+Brats18_TCIA01_448_1
+Brats18_TCIA03_498_1
+Brats18_TCIA10_310_1
+Brats18_TCIA02_283_1
+Brats18_TCIA02_151_1
+Brats18_TCIA12_298_1
+Brats18_CBICA_BFP_1
+Brats18_TCIA03_138_1
+Brats18_TCIA10_420_1
+Brats18_TCIA10_410_1
+Brats18_TCIA02_471_1
+Brats18_CBICA_ATX_1
+Brats18_CBICA_APY_1
+Brats18_TCIA02_168_1
+Brats18_TCIA13_653_1
+Brats18_CBICA_AWH_1
+Brats18_2013_14_1
+Brats18_TCIA05_478_1
+Brats18_CBICA_AXL_1
+Brats18_TCIA09_462_1
+Brats18_CBICA_ARW_1
+Brats18_TCIA03_257_1
+Brats18_TCIA02_605_1
+Brats18_TCIA01_186_1
+Brats18_2013_26_1
+Brats18_CBICA_AAP_1
+Brats18_CBICA_AXO_1
+Brats18_TCIA10_639_1
+Brats18_2013_6_1
+Brats18_TCIA08_218_1
+Brats18_CBICA_AXM_1
+Brats18_CBICA_AVG_1
+Brats18_CBICA_AAL_1
diff --git a/keras/downstream_tasks/data/bms/fold_2.csv b/keras/downstream_tasks/data/bms/fold_2.csv
new file mode 100755
index 0000000..18066eb
--- /dev/null
+++ b/keras/downstream_tasks/data/bms/fold_2.csv
@@ -0,0 +1,95 @@
+Brats18_CBICA_AVV_1
+Brats18_TCIA01_147_1
+Brats18_TCIA01_460_1
+Brats18_TCIA10_387_1
+Brats18_2013_7_1
+Brats18_TCIA12_249_1
+Brats18_TCIA09_493_1
+Brats18_TCIA01_190_1
+Brats18_TCIA10_644_1
+Brats18_TCIA12_480_1
+Brats18_2013_8_1
+Brats18_TCIA10_351_1
+Brats18_TCIA01_203_1
+Brats18_TCIA10_299_1
+Brats18_CBICA_APZ_1
+Brats18_TCIA13_618_1
+Brats18_TCIA02_300_1
+Brats18_CBICA_AQN_1
+Brats18_TCIA03_419_1
+Brats18_TCIA08_105_1
+Brats18_TCIA13_650_1
+Brats18_TCIA10_413_1
+Brats18_TCIA13_645_1
+Brats18_CBICA_AQU_1
+Brats18_CBICA_AXW_1
+Brats18_TCIA01_390_1
+Brats18_TCIA02_394_1
+Brats18_TCIA09_141_1
+Brats18_TCIA03_133_1
+Brats18_TCIA10_637_1
+Brats18_CBICA_AQO_1
+Brats18_CBICA_AQY_1
+Brats18_TCIA02_491_1
+Brats18_CBICA_ABO_1
+Brats18_TCIA04_111_1
+Brats18_2013_22_1
+Brats18_TCIA08_319_1
+Brats18_TCIA03_375_1
+Brats18_2013_9_1
+Brats18_TCIA08_113_1
+Brats18_TCIA10_202_1
+Brats18_CBICA_AOZ_1
+Brats18_TCIA05_277_1
+Brats18_2013_4_1
+Brats18_TCIA09_312_1
+Brats18_CBICA_AUQ_1
+Brats18_TCIA02_171_1
+Brats18_CBICA_AME_1
+Brats18_CBICA_BHK_1
+Brats18_TCIA08_234_1
+Brats18_CBICA_AUR_1
+Brats18_2013_11_1
+Brats18_TCIA10_152_1
+Brats18_TCIA03_121_1
+Brats18_CBICA_ALN_1
+Brats18_CBICA_AWG_1
+Brats18_CBICA_AQQ_1
+Brats18_TCIA13_630_1
+Brats18_TCIA06_247_1
+Brats18_TCIA13_615_1
+Brats18_TCIA09_451_1
+Brats18_CBICA_ASE_1
+Brats18_2013_27_1
+Brats18_TCIA10_628_1
+Brats18_TCIA06_165_1
+Brats18_CBICA_ABY_1
+Brats18_TCIA02_377_1
+Brats18_TCIA02_455_1
+Brats18_TCIA12_470_1
+Brats18_2013_13_1
+Brats18_CBICA_ASW_1
+Brats18_TCIA09_255_1
+Brats18_2013_29_1
+Brats18_TCIA04_361_1
+Brats18_TCIA13_624_1
+Brats18_2013_15_1
+Brats18_CBICA_BHM_1
+Brats18_TCIA10_175_1
+Brats18_TCIA10_393_1
+Brats18_TCIA10_629_1
+Brats18_CBICA_AAG_1
+Brats18_CBICA_AQJ_1
+Brats18_TCIA02_321_1
+Brats18_TCIA02_222_1
+Brats18_TCIA10_307_1
+Brats18_CBICA_AQD_1
+Brats18_TCIA03_338_1
+Brats18_2013_23_1
+Brats18_2013_5_1
+Brats18_TCIA04_192_1
+Brats18_TCIA06_211_1
+Brats18_TCIA02_135_1
+Brats18_TCIA05_444_1
+Brats18_CBICA_ASV_1
+Brats18_TCIA02_226_1
diff --git a/keras/downstream_tasks/data/bms/fold_3.csv b/keras/downstream_tasks/data/bms/fold_3.csv
new file mode 100755
index 0000000..04babdb
--- /dev/null
+++ b/keras/downstream_tasks/data/bms/fold_3.csv
@@ -0,0 +1,95 @@
+Brats18_CBICA_AZD_1
+Brats18_CBICA_AUN_1
+Brats18_CBICA_ANP_1
+Brats18_CBICA_AQZ_1
+Brats18_CBICA_AZH_1
+Brats18_TCIA02_370_1
+Brats18_TCIA02_374_1
+Brats18_CBICA_AOO_1
+Brats18_TCIA09_428_1
+Brats18_2013_25_1
+Brats18_CBICA_AOH_1
+Brats18_TCIA10_442_1
+Brats18_CBICA_ABN_1
+Brats18_CBICA_ATF_1
+Brats18_TCIA03_265_1
+Brats18_TCIA13_654_1
+Brats18_TCIA02_430_1
+Brats18_TCIA01_429_1
+Brats18_TCIA01_401_1
+Brats18_TCIA10_346_1
+Brats18_TCIA02_368_1
+Brats18_TCIA01_131_1
+Brats18_TCIA08_278_1
+Brats18_2013_28_1
+Brats18_2013_1_1
+Brats18_TCIA06_409_1
+Brats18_TCIA08_162_1
+Brats18_CBICA_AQT_1
+Brats18_CBICA_ASK_1
+Brats18_CBICA_AQG_1
+Brats18_CBICA_ALU_1
+Brats18_CBICA_BHB_1
+Brats18_CBICA_AYW_1
+Brats18_CBICA_ARZ_1
+Brats18_TCIA02_290_1
+Brats18_CBICA_AYI_1
+Brats18_CBICA_AXQ_1
+Brats18_CBICA_AOD_1
+Brats18_TCIA01_378_1
+Brats18_TCIA05_396_1
+Brats18_TCIA08_406_1
+Brats18_TCIA13_634_1
+Brats18_TCIA09_402_1
+Brats18_TCIA03_296_1
+Brats18_TCIA02_179_1
+Brats18_CBICA_ASA_1
+Brats18_TCIA10_109_1
+Brats18_2013_10_1
+Brats18_CBICA_ASG_1
+Brats18_TCIA08_280_1
+Brats18_TCIA02_117_1
+Brats18_TCIA13_642_1
+Brats18_TCIA09_177_1
+Brats18_TCIA08_167_1
+Brats18_TCIA10_266_1
+Brats18_TCIA10_282_1
+Brats18_2013_2_1
+Brats18_CBICA_ARF_1
+Brats18_TCIA01_180_1
+Brats18_TCIA10_408_1
+Brats18_CBICA_ANG_1
+Brats18_CBICA_AQP_1
+Brats18_TCIA01_335_1
+Brats18_TCIA10_632_1
+Brats18_TCIA02_606_1
+Brats18_TCIA02_607_1
+Brats18_CBICA_AMH_1
+Brats18_TCIA04_343_1
+Brats18_TCIA13_621_1
+Brats18_TCIA02_322_1
+Brats18_CBICA_ASY_1
+Brats18_CBICA_AWI_1
+Brats18_TCIA01_499_1
+Brats18_TCIA01_411_1
+Brats18_2013_21_1
+Brats18_CBICA_AYU_1
+Brats18_TCIA01_412_1
+Brats18_CBICA_APR_1
+Brats18_CBICA_ATP_1
+Brats18_TCIA02_118_1
+Brats18_TCIA03_474_1
+Brats18_TCIA12_101_1
+Brats18_CBICA_BFB_1
+Brats18_CBICA_AAB_1
+Brats18_TCIA02_208_1
+Brats18_TCIA06_603_1
+Brats18_2013_19_1
+Brats18_CBICA_ABB_1
+Brats18_CBICA_ANI_1
+Brats18_CBICA_ASN_1
+Brats18_TCIA10_325_1
+Brats18_TCIA06_332_1
+Brats18_CBICA_AOP_1
+Brats18_TCIA02_309_1
+Brats18_TCIA01_150_1
diff --git a/keras/downstream_tasks/data/ecc/test_cv-1.csv b/keras/downstream_tasks/data/ecc/test_cv-1.csv
new file mode 100755
index 0000000..347af46
--- /dev/null
+++ b/keras/downstream_tasks/data/ecc/test_cv-1.csv
@@ -0,0 +1,40 @@
+FileName
+Patient03284
+Patient03266
+Patient03234
+Patient03280
+Patient03286
+Patient03262
+Patient03237
+Patient03243
+Patient03275
+Patient03268
+Patient03232
+Patient03240
+Patient03228
+Patient03229
+Patient03283
+Patient03222
+Patient03271
+Patient03256
+Patient03246
+Patient03239
+Patient03251
+Patient03276
+Patient03281
+Patient03263
+Patient03250
+Patient03257
+Patient03242
+Patient03267
+Patient03258
+Patient03272
+Patient03282
+Patient03291
+Patient03244
+Patient03231
+Patient03287
+Patient03249
+Patient03253
+Patient03278
+Patient03254
diff --git a/keras/downstream_tasks/data/ecc/test_cv-2.csv b/keras/downstream_tasks/data/ecc/test_cv-2.csv
new file mode 100755
index 0000000..497dd97
--- /dev/null
+++ b/keras/downstream_tasks/data/ecc/test_cv-2.csv
@@ -0,0 +1,40 @@
+FileName
+Patient21229
+Patient21108
+Patient03209
+Patient03210
+Patient21115
+Patient21107
+Patient03130
+Patient03204
+Patient03213
+Patient03129
+Patient03206
+Patient03218
+Patient21113
+Patient21228
+Patient21106
+Patient21112
+Patient21227
+Patient21101
+Patient03122
+Patient03201
+Patient03220
+Patient03221
+Patient21100
+Patient03216
+Patient03124
+Patient03215
+Patient21118
+Patient21110
+Patient21104
+Patient03125
+Patient21117
+Patient03212
+Patient03219
+Patient21109
+Patient21102
+Patient21119
+Patient03208
+Patient21116
+Patient21103
diff --git a/keras/downstream_tasks/data/ecc/test_cv-3.csv b/keras/downstream_tasks/data/ecc/test_cv-3.csv
new file mode 100755
index 0000000..46b8084
--- /dev/null
+++ b/keras/downstream_tasks/data/ecc/test_cv-3.csv
@@ -0,0 +1,40 @@
+FileName
+Patient21222
+Patient03118
+Patient21215
+Patient28005
+Patient21214
+Patient03000
+Patient03001
+Patient28010
+Patient03102
+Patient03103
+Patient21225
+Patient03120
+Patient03002
+Patient03108
+Patient03116
+Patient03003
+Patient28008
+Patient28002
+Patient03109
+Patient21220
+Patient21206
+Patient21216
+Patient21205
+Patient21217
+Patient03104
+Patient03005
+Patient03119
+Patient03110
+Patient28004
+Patient03106
+Patient21221
+Patient21213
+Patient28007
+Patient03114
+Patient21201
+Patient28006
+Patient21224
+Patient21208
+Patient21200
diff --git a/keras/downstream_tasks/data/ecc/train_cv-1.csv b/keras/downstream_tasks/data/ecc/train_cv-1.csv
new file mode 100755
index 0000000..e7ce590
--- /dev/null
+++ b/keras/downstream_tasks/data/ecc/train_cv-1.csv
@@ -0,0 +1,75 @@
+FileName
+Patient21108
+Patient03219
+Patient03201
+Patient21103
+Patient03125
+Patient21104
+Patient28002
+Patient03114
+Patient03102
+Patient03116
+Patient28010
+Patient21113
+Patient21205
+Patient03000
+Patient03129
+Patient21206
+Patient21227
+Patient21214
+Patient21220
+Patient03216
+Patient21201
+Patient28005
+Patient03204
+Patient03209
+Patient21119
+Patient03003
+Patient03118
+Patient03210
+Patient21224
+Patient21217
+Patient21112
+Patient21102
+Patient21215
+Patient03124
+Patient21221
+Patient21225
+Patient28006
+Patient21200
+Patient21117
+Patient28008
+Patient03215
+Patient21118
+Patient03208
+Patient03001
+Patient03110
+Patient28007
+Patient03212
+Patient03005
+Patient03130
+Patient03122
+Patient21110
+Patient21229
+Patient03119
+Patient21116
+Patient03104
+Patient21208
+Patient21222
+Patient03120
+Patient03213
+Patient21106
+Patient03108
+Patient03220
+Patient03109
+Patient21107
+Patient21228
+Patient21101
+Patient21100
+Patient03218
+Patient03103
+Patient21115
+Patient03002
+Patient28004
+Patient21213
+Patient03206
diff --git a/keras/downstream_tasks/data/ecc/train_cv-2.csv b/keras/downstream_tasks/data/ecc/train_cv-2.csv
new file mode 100755
index 0000000..2cd1915
--- /dev/null
+++ b/keras/downstream_tasks/data/ecc/train_cv-2.csv
@@ -0,0 +1,75 @@
+FileName
+Patient21215
+Patient21201
+Patient03103
+Patient03114
+Patient21224
+Patient03119
+Patient28005
+Patient21208
+Patient03256
+Patient21220
+Patient21217
+Patient03234
+Patient03278
+Patient03262
+Patient21200
+Patient28007
+Patient03108
+Patient28004
+Patient03104
+Patient28010
+Patient03001
+Patient21225
+Patient03232
+Patient03268
+Patient03110
+Patient03116
+Patient03257
+Patient03280
+Patient28008
+Patient03222
+Patient03251
+Patient03239
+Patient03254
+Patient21213
+Patient03267
+Patient21222
+Patient03250
+Patient03120
+Patient03237
+Patient03242
+Patient03240
+Patient03282
+Patient03263
+Patient03102
+Patient03253
+Patient03246
+Patient03231
+Patient03229
+Patient03258
+Patient03249
+Patient21221
+Patient28006
+Patient21216
+Patient03109
+Patient03005
+Patient21214
+Patient03002
+Patient03287
+Patient03281
+Patient03106
+Patient03243
+Patient21206
+Patient03118
+Patient03003
+Patient03271
+Patient03228
+Patient28002
+Patient03284
+Patient03276
+Patient03286
+Patient21205
+Patient03275
+Patient03000
+Patient03291
diff --git a/keras/downstream_tasks/data/ecc/train_cv-3.csv b/keras/downstream_tasks/data/ecc/train_cv-3.csv
new file mode 100755
index 0000000..7ec23df
--- /dev/null
+++ b/keras/downstream_tasks/data/ecc/train_cv-3.csv
@@ -0,0 +1,75 @@
+FileName
+Patient03276
+Patient03251
+Patient03215
+Patient21118
+Patient03282
+Patient03232
+Patient03287
+Patient03284
+Patient21104
+Patient03209
+Patient21108
+Patient03281
+Patient21229
+Patient03278
+Patient03256
+Patient03208
+Patient03263
+Patient21116
+Patient21103
+Patient21100
+Patient03130
+Patient03129
+Patient03262
+Patient03212
+Patient03272
+Patient03254
+Patient03221
+Patient21102
+Patient21227
+Patient03228
+Patient03218
+Patient03268
+Patient21119
+Patient21107
+Patient03210
+Patient03206
+Patient03250
+Patient03216
+Patient21101
+Patient03244
+Patient03220
+Patient03125
+Patient03229
+Patient03124
+Patient03257
+Patient03283
+Patient21112
+Patient03271
+Patient03219
+Patient21113
+Patient03275
+Patient03204
+Patient03231
+Patient03201
+Patient21117
+Patient03213
+Patient21115
+Patient21110
+Patient03258
+Patient03239
+Patient03242
+Patient21106
+Patient03280
+Patient03249
+Patient03237
+Patient03240
+Patient03266
+Patient03222
+Patient03267
+Patient03291
+Patient03234
+Patient21109
+Patient03243
+Patient03246
diff --git a/keras/downstream_tasks/data/ecc/val_cv-1.csv b/keras/downstream_tasks/data/ecc/val_cv-1.csv
new file mode 100755
index 0000000..ae2133b
--- /dev/null
+++ b/keras/downstream_tasks/data/ecc/val_cv-1.csv
@@ -0,0 +1,5 @@
+FileName
+Patient21216
+Patient03106
+Patient21109
+Patient03221
diff --git a/keras/downstream_tasks/data/ecc/val_cv-2.csv b/keras/downstream_tasks/data/ecc/val_cv-2.csv
new file mode 100755
index 0000000..b820563
--- /dev/null
+++ b/keras/downstream_tasks/data/ecc/val_cv-2.csv
@@ -0,0 +1,5 @@
+FileName
+Patient03283
+Patient03266
+Patient03272
+Patient03244
diff --git a/keras/downstream_tasks/data/ecc/val_cv-3.csv b/keras/downstream_tasks/data/ecc/val_cv-3.csv
new file mode 100755
index 0000000..bfd59a4
--- /dev/null
+++ b/keras/downstream_tasks/data/ecc/val_cv-3.csv
@@ -0,0 +1,5 @@
+FileName
+Patient03286
+Patient03253
+Patient21228
+Patient03122
diff --git a/keras/downstream_tasks/lung nodule segmentation.ipynb b/keras/downstream_tasks/lung nodule segmentation.ipynb
new file mode 100644
index 0000000..d025690
--- /dev/null
+++ b/keras/downstream_tasks/lung nodule segmentation.ipynb	
@@ -0,0 +1,489 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "keras = 2.2.4\n",
+      "tensorflow-gpu = 1.13.1\n",
+      "\n",
+      "Configurations:\n",
+      "arch                           Vnet\n",
+      "batch_size                     16\n",
+      "data                           /mnt/dataset/shared/zongwei/LIDC\n",
+      "exp_name                       Vnet-genesis\n",
+      "input_cols                     64\n",
+      "input_deps                     32\n",
+      "input_rows                     64\n",
+      "logs_path                      models/ncs/run_1/logs\n",
+      "lr                             0.001\n",
+      "max_queue_size                 1\n",
+      "model_path                     models/ncs/run_1\n",
+      "nb_epoch                       10000\n",
+      "optimizer                      adam\n",
+      "patience                       50\n",
+      "verbose                        1\n",
+      "weights                        pretrained_weights/Genesis_Chest_CT.h5\n",
+      "workers                        1\n",
+      "\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "#!/usr/bin/env python\n",
+    "# coding: utf-8\n",
+    "from __future__ import print_function\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')\n",
+    "import os\n",
+    "os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'  # or any {'0', '1', '2'}\n",
+    "import keras\n",
+    "print(\"keras = {}\".format(keras.__version__))\n",
+    "import tensorflow as tf\n",
+    "print(\"tensorflow-gpu = {}\".format(tf.__version__))\n",
+    "try:\n",
+    "    tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)\n",
+    "except:\n",
+    "    pass\n",
+    "import random\n",
+    "import shutil\n",
+    "import argparse\n",
+    "import sklearn\n",
+    "from pathlib import Path\n",
+    "from utils import *\n",
+    "from unet3d import *\n",
+    "from config import *\n",
+    "\n",
+    "class set_args():\n",
+    "    gpu = 0\n",
+    "    data = None\n",
+    "    apps = 'ncs'\n",
+    "    run = 1\n",
+    "    cv = None\n",
+    "    subsetting = None\n",
+    "    suffix = 'genesis'\n",
+    "    task = 'segmentation'\n",
+    "    \n",
+    "args = set_args()\n",
+    "\n",
+    "if args.gpu is not None:\n",
+    "    os.environ[\"CUDA_VISIBLE_DEVICES\"] = str(args.gpu)\n",
+    "    \n",
+    "from ncs_data import *\n",
+    "conf = ncs_config(args)\n",
+    "\n",
+    "conf.display()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Train"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "x_train: (4082, 1, 64, 64, 32) | 0.0 ~ 1.0\n",
+      "y_train: (4082, 1, 64, 64, 32) | 0 ~ 1\n",
+      "x_valid: (3126, 1, 64, 64, 32) | 0.0 ~ 1.0\n",
+      "y_valid: (3126, 1, 64, 64, 32) | 0 ~ 1\n",
+      "[INFO] Load pre-trained weights from pretrained_weights/Genesis_Chest_CT.h5\n",
+      "Train on 4082 samples, validate on 3126 samples\n",
+      "Epoch 1/10000\n",
+      "\n",
+      "> Batch size = 14\n",
+      "Train on 4082 samples, validate on 3126 samples\n",
+      "Epoch 1/10000\n",
+      "1036/4082 [======>.......................] - ETA: 7:37 - loss: 0.4391 - mean_iou: 0.6119 - dice_coef: 0.5609\n",
+      "> Batch size = 12\n",
+      "Train on 4082 samples, validate on 3126 samples\n",
+      "Epoch 1/10000\n",
+      "4082/4082 [==============================] - 709s 174ms/step - loss: 0.2932 - mean_iou: 0.7156 - dice_coef: 0.7068 - val_loss: 0.3287 - val_mean_iou: 0.7407 - val_dice_coef: 0.6713\n",
+      "\n",
+      "Epoch 00001: val_loss improved from inf to 0.32870, saving model to models/ncs/run_1/Vnet-genesis.h5\n",
+      "Epoch 2/10000\n",
+      "4082/4082 [==============================] - 699s 171ms/step - loss: 0.2394 - mean_iou: 0.7524 - dice_coef: 0.7606 - val_loss: 0.3988 - val_mean_iou: 0.7547 - val_dice_coef: 0.6012\n",
+      "\n",
+      "Epoch 00002: val_loss did not improve from 0.32870\n",
+      "Epoch 3/10000\n",
+      "4082/4082 [==============================] - 700s 171ms/step - loss: 0.1950 - mean_iou: 0.7582 - dice_coef: 0.8050 - val_loss: 0.3279 - val_mean_iou: 0.7705 - val_dice_coef: 0.6721\n",
+      "\n",
+      "Epoch 00003: val_loss improved from 0.32870 to 0.32789, saving model to models/ncs/run_1/Vnet-genesis.h5\n",
+      "Epoch 4/10000\n",
+      "3756/4082 [==========================>...] - ETA: 44s - loss: 0.1836 - mean_iou: 0.7800 - dice_coef: 0.8164\n",
+      "> Batch size = 10\n",
+      "Train on 4082 samples, validate on 3126 samples\n",
+      "Epoch 1/10000\n",
+      "4082/4082 [==============================] - 708s 173ms/step - loss: 0.1886 - mean_iou: 0.7914 - dice_coef: 0.8114 - val_loss: 0.2994 - val_mean_iou: 0.7959 - val_dice_coef: 0.7006\n",
+      "\n",
+      "Epoch 00001: val_loss improved from 0.32789 to 0.29936, saving model to models/ncs/run_1/Vnet-genesis.h5\n",
+      "Epoch 2/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.1628 - mean_iou: 0.8009 - dice_coef: 0.8372 - val_loss: 0.2804 - val_mean_iou: 0.8049 - val_dice_coef: 0.7196\n",
+      "\n",
+      "Epoch 00002: val_loss improved from 0.29936 to 0.28040, saving model to models/ncs/run_1/Vnet-genesis.h5\n",
+      "Epoch 3/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.1491 - mean_iou: 0.8091 - dice_coef: 0.8509 - val_loss: 0.2657 - val_mean_iou: 0.8126 - val_dice_coef: 0.7343\n",
+      "\n",
+      "Epoch 00003: val_loss improved from 0.28040 to 0.26571, saving model to models/ncs/run_1/Vnet-genesis.h5\n",
+      "Epoch 4/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.1382 - mean_iou: 0.8161 - dice_coef: 0.8618 - val_loss: 0.2471 - val_mean_iou: 0.8187 - val_dice_coef: 0.7529\n",
+      "\n",
+      "Epoch 00004: val_loss improved from 0.26571 to 0.24712, saving model to models/ncs/run_1/Vnet-genesis.h5\n",
+      "Epoch 5/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.1279 - mean_iou: 0.8214 - dice_coef: 0.8721 - val_loss: 0.2390 - val_mean_iou: 0.8239 - val_dice_coef: 0.7610\n",
+      "\n",
+      "Epoch 00005: val_loss improved from 0.24712 to 0.23904, saving model to models/ncs/run_1/Vnet-genesis.h5\n",
+      "Epoch 6/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.1185 - mean_iou: 0.8267 - dice_coef: 0.8815 - val_loss: 0.2461 - val_mean_iou: 0.8287 - val_dice_coef: 0.7539\n",
+      "\n",
+      "Epoch 00006: val_loss did not improve from 0.23904\n",
+      "Epoch 7/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.1167 - mean_iou: 0.8308 - dice_coef: 0.8833 - val_loss: 0.2459 - val_mean_iou: 0.8322 - val_dice_coef: 0.7541\n",
+      "\n",
+      "Epoch 00007: val_loss did not improve from 0.23904\n",
+      "Epoch 8/10000\n",
+      "4082/4082 [==============================] - 703s 172ms/step - loss: 0.1251 - mean_iou: 0.8337 - dice_coef: 0.8749 - val_loss: 0.2395 - val_mean_iou: 0.8349 - val_dice_coef: 0.7605\n",
+      "\n",
+      "Epoch 00008: val_loss did not improve from 0.23904\n",
+      "Epoch 9/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.1071 - mean_iou: 0.8366 - dice_coef: 0.8929 - val_loss: 0.2241 - val_mean_iou: 0.8380 - val_dice_coef: 0.7759\n",
+      "\n",
+      "Epoch 00009: val_loss improved from 0.23904 to 0.22408, saving model to models/ncs/run_1/Vnet-genesis.h5\n",
+      "Epoch 10/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.1058 - mean_iou: 0.8395 - dice_coef: 0.8942 - val_loss: 0.2433 - val_mean_iou: 0.8406 - val_dice_coef: 0.7567\n",
+      "\n",
+      "Epoch 00010: val_loss did not improve from 0.22408\n",
+      "Epoch 11/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0951 - mean_iou: 0.8420 - dice_coef: 0.9049 - val_loss: 0.2280 - val_mean_iou: 0.8432 - val_dice_coef: 0.7720\n",
+      "\n",
+      "Epoch 00011: val_loss did not improve from 0.22408\n",
+      "Epoch 12/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.1027 - mean_iou: 0.8444 - dice_coef: 0.8973 - val_loss: 0.2540 - val_mean_iou: 0.8452 - val_dice_coef: 0.7460\n",
+      "\n",
+      "Epoch 00012: val_loss did not improve from 0.22408\n",
+      "Epoch 13/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0900 - mean_iou: 0.8463 - dice_coef: 0.9100 - val_loss: 0.2332 - val_mean_iou: 0.8473 - val_dice_coef: 0.7668\n",
+      "\n",
+      "Epoch 00013: val_loss did not improve from 0.22408\n",
+      "Epoch 14/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0853 - mean_iou: 0.8484 - dice_coef: 0.9147 - val_loss: 0.2253 - val_mean_iou: 0.8493 - val_dice_coef: 0.7747\n",
+      "\n",
+      "Epoch 00014: val_loss did not improve from 0.22408\n",
+      "Epoch 15/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0814 - mean_iou: 0.8504 - dice_coef: 0.9186 - val_loss: 0.2390 - val_mean_iou: 0.8512 - val_dice_coef: 0.7610\n",
+      "\n",
+      "Epoch 00015: val_loss did not improve from 0.22408\n",
+      "\n",
+      "Epoch 00015: ReduceLROnPlateau reducing learning rate to 0.0005000000237487257.\n",
+      "Epoch 16/10000\n",
+      "4082/4082 [==============================] - 705s 173ms/step - loss: 0.0713 - mean_iou: 0.8523 - dice_coef: 0.9287 - val_loss: 0.2344 - val_mean_iou: 0.8531 - val_dice_coef: 0.7656\n",
+      "\n",
+      "Epoch 00016: val_loss did not improve from 0.22408\n",
+      "Epoch 17/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0672 - mean_iou: 0.8541 - dice_coef: 0.9328 - val_loss: 0.2396 - val_mean_iou: 0.8550 - val_dice_coef: 0.7604\n",
+      "\n",
+      "Epoch 00017: val_loss did not improve from 0.22408\n",
+      "Epoch 18/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0652 - mean_iou: 0.8559 - dice_coef: 0.9348 - val_loss: 0.2411 - val_mean_iou: 0.8567 - val_dice_coef: 0.7589\n",
+      "\n",
+      "Epoch 00018: val_loss did not improve from 0.22408\n",
+      "Epoch 19/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0640 - mean_iou: 0.8575 - dice_coef: 0.9360 - val_loss: 0.2457 - val_mean_iou: 0.8582 - val_dice_coef: 0.7543\n",
+      "\n",
+      "Epoch 00019: val_loss did not improve from 0.22408\n",
+      "Epoch 20/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0617 - mean_iou: 0.8590 - dice_coef: 0.9383 - val_loss: 0.2381 - val_mean_iou: 0.8597 - val_dice_coef: 0.7619\n",
+      "\n",
+      "Epoch 00020: val_loss did not improve from 0.22408\n",
+      "Epoch 21/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0619 - mean_iou: 0.8604 - dice_coef: 0.9381 - val_loss: 0.2309 - val_mean_iou: 0.8610 - val_dice_coef: 0.7691\n",
+      "\n",
+      "Epoch 00021: val_loss did not improve from 0.22408\n",
+      "\n",
+      "Epoch 00021: ReduceLROnPlateau reducing learning rate to 0.0002500000118743628.\n",
+      "Epoch 22/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0547 - mean_iou: 0.8617 - dice_coef: 0.9453 - val_loss: 0.2348 - val_mean_iou: 0.8624 - val_dice_coef: 0.7652\n",
+      "\n",
+      "Epoch 00022: val_loss did not improve from 0.22408\n",
+      "Epoch 23/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0526 - mean_iou: 0.8631 - dice_coef: 0.9474 - val_loss: 0.2351 - val_mean_iou: 0.8637 - val_dice_coef: 0.7649\n",
+      "\n",
+      "Epoch 00023: val_loss did not improve from 0.22408\n",
+      "Epoch 24/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0516 - mean_iou: 0.8644 - dice_coef: 0.9484 - val_loss: 0.2368 - val_mean_iou: 0.8649 - val_dice_coef: 0.7632\n",
+      "\n",
+      "Epoch 00024: val_loss did not improve from 0.22408\n",
+      "Epoch 25/10000\n",
+      "4082/4082 [==============================] - 705s 173ms/step - loss: 0.0510 - mean_iou: 0.8655 - dice_coef: 0.9490 - val_loss: 0.2353 - val_mean_iou: 0.8661 - val_dice_coef: 0.7647\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Epoch 00025: val_loss did not improve from 0.22408\n",
+      "Epoch 26/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0485 - mean_iou: 0.8667 - dice_coef: 0.9515 - val_loss: 0.2327 - val_mean_iou: 0.8672 - val_dice_coef: 0.7673\n",
+      "\n",
+      "Epoch 00026: val_loss did not improve from 0.22408\n",
+      "Epoch 27/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0475 - mean_iou: 0.8678 - dice_coef: 0.9525 - val_loss: 0.2368 - val_mean_iou: 0.8682 - val_dice_coef: 0.7632\n",
+      "\n",
+      "Epoch 00027: val_loss did not improve from 0.22408\n",
+      "\n",
+      "Epoch 00027: ReduceLROnPlateau reducing learning rate to 0.0001250000059371814.\n",
+      "Epoch 28/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0447 - mean_iou: 0.8688 - dice_coef: 0.9553 - val_loss: 0.2344 - val_mean_iou: 0.8693 - val_dice_coef: 0.7656\n",
+      "\n",
+      "Epoch 00028: val_loss did not improve from 0.22408\n",
+      "Epoch 29/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0437 - mean_iou: 0.8698 - dice_coef: 0.9563 - val_loss: 0.2325 - val_mean_iou: 0.8703 - val_dice_coef: 0.7675\n",
+      "\n",
+      "Epoch 00029: val_loss did not improve from 0.22408\n",
+      "Epoch 30/10000\n",
+      "4082/4082 [==============================] - 705s 173ms/step - loss: 0.0430 - mean_iou: 0.8708 - dice_coef: 0.9570 - val_loss: 0.2345 - val_mean_iou: 0.8712 - val_dice_coef: 0.7655\n",
+      "\n",
+      "Epoch 00030: val_loss did not improve from 0.22408\n",
+      "Epoch 31/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0422 - mean_iou: 0.8717 - dice_coef: 0.9578 - val_loss: 0.2383 - val_mean_iou: 0.8721 - val_dice_coef: 0.7617\n",
+      "\n",
+      "Epoch 00031: val_loss did not improve from 0.22408\n",
+      "Epoch 32/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0421 - mean_iou: 0.8725 - dice_coef: 0.9579 - val_loss: 0.2336 - val_mean_iou: 0.8729 - val_dice_coef: 0.7664\n",
+      "\n",
+      "Epoch 00032: val_loss did not improve from 0.22408\n",
+      "Epoch 33/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0415 - mean_iou: 0.8733 - dice_coef: 0.9585 - val_loss: 0.2378 - val_mean_iou: 0.8737 - val_dice_coef: 0.7622\n",
+      "\n",
+      "Epoch 00033: val_loss did not improve from 0.22408\n",
+      "\n",
+      "Epoch 00033: ReduceLROnPlateau reducing learning rate to 6.25000029685907e-05.\n",
+      "Epoch 34/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0402 - mean_iou: 0.8741 - dice_coef: 0.9598 - val_loss: 0.2364 - val_mean_iou: 0.8744 - val_dice_coef: 0.7636\n",
+      "\n",
+      "Epoch 00034: val_loss did not improve from 0.22408\n",
+      "Epoch 35/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0396 - mean_iou: 0.8749 - dice_coef: 0.9604 - val_loss: 0.2363 - val_mean_iou: 0.8752 - val_dice_coef: 0.7637\n",
+      "\n",
+      "Epoch 00035: val_loss did not improve from 0.22408\n",
+      "Epoch 36/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0395 - mean_iou: 0.8756 - dice_coef: 0.9605 - val_loss: 0.2357 - val_mean_iou: 0.8759 - val_dice_coef: 0.7643\n",
+      "\n",
+      "Epoch 00036: val_loss did not improve from 0.22408\n",
+      "Epoch 37/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0391 - mean_iou: 0.8763 - dice_coef: 0.9609 - val_loss: 0.2379 - val_mean_iou: 0.8766 - val_dice_coef: 0.7621\n",
+      "\n",
+      "Epoch 00037: val_loss did not improve from 0.22408\n",
+      "Epoch 38/10000\n",
+      "4082/4082 [==============================] - 705s 173ms/step - loss: 0.0391 - mean_iou: 0.8769 - dice_coef: 0.9609 - val_loss: 0.2384 - val_mean_iou: 0.8772 - val_dice_coef: 0.7616\n",
+      "\n",
+      "Epoch 00038: val_loss did not improve from 0.22408\n",
+      "Epoch 39/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0382 - mean_iou: 0.8775 - dice_coef: 0.9618 - val_loss: 0.2392 - val_mean_iou: 0.8778 - val_dice_coef: 0.7608\n",
+      "\n",
+      "Epoch 00039: val_loss did not improve from 0.22408\n",
+      "\n",
+      "Epoch 00039: ReduceLROnPlateau reducing learning rate to 3.125000148429535e-05.\n",
+      "Epoch 40/10000\n",
+      "4082/4082 [==============================] - 705s 173ms/step - loss: 0.0379 - mean_iou: 0.8781 - dice_coef: 0.9621 - val_loss: 0.2373 - val_mean_iou: 0.8784 - val_dice_coef: 0.7627\n",
+      "\n",
+      "Epoch 00040: val_loss did not improve from 0.22408\n",
+      "Epoch 41/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0373 - mean_iou: 0.8787 - dice_coef: 0.9627 - val_loss: 0.2385 - val_mean_iou: 0.8790 - val_dice_coef: 0.7615\n",
+      "\n",
+      "Epoch 00041: val_loss did not improve from 0.22408\n",
+      "Epoch 42/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0372 - mean_iou: 0.8793 - dice_coef: 0.9628 - val_loss: 0.2375 - val_mean_iou: 0.8795 - val_dice_coef: 0.7625\n",
+      "\n",
+      "Epoch 00042: val_loss did not improve from 0.22408\n",
+      "Epoch 43/10000\n",
+      "4082/4082 [==============================] - 705s 173ms/step - loss: 0.0371 - mean_iou: 0.8798 - dice_coef: 0.9629 - val_loss: 0.2390 - val_mean_iou: 0.8800 - val_dice_coef: 0.7610\n",
+      "\n",
+      "Epoch 00043: val_loss did not improve from 0.22408\n",
+      "Epoch 44/10000\n",
+      "4082/4082 [==============================] - 703s 172ms/step - loss: 0.0371 - mean_iou: 0.8803 - dice_coef: 0.9629 - val_loss: 0.2383 - val_mean_iou: 0.8806 - val_dice_coef: 0.7617\n",
+      "\n",
+      "Epoch 00044: val_loss did not improve from 0.22408\n",
+      "Epoch 45/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0368 - mean_iou: 0.8808 - dice_coef: 0.9632 - val_loss: 0.2388 - val_mean_iou: 0.8810 - val_dice_coef: 0.7612\n",
+      "\n",
+      "Epoch 00045: val_loss did not improve from 0.22408\n",
+      "\n",
+      "Epoch 00045: ReduceLROnPlateau reducing learning rate to 1.5625000742147677e-05.\n",
+      "Epoch 46/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0365 - mean_iou: 0.8813 - dice_coef: 0.9635 - val_loss: 0.2383 - val_mean_iou: 0.8815 - val_dice_coef: 0.7617\n",
+      "\n",
+      "Epoch 00046: val_loss did not improve from 0.22408\n",
+      "Epoch 47/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0367 - mean_iou: 0.8818 - dice_coef: 0.9633 - val_loss: 0.2396 - val_mean_iou: 0.8820 - val_dice_coef: 0.7604\n",
+      "\n",
+      "Epoch 00047: val_loss did not improve from 0.22408\n",
+      "Epoch 48/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0361 - mean_iou: 0.8822 - dice_coef: 0.9639 - val_loss: 0.2396 - val_mean_iou: 0.8824 - val_dice_coef: 0.7604\n",
+      "\n",
+      "Epoch 00048: val_loss did not improve from 0.22408\n",
+      "Epoch 49/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0367 - mean_iou: 0.8826 - dice_coef: 0.9633 - val_loss: 0.2387 - val_mean_iou: 0.8828 - val_dice_coef: 0.7613\n",
+      "\n",
+      "Epoch 00049: val_loss did not improve from 0.22408\n",
+      "Epoch 50/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0364 - mean_iou: 0.8830 - dice_coef: 0.9636 - val_loss: 0.2390 - val_mean_iou: 0.8832 - val_dice_coef: 0.7610\n",
+      "\n",
+      "Epoch 00050: val_loss did not improve from 0.22408\n",
+      "Epoch 51/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0364 - mean_iou: 0.8834 - dice_coef: 0.9636 - val_loss: 0.2395 - val_mean_iou: 0.8836 - val_dice_coef: 0.7605\n",
+      "\n",
+      "Epoch 00051: val_loss did not improve from 0.22408\n",
+      "\n",
+      "Epoch 00051: ReduceLROnPlateau reducing learning rate to 7.812500371073838e-06.\n",
+      "Epoch 52/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0359 - mean_iou: 0.8838 - dice_coef: 0.9641 - val_loss: 0.2394 - val_mean_iou: 0.8840 - val_dice_coef: 0.7606\n",
+      "\n",
+      "Epoch 00052: val_loss did not improve from 0.22408\n",
+      "Epoch 53/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0358 - mean_iou: 0.8842 - dice_coef: 0.9642 - val_loss: 0.2390 - val_mean_iou: 0.8843 - val_dice_coef: 0.7610\n",
+      "\n",
+      "Epoch 00053: val_loss did not improve from 0.22408\n",
+      "Epoch 54/10000\n",
+      "4082/4082 [==============================] - 705s 173ms/step - loss: 0.0354 - mean_iou: 0.8845 - dice_coef: 0.9646 - val_loss: 0.2390 - val_mean_iou: 0.8847 - val_dice_coef: 0.7610\n",
+      "\n",
+      "Epoch 00054: val_loss did not improve from 0.22408\n",
+      "Epoch 55/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0363 - mean_iou: 0.8849 - dice_coef: 0.9637 - val_loss: 0.2393 - val_mean_iou: 0.8850 - val_dice_coef: 0.7607\n",
+      "\n",
+      "Epoch 00055: val_loss did not improve from 0.22408\n",
+      "Epoch 56/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0360 - mean_iou: 0.8852 - dice_coef: 0.9640 - val_loss: 0.2397 - val_mean_iou: 0.8853 - val_dice_coef: 0.7603\n",
+      "\n",
+      "Epoch 00056: val_loss did not improve from 0.22408\n",
+      "Epoch 57/10000\n",
+      "4082/4082 [==============================] - 703s 172ms/step - loss: 0.0357 - mean_iou: 0.8855 - dice_coef: 0.9643 - val_loss: 0.2395 - val_mean_iou: 0.8857 - val_dice_coef: 0.7605\n",
+      "\n",
+      "Epoch 00057: val_loss did not improve from 0.22408\n",
+      "\n",
+      "Epoch 00057: ReduceLROnPlateau reducing learning rate to 3.906250185536919e-06.\n",
+      "Epoch 58/10000\n",
+      "4082/4082 [==============================] - 704s 172ms/step - loss: 0.0360 - mean_iou: 0.8858 - dice_coef: 0.9640 - val_loss: 0.2393 - val_mean_iou: 0.8860 - val_dice_coef: 0.7607\n",
+      "\n",
+      "Epoch 00058: val_loss did not improve from 0.22408\n",
+      "Epoch 59/10000\n",
+      "4082/4082 [==============================] - 704s 173ms/step - loss: 0.0353 - mean_iou: 0.8861 - dice_coef: 0.9647 - val_loss: 0.2392 - val_mean_iou: 0.8863 - val_dice_coef: 0.7608\n",
+      "\n",
+      "Epoch 00059: val_loss did not improve from 0.22408\n",
+      "Epoch 00059: early stopping\n"
+     ]
+    }
+   ],
+   "source": [
+    "x_train, y_train = load_image(conf, 'train')\n",
+    "print('x_train: {} | {} ~ {}'.format(x_train.shape, np.min(x_train), np.max(x_train)))\n",
+    "print('y_train: {} | {} ~ {}'.format(y_train.shape, np.min(y_train), np.max(y_train)))\n",
+    "\n",
+    "x_valid, y_valid = load_image(conf, 'valid')\n",
+    "print('x_valid: {} | {} ~ {}'.format(x_valid.shape, np.min(x_valid), np.max(x_valid)))\n",
+    "print('y_valid: {} | {} ~ {}'.format(y_valid.shape, np.min(y_valid), np.max(y_valid)))\n",
+    "\n",
+    "model = unet_model_3d((1,conf.input_rows,conf.input_cols,conf.input_deps), batch_normalization=True)\n",
+    "if conf.weights is not None:\n",
+    "    print(\"[INFO] Load pre-trained weights from {}\".format(conf.weights))\n",
+    "    model.load_weights(conf.weights)\n",
+    "model, callbacks = model_setup(model, conf, task=args.task)\n",
+    "\n",
+    "while conf.batch_size > 1:\n",
+    "    # To find a largest batch size that can be fit into GPU\n",
+    "    try:\n",
+    "        model.fit(x_train, y_train,\n",
+    "                  validation_data=(x_valid, y_valid),\n",
+    "                  batch_size=conf.batch_size,\n",
+    "                  epochs=conf.nb_epoch, \n",
+    "                  verbose=conf.verbose, \n",
+    "                  shuffle=True,\n",
+    "                  callbacks=callbacks)\n",
+    "        break\n",
+    "    except tf.errors.ResourceExhaustedError as e:\n",
+    "        conf.batch_size = int(conf.batch_size - 2)\n",
+    "        print(\"\\n> Batch size = {}\".format(conf.batch_size))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[INFO] Load trained model from models/ncs/run_1/Vnet-genesis.h5\n",
+      "x_test: (852, 1, 64, 64, 32) | 0.0 ~ 1.0\n",
+      "y_test: (852, 1, 64, 64, 32) | 0 ~ 1\n",
+      "852/852 [==============================] - 36s 42ms/step\n",
+      "852/852 [==============================] - 40s 47ms/step\n",
+      "[INFO] Vnet-genesis\n",
+      "x:  (852, 1, 64, 64, 32) | 0.0 ~ 1.0\n",
+      "y:  (852, 1, 64, 64, 32) | 0.0 ~ 1.0\n",
+      "p:  (852, 1, 64, 64, 32) | 0.0 ~ 1.0\n",
+      "[INFO] Dice = 74.39%\n",
+      "[INFO] IoU  = 59.22%\n",
+      "[EVAL] Dice = 75.38%\n",
+      "[EVAL] IoU  = 77.14%\n"
+     ]
+    }
+   ],
+   "source": [
+    "model = unet_model_3d((1,conf.input_rows,conf.input_cols,conf.input_deps), batch_normalization=True)\n",
+    "print(\"[INFO] Load trained model from {}\".format( os.path.join(conf.model_path, conf.exp_name+\".h5\") ))\n",
+    "model.load_weights( os.path.join(conf.model_path, conf.exp_name+\".h5\") )\n",
+    "\n",
+    "x_test, y_test = load_image(conf, 'test')\n",
+    "print('x_test: {} | {} ~ {}'.format(x_test.shape, np.min(x_test), np.max(x_test)))\n",
+    "print('y_test: {} | {} ~ {}'.format(y_test.shape, np.min(y_test), np.max(y_test)))\n",
+    "\n",
+    "_ = segmentation_model_evaluation(model=model, config=conf, x=x_test, y=y_test, note=conf.exp_name)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/keras/downstream_tasks/ncs_data.py b/keras/downstream_tasks/ncs_data.py
new file mode 100755
index 0000000..352dc4a
--- /dev/null
+++ b/keras/downstream_tasks/ncs_data.py
@@ -0,0 +1,32 @@
+import os
+import random
+import copy
+import keras
+import shutil
+import numpy as np
+from tqdm import tqdm
+from glob import glob
+from skimage.transform import resize
+
+def load_image(config, status=None):
+    
+    x = np.squeeze(np.load(os.path.join(config.data, 'x_'+status+'_64x64x32.npy')))
+    y = np.squeeze(np.load(os.path.join(config.data, 'm_'+status+'_64x64x32.npy')))
+    x = np.expand_dims(x, axis=1)
+    y = np.expand_dims(y, axis=1)
+
+    return x, y
+
+if __name__ == "__main__":
+    from config import *
+
+    class set_args():
+        apps = 'ncs'
+        task = 'segmentation'
+        suffix = 'random'
+    args = set_args()
+
+    conf = ncs_config(args)
+    x_valid, y_valid = load_image(conf, 'valid')
+    print(x_valid.shape, np.min(x_valid), np.max(x_valid))
+    print(y_valid.shape, np.min(y_valid), np.max(y_valid))
\ No newline at end of file
diff --git a/keras/downstream_tasks/unet3d.py b/keras/downstream_tasks/unet3d.py
new file mode 100755
index 0000000..f9076a9
--- /dev/null
+++ b/keras/downstream_tasks/unet3d.py
@@ -0,0 +1,123 @@
+import numpy as np
+from keras import backend as K
+from keras.engine import Input, Model
+from keras.layers import Conv3D, MaxPooling3D, UpSampling3D, Activation, BatchNormalization, PReLU, Deconvolution3D
+from keras.optimizers import Adam
+K.set_image_data_format("channels_first")
+
+try:
+    from keras.engine import merge
+except ImportError:
+    from keras.layers.merge import concatenate
+
+
+def unet_model_3d(input_shape, pool_size=(2, 2, 2), n_labels=1, deconvolution=False,
+                  depth=4, n_base_filters=32, batch_normalization=False, activation_name="sigmoid"):
+    """
+    Builds the 3D UNet Keras model.f
+    :param metrics: List metrics to be calculated during model training (default is dice coefficient).
+    :param include_label_wise_dice_coefficients: If True and n_labels is greater than 1, model will report the dice
+    coefficient for each label as metric.
+    :param n_base_filters: The number of filters that the first layer in the convolution network will have. Following
+    layers will contain a multiple of this number. Lowering this number will likely reduce the amount of memory required
+    to train the model.
+    :param depth: indicates the depth of the U-shape for the model. The greater the depth, the more max pooling
+    layers will be added to the model. Lowering the depth may reduce the amount of memory required for training.
+    :param input_shape: Shape of the input data (n_chanels, x_size, y_size, z_size). The x, y, and z sizes must be
+    divisible by the pool size to the power of the depth of the UNet, that is pool_size^depth.
+    :param pool_size: Pool size for the max pooling operations.
+    :param n_labels: Number of binary labels that the model is learning.
+    :param initial_learning_rate: Initial learning rate for the model. This will be decayed during training.
+    :param deconvolution: If set to True, will use transpose convolution(deconvolution) instead of up-sampling. This
+    increases the amount memory required during training.
+    :return: Untrained 3D UNet Model
+    """
+    inputs = Input(input_shape)
+    current_layer = inputs
+    levels = list()
+    num_layer = 0
+
+    # add levels with max pooling
+    for layer_depth in range(depth):
+        layer1 = create_convolution_block(input_layer=current_layer, n_filters=n_base_filters*(2**layer_depth),
+                                          batch_normalization=batch_normalization, layer_depth=num_layer)
+        num_layer += 1
+        layer2 = create_convolution_block(input_layer=layer1, n_filters=n_base_filters*(2**layer_depth)*2,
+                                          batch_normalization=batch_normalization, layer_depth=num_layer)
+        num_layer += 1
+        if layer_depth < depth - 1:
+            current_layer = MaxPooling3D(pool_size=pool_size)(layer2)
+            levels.append([layer1, layer2, current_layer])
+        else:
+            current_layer = layer2
+            levels.append([layer1, layer2])
+
+    # add levels with up-convolution or up-sampling
+    for layer_depth in range(depth-2, -1, -1):
+        up_convolution = get_up_convolution(pool_size=pool_size, deconvolution=deconvolution,
+                                            n_filters=current_layer._keras_shape[1])(current_layer)
+        concat = concatenate([up_convolution, levels[layer_depth][1]], axis=1)
+        current_layer = create_convolution_block(n_filters=levels[layer_depth][1]._keras_shape[1], layer_depth=num_layer,
+                                                 input_layer=concat, batch_normalization=batch_normalization)
+        num_layer += 1
+        current_layer = create_convolution_block(n_filters=levels[layer_depth][1]._keras_shape[1], layer_depth=num_layer,
+                                                 input_layer=current_layer,
+                                                 batch_normalization=batch_normalization)
+        num_layer += 1
+
+    final_convolution = Conv3D(n_labels, (1, 1, 1))(current_layer)
+    act = Activation(activation_name)(final_convolution)
+    model = Model(inputs=inputs, outputs=act)
+
+    return model
+
+def create_convolution_block(input_layer, n_filters, batch_normalization=False, kernel=(3, 3, 3), activation=None,
+                             padding='same', strides=(1, 1, 1), instance_normalization=False, layer_depth=None):
+    """
+
+    :param strides:
+    :param input_layer:
+    :param n_filters:
+    :param batch_normalization:
+    :param kernel:
+    :param activation: Keras activation layer to use. (default is 'relu')
+    :param padding:
+    :return:
+    """
+    layer = Conv3D(n_filters, kernel, padding=padding, strides=strides, name="depth_"+str(layer_depth)+"_conv")(input_layer)
+    if batch_normalization:
+        layer = BatchNormalization(axis=1, name="depth_"+str(layer_depth)+"_bn")(layer)
+    elif instance_normalization:
+        try:
+            from keras_contrib.layers.normalization.instancenormalization import InstanceNormalization
+        except ImportError:
+            raise ImportError("Install keras_contrib in order to use instance normalization."
+                              "\nTry: pip install git+https://www.github.com/farizrahman4u/keras-contrib.git")
+        layer = InstanceNormalization(axis=1, name="depth_"+str(layer_depth)+"_in")(layer)
+    if activation is None:
+        return Activation('relu', name="depth_"+str(layer_depth)+"_relu")(layer)
+    else:
+        return activation()(layer)
+
+
+def compute_level_output_shape(n_filters, depth, pool_size, image_shape):
+    """
+    Each level has a particular output shape based on the number of filters used in that level and the depth or number 
+    of max pooling operations that have been done on the data at that point.
+    :param image_shape: shape of the 3d image.
+    :param pool_size: the pool_size parameter used in the max pooling operation.
+    :param n_filters: Number of filters used by the last node in a given level.
+    :param depth: The number of levels down in the U-shaped model a given node is.
+    :return: 5D vector of the shape of the output node 
+    """
+    output_image_shape = np.asarray(np.divide(image_shape, np.power(pool_size, depth)), dtype=np.int32).tolist()
+    return tuple([None, n_filters] + output_image_shape)
+
+
+def get_up_convolution(n_filters, pool_size, kernel_size=(2, 2, 2), strides=(2, 2, 2),
+                       deconvolution=False):
+    if deconvolution:
+        return Deconvolution3D(filters=n_filters, kernel_size=kernel_size,
+                               strides=strides)
+    else:
+        return UpSampling3D(size=pool_size)
diff --git a/keras/downstream_tasks/utils.py b/keras/downstream_tasks/utils.py
new file mode 100755
index 0000000..f678ac7
--- /dev/null
+++ b/keras/downstream_tasks/utils.py
@@ -0,0 +1,289 @@
+import os
+import random
+import copy
+import keras
+import shutil
+import math
+import numpy as np
+import tensorflow as tf
+import matplotlib.pyplot as plt
+from tqdm import tqdm
+from keras import backend as K
+from sklearn import metrics
+from skimage.transform import resize
+from keras.callbacks import LambdaCallback,TensorBoard,ReduceLROnPlateau
+
+def augment_rician_noise(data_sample, noise_variance=(0, 0.1)):
+    variance = random.uniform(noise_variance[0], noise_variance[1])
+    data_sample = np.sqrt(
+        (data_sample + np.random.normal(0.0, variance, size=data_sample.shape)) ** 2 +
+        np.random.normal(0.0, variance, size=data_sample.shape) ** 2)
+    return data_sample
+
+def augment_gaussian_noise(data_sample, noise_variance=(0, 0.1)):
+    if noise_variance[0] == noise_variance[1]:
+        variance = noise_variance[0]
+    else:
+        variance = random.uniform(noise_variance[0], noise_variance[1])
+    data_sample = data_sample + np.random.normal(0.0, variance, size=data_sample.shape)
+    return data_sample
+
+######
+# Module: Evaluation metric
+######
+def mean_iou(y_true, y_pred):
+    prec = []
+    for t in np.arange(0.5, 1.0, 0.05):
+        y_pred_ = tf.to_int32(y_pred > t)
+        score, up_opt = tf.metrics.mean_iou(y_true, y_pred_, 2)
+        K.get_session().run(tf.local_variables_initializer())
+        with tf.control_dependencies([up_opt]):
+            score = tf.identity(score)
+        prec.append(score)
+    return K.mean(K.stack(prec), axis=0)
+
+def dice_coef(y_true, y_pred, smooth=1.):
+    y_true_f = K.flatten(y_true)
+    y_pred_f = K.flatten(y_pred)
+    intersection = K.sum(y_true_f * y_pred_f)
+    return (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)
+
+def dice_coef_loss(y_true, y_pred):
+    return 1. - dice_coef(y_true, y_pred)
+
+def bce_dice_loss(y_true, y_pred):
+    return 0.5 * keras.losses.binary_crossentropy(y_true, y_pred) - dice_coef(y_true, y_pred)
+
+def iou(im1, im2):
+    overlap = (im1>0.5) * (im2>0.5)
+    union = (im1>0.5) + (im2>0.5)
+    return overlap.sum()/float(union.sum())
+        
+def dice(im1, im2, empty_score=1.0):
+    im1 = np.asarray(im1>0.5).astype(np.bool)
+    im2 = np.asarray(im2>0.5).astype(np.bool)
+
+    if im1.shape != im2.shape:
+        raise ValueError("Shape mismatch: im1 and im2 must have the same shape.")
+
+    im_sum = im1.sum() + im2.sum()
+    if im_sum == 0:
+        return empty_score
+
+    intersection = np.logical_and(im1, im2)
+
+    return 2. * intersection.sum() / im_sum
+
+
+
+######
+# Module: model setup
+######
+def classification_model_compile(model, config):
+    if config.num_classes <= 2:
+        model.compile(optimizer=config.optimizer, 
+                      loss="binary_crossentropy", 
+                      metrics=['accuracy','binary_crossentropy'],
+                 )
+    else:
+        model.compile(optimizer=config.optimizer, 
+                      loss="categorical_crossentropy", 
+                      metrics=['categorical_accuracy','categorical_crossentropy'],
+                 )
+    return model
+
+def segmentation_model_compile(model, config):
+    model.compile(optimizer=config.optimizer, 
+                  loss=dice_coef_loss, 
+                  metrics=[mean_iou, 
+                           dice_coef],
+                 )
+    return model
+    
+def model_setup(model, config, task=None):
+    if task == 'segmentation':
+        model = segmentation_model_compile(model, config)
+    elif task == 'classification':
+        model = classification_model_compile(model, config)
+    else:
+        raise
+
+    if os.path.exists(os.path.join(config.model_path, config.exp_name+".txt")):
+        os.remove(os.path.join(config.model_path, config.exp_name+".txt"))
+    with open(os.path.join(config.model_path, config.exp_name+".txt"),'w') as fh:
+        model.summary(print_fn=lambda x: fh.write(x + '\n'))
+
+    shutil.rmtree(os.path.join(config.logs_path, config.exp_name), ignore_errors=True)
+    if not os.path.exists(os.path.join(config.logs_path, config.exp_name)):
+        os.makedirs(os.path.join(config.logs_path, config.exp_name))
+    tbCallBack = TensorBoard(log_dir=os.path.join(config.logs_path, config.exp_name),
+                             histogram_freq=0,
+                             write_graph=True, 
+                             write_images=True,
+                            )
+    tbCallBack.set_model(model)
+
+    early_stopping = keras.callbacks.EarlyStopping(monitor='val_loss', 
+                                                   patience=config.patience, 
+                                                   verbose=config.verbose,
+                                                   mode='min',
+                                                  )
+    check_point = keras.callbacks.ModelCheckpoint(os.path.join(config.model_path, config.exp_name+".h5"),
+                                                  monitor='val_loss', 
+                                                  verbose=config.verbose, 
+                                                  save_best_only=True, 
+                                                  mode='min',
+                                                 )
+    lrate_scheduler = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=6,
+                                        min_delta=0.0001, min_lr=1e-6, verbose=1)
+    callbacks = [check_point, early_stopping, tbCallBack, lrate_scheduler]
+    return model, callbacks
+
+def classification_model_evaluation(model, config, x, y, note=None):
+    model = classification_model_compile(model, config)
+    p = model.predict(x, verbose=config.verbose, batch_size=config.batch_size)
+    if note is not None:
+        print("[INFO] {}".format(note))
+    print("x:  {} | {:.1f} ~ {:.1f}".format(x.shape, np.min(x), np.max(x)))
+    print("y:  {} | {:.1f} ~ {:.1f}".format(y.shape, np.min(y), np.max(y)))
+    print("p:  {} | {:.1f} ~ {:.1f}".format(p.shape, np.min(p), np.max(p)))
+    
+    fpr, tpr, thresholds = metrics.roc_curve(y, p, pos_label=1)
+    
+    print("[EVAL] AUC = {:.2f}%".format(100.0 * metrics.auc(fpr, tpr)))
+    
+    return p
+
+def segmentation_model_evaluation(model, config, x, y, note=None):
+    model.compile(optimizer=config.optimizer, 
+                  loss=dice_coef_loss, 
+                  metrics=[mean_iou, 
+                           dice_coef],
+                 )
+    p = model.predict(x, verbose=config.verbose, batch_size=config.batch_size)
+    eva = model.evaluate(x, y, verbose=config.verbose, batch_size=config.batch_size)
+    if note is not None:
+        print("[INFO] {}".format(note))
+    print("x:  {} | {:.1f} ~ {:.1f}".format(x.shape, np.min(x), np.max(x)))
+    print("y:  {} | {:.1f} ~ {:.1f}".format(y.shape, np.min(y), np.max(y)))
+    print("p:  {} | {:.1f} ~ {:.1f}".format(p.shape, np.min(p), np.max(p)))
+    print("[BIN]  Dice = {:.2f}%".format(100.0 * dice(p, y)))
+    print("[BIN]  IoU  = {:.2f}%".format(100.0 * iou(p, y)))
+    print("[EVAL] Dice = {:.2f}%".format(100.0 * eva[-1]))
+    print("[EVAL] IoU  = {:.2f}%".format(100.0 * eva[-2]))
+    
+    return p
+
+def plot_image_truth_prediction(x, y, p):
+    x, y, p = np.squeeze(x), np.squeeze(y), np.squeeze(p>0.5)
+    rows, cols = 12, 12
+    plt.rcParams.update({'font.size': 30})
+    plt.figure(figsize=(25*3, 25))
+
+    large_image = np.zeros((rows*x.shape[0], cols*x.shape[1]))
+    for b in range(rows*cols):
+        large_image[(b//rows)*x.shape[0]:(b//rows+1)*x.shape[0], 
+                    (b%cols)*x.shape[1]:(b%cols+1)*x.shape[1]] = np.transpose(np.squeeze(x[:, :, b]))
+    plt.subplot(1, 3, 1)
+    plt.imshow(large_image, cmap='gray', vmin=0, vmax=1); plt.axis('off')
+    
+    large_image = np.zeros((rows*x.shape[0], cols*x.shape[1]))
+    for b in range(rows*cols):
+        large_image[(b//rows)*y.shape[0]:(b//rows+1)*y.shape[0], 
+                    (b%cols)*y.shape[1]:(b%cols+1)*y.shape[1]] = np.transpose(np.squeeze(y[:, :, b]))
+    plt.subplot(1, 3, 2)
+    plt.imshow(large_image, cmap='gray', vmin=0, vmax=1); plt.axis('off')
+    
+    large_image = np.zeros((rows*p.shape[0], cols*p.shape[1]))
+    for b in range(rows*cols):
+        large_image[(b//rows)*p.shape[0]:(b//rows+1)*p.shape[0], 
+                    (b%cols)*p.shape[1]:(b%cols+1)*p.shape[1]] = np.transpose(np.squeeze(p[:, :, b]))
+    plt.subplot(1, 3, 3)
+    plt.imshow(large_image, cmap='gray', vmin=0, vmax=1); plt.axis('off')
+    
+    plt.show()
+
+def predict_on_test_image(x, model, config):
+    rows, cols, deps = x.shape[0], x.shape[1], x.shape[2]
+    _resize = False
+    
+    p = np.zeros((rows, cols, deps), dtype='float')
+    n = np.ones((rows, cols, deps), dtype='float')
+    
+    nb_rows = int( math.floor( (rows-config.crop_rows) / config.step_pixel_size) ) + 1
+    nb_cols = int( math.floor( (cols-config.crop_cols) / config.step_pixel_size) ) + 1
+    nb_deps = int( math.floor( (deps-config.crop_deps) / config.step_pixel_size) ) + 1
+    row_list = [x*config.step_pixel_size for x in range(nb_rows)]
+    col_list = [x*config.step_pixel_size for x in range(nb_cols)]
+    dep_list = [x*config.step_pixel_size for x in range(nb_deps)]
+    
+    for i in row_list:
+        for j in col_list:
+            for k in dep_list:
+                im = x[i:i+config.crop_rows, j:j+config.crop_cols, k:k+config.crop_deps]
+                im = resize(im, (config.input_rows, config.input_cols, config.input_deps), preserve_range=True)
+                im = np.expand_dims(np.expand_dims(im, axis=0), axis=0)
+                pr = np.squeeze(model.predict(im, verbose=0))
+                pr = resize(pr, (config.crop_rows, config.crop_cols, config.crop_deps), preserve_range=True)
+                p[i:i+config.crop_rows, j:j+config.crop_cols, k:k+config.crop_deps] += pr
+                n[i:i+config.crop_rows, j:j+config.crop_cols, k:k+config.crop_deps] += 1
+
+            im = x[i:i+config.crop_rows, j:j+config.crop_cols, deps-config.crop_deps:deps]
+            im = resize(im, (config.input_rows, config.input_cols, config.input_deps), preserve_range=True)
+            im = np.expand_dims(np.expand_dims(im, axis=0), axis=0)
+            pr = np.squeeze(model.predict(im, verbose=0))
+            pr = resize(pr, (config.crop_rows, config.crop_cols, config.crop_deps), preserve_range=True)
+            p[i:i+config.crop_rows, j:j+config.crop_cols, deps-config.crop_deps:deps] += pr
+            n[i:i+config.crop_rows, j:j+config.crop_cols, deps-config.crop_deps:deps] += 1
+            
+        im = x[i:i+config.crop_rows, cols-config.crop_cols:cols, deps-config.crop_deps:deps]
+        im = resize(im, (config.input_rows, config.input_cols, config.input_deps), preserve_range=True)
+        im = np.expand_dims(np.expand_dims(im, axis=0), axis=0)
+        pr = np.squeeze(model.predict(im, verbose=0))
+        pr = resize(pr, (config.crop_rows, config.crop_cols, config.crop_deps), preserve_range=True)
+        p[i:i+config.crop_rows, cols-config.crop_cols:cols, deps-config.crop_deps:deps] += pr
+        n[i:i+config.crop_rows, cols-config.crop_cols:cols, deps-config.crop_deps:deps] += 1
+
+    im = x[rows-config.crop_rows:rows, cols-config.crop_cols:cols, deps-config.crop_deps:deps]
+    im = resize(im, (config.input_rows, config.input_cols, config.input_deps), preserve_range=True)
+    im = np.expand_dims(np.expand_dims(im, axis=0), axis=0)
+    pr = np.squeeze(model.predict(im, verbose=0))
+    pr = resize(pr, (config.crop_rows, config.crop_cols, config.crop_deps), preserve_range=True)
+    p[rows-config.crop_rows:rows, cols-config.crop_cols:cols, deps-config.crop_deps:deps] += pr
+    n[rows-config.crop_rows:rows, cols-config.crop_cols:cols, deps-config.crop_deps:deps] += 1
+    
+    p = 1.0 * p / n
+    
+    return p
+
+######
+# Module: Visualization
+######
+def plot_case(case_id=None, mris=None, segs=None, rows=10, cols=10, increment=38):
+    assert case_id is not None
+    assert mris is not None
+    assert segs is not None
+    font = {'family' : 'times',
+            'weight' : 'bold',
+            'size'   : 22}
+    plt.rc('font', **font)
+    
+    print("\n\n[INFO] case id {}".format(case_id))
+    
+    # plot the patient MRI
+    plt.figure(figsize=(cols*1, rows*1))
+    plt.subplots_adjust(wspace=0.01, hspace=0.1)
+    for i in range(rows*cols):
+        plt.subplot(rows, cols, i+1)
+        plt.imshow(np.transpose(mris[case_id, 0, :, :, i+increment]), cmap="gray", vmin=0, vmax=1)
+        plt.axis('off')
+    plt.show()
+
+    # plot the segmentation mask
+    plt.figure(figsize=(cols*1, rows*1))
+    plt.subplots_adjust(wspace=0.01, hspace=0.1)
+    for i in range(rows*cols):
+        plt.subplot(rows, cols, i+1)
+        plt.imshow(np.transpose(segs[case_id, 0, :, :, i+increment]), cmap="gray", vmin=0, vmax=1)
+        plt.axis('off')
+    plt.show()
\ No newline at end of file