cli

Former-commit-id: c3687684a19c18309f97b69f8161af7a31fe0fb8 [formerly b68719d5e14a54377fafbea9f2c7c9b996bea583]
Former-commit-id: f17d9cbb79833f56450e0518d978603997037e94

fawkes/__init__.py

@@ -0,0 +1,24 @@
+# -*- coding: utf-8 -*-
+# @Date    : 2020-07-01
+# @Author  : Shawn Shan (shansixiong@cs.uchicago.edu)
+# @Link    : https://www.shawnshan.com/
+
+
+__version__ = '0.0.2'
+
+from .differentiator import FawkesMaskGeneration
+from .utils import load_extractor, init_gpu, select_target_label, dump_image, reverse_process_cloaked, \
+    Faces
+from .protection import main
+import logging
+import sys
+import os
+logging.getLogger('tensorflow').disabled = True
+
+
+__all__ = (
+    '__version__',
+    'FawkesMaskGeneration', 'load_extractor',
+    'init_gpu',
+    'select_target_label', 'dump_image', 'reverse_process_cloaked', 'Faces', 'main'
+)

fawkes/__main__.py

@@ -0,0 +1,4 @@
+from .protection import main
+
+if __name__ == '__main__':
+    main()

fawkes/align_face.py

@@ -1,6 +1,5 @@
-import detect_face
+from .detect_face import detect_face, create_mtcnn
 import numpy as np
-import tensorflow as tf
 
 # modify the default parameters of np.load
 np_load_old = np.load
@@ -15,7 +14,7 @@ def to_rgb(img):
 
 
 def aligner(sess):
-    pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
+    pnet, rnet, onet = create_mtcnn(sess, None)
     return [pnet, rnet, onet]
 
 
@@ -31,7 +30,7 @@ def align(orig_img, aligner, margin=0.8, detect_multiple_faces=True):
         orig_img = to_rgb(orig_img)
     orig_img = orig_img[:, :, 0:3]
 
-    bounding_boxes, _ = detect_face.detect_face(orig_img, minsize, pnet, rnet, onet, threshold, factor)
+    bounding_boxes, _ = detect_face(orig_img, minsize, pnet, rnet, onet, threshold, factor)
     nrof_faces = bounding_boxes.shape[0]
     if nrof_faces > 0:
         det = bounding_boxes[:, 0:4]

fawkes/detect_face.py

@@ -29,7 +29,6 @@ from __future__ import print_function
 
 import os
 
-# from math import floor
 import cv2
 import numpy as np
 import tensorflow as tf

fawkes/differentiator.py

@@ -10,7 +10,7 @@ from decimal import Decimal
 
 import numpy as np
 import tensorflow as tf
-from utils import preprocess, reverse_preprocess
+from .utils import preprocess, reverse_preprocess
 
 
 class FawkesMaskGeneration:

fawkes/protection.py

@@ -1,3 +1,7 @@
+# from __future__ import absolute_import
+# from __future__ import division
+# from __future__ import print_function
+
 import argparse
 import glob
 import os
@@ -5,26 +9,28 @@ import random
 import sys
 
 import numpy as np
-from differentiator import FawkesMaskGeneration
-from utils import load_extractor, init_gpu, select_target_label, dump_image, reverse_process_cloaked, \
+
+from .differentiator import FawkesMaskGeneration
+from .utils import load_extractor, init_gpu, select_target_label, dump_image, reverse_process_cloaked, \
     Faces
 
 random.seed(12243)
 np.random.seed(122412)
 
-BATCH_SIZE = 10
+BATCH_SIZE = 32
 
 
-def generate_cloak_images(sess, feature_extractors, image_X, target_emb=None, th=0.01, faces=None):
+def generate_cloak_images(sess, feature_extractors, image_X, target_emb=None, th=0.01, faces=None, sd=1e9, lr=2,
+                          max_step=500):
     batch_size = BATCH_SIZE if len(image_X) > BATCH_SIZE else len(image_X)
 
     differentiator = FawkesMaskGeneration(sess, feature_extractors,
                                           batch_size=batch_size,
                                           mimic_img=True,
                                           intensity_range='imagenet',
-                                          initial_const=args.sd,
-                                          learning_rate=args.lr,
-                                          max_iterations=args.max_step,
+                                          initial_const=sd,
+                                          learning_rate=lr,
+                                          max_iterations=max_step,
                                           l_threshold=th,
                                           verbose=1, maximize=False, keep_final=False, image_shape=image_X.shape[1:],
                                           faces=faces)
@@ -33,26 +39,6 @@ def generate_cloak_images(sess, feature_extractors, image_X, target_emb=None, th
     return cloaked_image_X
 
 
-def get_mode_config(mode):
-    if mode == 'low':
-        args.feature_extractor = "low_extract"
-        # args.th = 0.003
-        args.th = 0.001
-    elif mode == 'mid':
-        args.feature_extractor = "mid_extract"
-        args.th = 0.004
-    elif mode == 'high':
-        args.feature_extractor = "high_extract"
-        args.th = 0.004
-    elif mode == 'ultra':
-        args.feature_extractor = "high_extract"
-        args.th = 0.03
-    elif mode == 'custom':
-        pass
-    else:
-        raise Exception("mode must be one of 'low', 'mid', 'high', 'ultra', 'custom'")
-
-
 def check_imgs(imgs):
     if np.max(imgs) <= 1 and np.min(imgs) >= 0:
         imgs = imgs * 255.0
@@ -63,20 +49,72 @@ def check_imgs(imgs):
     return imgs
 
 
-def fawkes():
+def main(*argv):
+    if not argv:
+        argv = list(sys.argv)
+
+    # attach SIGPIPE handler to properly handle broken pipe
+    try:  # sigpipe not available under windows. just ignore in this case
+        import signal
+        signal.signal(signal.SIGPIPE, signal.SIG_DFL)
+    except Exception as e:
+        pass
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--directory', '-d', type=str,
+                        help='directory that contain images for cloaking', default='imgs/')
+
+    parser.add_argument('--gpu', type=str,
+                        help='GPU id', default='0')
+
+    parser.add_argument('--mode', type=str,
+                        help='cloak generation mode', default='high')
+    parser.add_argument('--feature-extractor', type=str,
+                        help="name of the feature extractor used for optimization",
+                        default="high_extract")
+
+    parser.add_argument('--th', type=float, default=0.01)
+    parser.add_argument('--max-step', type=int, default=500)
+    parser.add_argument('--sd', type=int, default=1e9)
+    parser.add_argument('--lr', type=float, default=2)
+
+    parser.add_argument('--separate_target', action='store_true')
+
+    parser.add_argument('--format', type=str,
+                        help="final image format",
+                        default="jpg")
+    args = parser.parse_args(argv[1:])
+
+    if args.mode == 'low':
+        args.feature_extractor = "high_extract"
+        args.th = 0.003
+    elif args.mode == 'mid':
+        args.feature_extractor = "high_extract"
+        args.th = 0.005
+    elif args.mode == 'high':
+        args.feature_extractor = "high_extract"
+        args.th = 0.007
+    elif args.mode == 'ultra':
+        args.feature_extractor = "high_extract"
+        args.th = 0.01
+    elif args.mode == 'custom':
+        pass
+    else:
+        raise Exception("mode must be one of 'low', 'mid', 'high', 'ultra', 'custom'")
+
     assert args.format in ['png', 'jpg', 'jpeg']
     if args.format == 'jpg':
         args.format = 'jpeg'
-    get_mode_config(args.mode)
 
     sess = init_gpu(args.gpu)
-    # feature_extractors_ls = [load_extractor(args.feature_extractor)]
-    # fs_names = ['mid_extract', 'high_extract']
     fs_names = [args.feature_extractor]
     feature_extractors_ls = [load_extractor(name) for name in fs_names]
 
     image_paths = glob.glob(os.path.join(args.directory, "*"))
     image_paths = [path for path in image_paths if "_cloaked" not in path.split("/")[-1]]
+    if not image_paths:
+        print("No images in the directory")
+        exit(1)
 
     faces = Faces(image_paths, sess)
 
@@ -94,7 +132,8 @@ def fawkes():
         target_embedding = select_target_label(orginal_images, feature_extractors_ls, fs_names)
 
     protected_images = generate_cloak_images(sess, feature_extractors_ls, orginal_images,
-                                             target_emb=target_embedding, th=args.th, faces=faces)
+                                             target_emb=target_embedding, th=args.th, faces=faces, sd=args.sd,
+                                             lr=args.lr, max_step=args.max_step)
 
     faces.cloaked_cropped_faces = protected_images
 
@@ -102,42 +141,9 @@ def fawkes():
     final_images = faces.merge_faces(cloak_perturbation)
 
     for p_img, cloaked_img, path in zip(final_images, protected_images, image_paths):
-        file_name = "{}_{}_{}_{}_cloaked.{}".format(".".join(path.split(".")[:-1]), args.mode, args.th,
-                                                     args.feature_extractor, args.format)
+        file_name = "{}_{}_{}_cloaked.{}".format(".".join(path.split(".")[:-1]), args.mode, args.th, args.format)
         dump_image(p_img, file_name, format=args.format)
-        #
-        # file_name = "{}_{}_{}_{}_cloaked_cropped.png".format(".".join(path.split(".")[:-1]), args.mode, args.th,
-        #                                                      args.feature_extractor)
-        # dump_image(reverse_process_cloaked(cloaked_img), file_name, format="png")
-
-
-def parse_arguments(argv):
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--directory', '-d', type=str,
-                        help='directory that contain images for cloaking', default='imgs/')
-
-    parser.add_argument('--gpu', type=str,
-                        help='GPU id', default='0')
-
-    parser.add_argument('--mode', type=str,
-                        help='cloak generation mode', default='high')
-    parser.add_argument('--feature-extractor', type=str,
-                        help="name of the feature extractor used for optimization",
-                        default="high_extract")
-
-    parser.add_argument('--th', type=float, default=0.01)
-    parser.add_argument('--max-step', type=int, default=200)
-    parser.add_argument('--sd', type=int, default=1e9)
-    parser.add_argument('--lr', type=float, default=10)
-
-    parser.add_argument('--separate_target', action='store_true')
-
-    parser.add_argument('--format', type=str,
-                        help="final image format",
-                        default="jpg")
-    return parser.parse_args(argv)
 
 
 if __name__ == '__main__':
-    args = parse_arguments(sys.argv[1:])
-    fawkes()
+    main(*sys.argv)

fawkes/utils.py

@@ -4,21 +4,26 @@ import json
 import os
 import pickle
 import random
+import sys
 
+stderr = sys.stderr
+sys.stderr = open(os.devnull, 'w')
 import keras
+
+sys.stderr = stderr
 import keras.backend as K
 import numpy as np
 import tensorflow as tf
-from align_face import align, aligner
-from keras.applications.vgg16 import preprocess_input
+from PIL import Image, ExifTags
+# from keras.applications.vgg16 import preprocess_input
 from keras.layers import Dense, Activation
 from keras.models import Model
 from keras.preprocessing import image
 from keras.utils import get_file
-from keras.utils import to_categorical
 from skimage.transform import resize
 from sklearn.metrics import pairwise_distances
-from PIL import Image, ExifTags
+
+from .align_face import align, aligner
 
 
 def clip_img(X, preprocessing='raw'):
@@ -81,7 +86,14 @@ class Faces(object):
             self.cropped_index.extend(cur_index)
             self.callback_idx.extend([i] * len(cur_faces_square))
 
-        self.cropped_faces = preprocess_input(np.array(self.cropped_faces))
+        if not self.cropped_faces:
+            print("No faces detected")
+            exit(1)
+
+        self.cropped_faces = np.array(self.cropped_faces)
+
+        self.cropped_faces = preprocess(self.cropped_faces, 'imagenet')
+
         self.cloaked_cropped_faces = None
         self.cloaked_faces = np.copy(self.org_faces)
 
@@ -89,8 +101,6 @@ class Faces(object):
         return self.cropped_faces
 
     def merge_faces(self, cloaks):
-        # import pdb
-        # pdb.set_trace()
 
         self.cloaked_faces = np.copy(self.org_faces)
 
@@ -300,7 +310,6 @@ def load_extractor(name):
     return model
 
 
-
 def get_dataset_path(dataset):
     model_dir = os.path.join(os.path.expanduser('~'), '.fawkes')
     if not os.path.exists(os.path.join(model_dir, "config.json")):
@@ -335,7 +344,7 @@ def load_dir(path):
         im = image.img_to_array(im)
         x_ls.append(im)
     raw_x = np.array(x_ls)
-    return preprocess_input(raw_x)
+    return preprocess(raw_x, 'imagenet')
 
 
 def load_embeddings(feature_extractors_names):
@@ -394,10 +403,19 @@ def select_target_label(imgs, feature_extractors_ls, feature_extractors_names, m
     max_sum = np.min(pair_dist, axis=0)
     max_id = np.argmax(max_sum)
 
-    image_paths = glob.glob(os.path.join(model_dir, "target_data/{}/*".format(paths[int(max_id)])))
+    target_data_id = paths[int(max_id)]
+    image_dir = os.path.join(model_dir, "target_data/{}/*".format(target_data_id))
+    if not os.path.exists(image_dir):
+        get_file("{}.h5".format(name), "http://sandlab.cs.uchicago.edu/fawkes/files/target_images".format(name),
+                 cache_dir=model_dir, cache_subdir='')
+
+    image_paths = glob.glob(image_dir)
+
     target_images = [image.img_to_array(image.load_img(cur_path)) for cur_path in
                      image_paths]
-    target_images = preprocess_input(np.array([resize(x, (224, 224)) for x in target_images]))
+
+    target_images = np.array([resize(x, (224, 224)) for x in target_images])
+    target_images = preprocess(target_images, 'imagenet')
 
     target_images = list(target_images)
     while len(target_images) < len(imgs):
@@ -406,152 +424,151 @@ def select_target_label(imgs, feature_extractors_ls, feature_extractors_names, m
     target_images = random.sample(target_images, len(imgs))
     return np.array(target_images)
 
-
-class CloakData(object):
-    def __init__(self, protect_directory=None, img_shape=(224, 224)):
-
-        self.img_shape = img_shape
-        # self.train_data_dir, self.test_data_dir, self.number_classes, self.number_samples = get_dataset_path(dataset)
-        # self.all_labels = sorted(list(os.listdir(self.train_data_dir)))
-        self.protect_directory = protect_directory
-
-        self.protect_X = self.load_label_data(self.protect_directory)
-
-        self.cloaked_protect_train_X = None
-
-        self.label2path_train, self.label2path_test, self.path2idx = self.build_data_mapping()
-        self.all_training_path = self.get_all_data_path(self.label2path_train)
-        self.all_test_path = self.get_all_data_path(self.label2path_test)
-        self.protect_class_path = self.get_class_image_files(os.path.join(self.train_data_dir, self.protect_class))
-
-    def get_class_image_files(self, path):
-        return [os.path.join(path, f) for f in os.listdir(path)]
-
-    def extractor_ls_predict(self, feature_extractors_ls, X):
-        feature_ls = []
-        for extractor in feature_extractors_ls:
-            cur_features = extractor.predict(X)
-            feature_ls.append(cur_features)
-        concated_feature_ls = np.concatenate(feature_ls, axis=1)
-        concated_feature_ls = normalize(concated_feature_ls)
-        return concated_feature_ls
-
-    def load_embeddings(self, feature_extractors_names):
-        dictionaries = []
-        for extractor_name in feature_extractors_names:
-            path2emb = pickle.load(open("../feature_extractors/embeddings/{}_emb_norm.p".format(extractor_name), "rb"))
-            dictionaries.append(path2emb)
-
-        merge_dict = {}
-        for k in dictionaries[0].keys():
-            cur_emb = [dic[k] for dic in dictionaries]
-            merge_dict[k] = np.concatenate(cur_emb)
-        return merge_dict
-
-    def select_target_label(self, feature_extractors_ls, feature_extractors_names, metric='l2'):
-        original_feature_x = self.extractor_ls_predict(feature_extractors_ls, self.protect_train_X)
-
-        path2emb = self.load_embeddings(feature_extractors_names)
-        items = list(path2emb.items())
-        paths = [p[0] for p in items]
-        embs = [p[1] for p in items]
-        embs = np.array(embs)
-
-        pair_dist = pairwise_distances(original_feature_x, embs, metric)
-        max_sum = np.min(pair_dist, axis=0)
-        sorted_idx = np.argsort(max_sum)[::-1]
-
-        highest_num = 0
-        paired_target_X = None
-        final_target_class_path = None
-        for idx in sorted_idx[:5]:
-            target_class_path = paths[idx]
-            cur_target_X = self.load_dir(target_class_path)
-            cur_target_X = np.concatenate([cur_target_X, cur_target_X, cur_target_X])
-            cur_tot_sum, cur_paired_target_X = self.calculate_dist_score(self.protect_train_X, cur_target_X,
-                                                                         feature_extractors_ls,
-                                                                         metric=metric)
-            if cur_tot_sum > highest_num:
-                highest_num = cur_tot_sum
-                paired_target_X = cur_paired_target_X
-                final_target_class_path = target_class_path
-
-        np.random.shuffle(paired_target_X)
-        return final_target_class_path, paired_target_X
-
-    def calculate_dist_score(self, a, b, feature_extractors_ls, metric='l2'):
-        features1 = self.extractor_ls_predict(feature_extractors_ls, a)
-        features2 = self.extractor_ls_predict(feature_extractors_ls, b)
-
-        pair_cos = pairwise_distances(features1, features2, metric)
-        max_sum = np.min(pair_cos, axis=0)
-        max_sum_arg = np.argsort(max_sum)[::-1]
-        max_sum_arg = max_sum_arg[:len(a)]
-        max_sum = [max_sum[i] for i in max_sum_arg]
-        paired_target_X = [b[j] for j in max_sum_arg]
-        paired_target_X = np.array(paired_target_X)
-        return np.min(max_sum), paired_target_X
-
-    def get_all_data_path(self, label2path):
-        all_paths = []
-        for k, v in label2path.items():
-            cur_all_paths = [os.path.join(k, cur_p) for cur_p in v]
-            all_paths.extend(cur_all_paths)
-        return all_paths
-
-    def load_label_data(self, label):
-        train_label_path = os.path.join(self.train_data_dir, label)
-        test_label_path = os.path.join(self.test_data_dir, label)
-        train_X = self.load_dir(train_label_path)
-        test_X = self.load_dir(test_label_path)
-        return train_X, test_X
-
-    def load_dir(self, path):
-        assert os.path.exists(path)
-        x_ls = []
-        for file in os.listdir(path):
-            cur_path = os.path.join(path, file)
-            im = image.load_img(cur_path, target_size=self.img_shape)
-            im = image.img_to_array(im)
-            x_ls.append(im)
-        raw_x = np.array(x_ls)
-        return preprocess_input(raw_x)
-
-    def build_data_mapping(self):
-        label2path_train = {}
-        label2path_test = {}
-        idx = 0
-        path2idx = {}
-        for label_name in self.all_labels:
-            full_path_train = os.path.join(self.train_data_dir, label_name)
-            full_path_test = os.path.join(self.test_data_dir, label_name)
-            label2path_train[full_path_train] = list(os.listdir(full_path_train))
-            label2path_test[full_path_test] = list(os.listdir(full_path_test))
-            for img_file in os.listdir(full_path_train):
-                path2idx[os.path.join(full_path_train, img_file)] = idx
-            for img_file in os.listdir(full_path_test):
-                path2idx[os.path.join(full_path_test, img_file)] = idx
-            idx += 1
-        return label2path_train, label2path_test, path2idx
-
-    def generate_data_post_cloak(self, sybil=False):
-        assert self.cloaked_protect_train_X is not None
-        while True:
-            batch_X = []
-            batch_Y = []
-            cur_batch_path = random.sample(self.all_training_path, 32)
-            for p in cur_batch_path:
-                cur_y = self.path2idx[p]
-                if p in self.protect_class_path:
-                    cur_x = random.choice(self.cloaked_protect_train_X)
-                elif sybil and (p in self.sybil_class):
-                    cur_x = random.choice(self.cloaked_sybil_train_X)
-                else:
-                    im = image.load_img(p, target_size=self.img_shape)
-                    im = image.img_to_array(im)
-                    cur_x = preprocess_input(im)
-                batch_X.append(cur_x)
-                batch_Y.append(cur_y)
-            batch_X = np.array(batch_X)
-            batch_Y = to_categorical(np.array(batch_Y), num_classes=self.number_classes)
-            yield batch_X, batch_Y
+# class CloakData(object):
+#     def __init__(self, protect_directory=None, img_shape=(224, 224)):
+#
+#         self.img_shape = img_shape
+#         # self.train_data_dir, self.test_data_dir, self.number_classes, self.number_samples = get_dataset_path(dataset)
+#         # self.all_labels = sorted(list(os.listdir(self.train_data_dir)))
+#         self.protect_directory = protect_directory
+#
+#         self.protect_X = self.load_label_data(self.protect_directory)
+#
+#         self.cloaked_protect_train_X = None
+#
+#         self.label2path_train, self.label2path_test, self.path2idx = self.build_data_mapping()
+#         self.all_training_path = self.get_all_data_path(self.label2path_train)
+#         self.all_test_path = self.get_all_data_path(self.label2path_test)
+#         self.protect_class_path = self.get_class_image_files(os.path.join(self.train_data_dir, self.protect_class))
+#
+#     def get_class_image_files(self, path):
+#         return [os.path.join(path, f) for f in os.listdir(path)]
+#
+#     def extractor_ls_predict(self, feature_extractors_ls, X):
+#         feature_ls = []
+#         for extractor in feature_extractors_ls:
+#             cur_features = extractor.predict(X)
+#             feature_ls.append(cur_features)
+#         concated_feature_ls = np.concatenate(feature_ls, axis=1)
+#         concated_feature_ls = normalize(concated_feature_ls)
+#         return concated_feature_ls
+#
+#     def load_embeddings(self, feature_extractors_names):
+#         dictionaries = []
+#         for extractor_name in feature_extractors_names:
+#             path2emb = pickle.load(open("../feature_extractors/embeddings/{}_emb_norm.p".format(extractor_name), "rb"))
+#             dictionaries.append(path2emb)
+#
+#         merge_dict = {}
+#         for k in dictionaries[0].keys():
+#             cur_emb = [dic[k] for dic in dictionaries]
+#             merge_dict[k] = np.concatenate(cur_emb)
+#         return merge_dict
+#
+#     def select_target_label(self, feature_extractors_ls, feature_extractors_names, metric='l2'):
+#         original_feature_x = self.extractor_ls_predict(feature_extractors_ls, self.protect_train_X)
+#
+#         path2emb = self.load_embeddings(feature_extractors_names)
+#         items = list(path2emb.items())
+#         paths = [p[0] for p in items]
+#         embs = [p[1] for p in items]
+#         embs = np.array(embs)
+#
+#         pair_dist = pairwise_distances(original_feature_x, embs, metric)
+#         max_sum = np.min(pair_dist, axis=0)
+#         sorted_idx = np.argsort(max_sum)[::-1]
+#
+#         highest_num = 0
+#         paired_target_X = None
+#         final_target_class_path = None
+#         for idx in sorted_idx[:5]:
+#             target_class_path = paths[idx]
+#             cur_target_X = self.load_dir(target_class_path)
+#             cur_target_X = np.concatenate([cur_target_X, cur_target_X, cur_target_X])
+#             cur_tot_sum, cur_paired_target_X = self.calculate_dist_score(self.protect_train_X, cur_target_X,
+#                                                                          feature_extractors_ls,
+#                                                                          metric=metric)
+#             if cur_tot_sum > highest_num:
+#                 highest_num = cur_tot_sum
+#                 paired_target_X = cur_paired_target_X
+#                 final_target_class_path = target_class_path
+#
+#         np.random.shuffle(paired_target_X)
+#         return final_target_class_path, paired_target_X
+#
+#     def calculate_dist_score(self, a, b, feature_extractors_ls, metric='l2'):
+#         features1 = self.extractor_ls_predict(feature_extractors_ls, a)
+#         features2 = self.extractor_ls_predict(feature_extractors_ls, b)
+#
+#         pair_cos = pairwise_distances(features1, features2, metric)
+#         max_sum = np.min(pair_cos, axis=0)
+#         max_sum_arg = np.argsort(max_sum)[::-1]
+#         max_sum_arg = max_sum_arg[:len(a)]
+#         max_sum = [max_sum[i] for i in max_sum_arg]
+#         paired_target_X = [b[j] for j in max_sum_arg]
+#         paired_target_X = np.array(paired_target_X)
+#         return np.min(max_sum), paired_target_X
+#
+#     def get_all_data_path(self, label2path):
+#         all_paths = []
+#         for k, v in label2path.items():
+#             cur_all_paths = [os.path.join(k, cur_p) for cur_p in v]
+#             all_paths.extend(cur_all_paths)
+#         return all_paths
+#
+#     def load_label_data(self, label):
+#         train_label_path = os.path.join(self.train_data_dir, label)
+#         test_label_path = os.path.join(self.test_data_dir, label)
+#         train_X = self.load_dir(train_label_path)
+#         test_X = self.load_dir(test_label_path)
+#         return train_X, test_X
+#
+#     def load_dir(self, path):
+#         assert os.path.exists(path)
+#         x_ls = []
+#         for file in os.listdir(path):
+#             cur_path = os.path.join(path, file)
+#             im = image.load_img(cur_path, target_size=self.img_shape)
+#             im = image.img_to_array(im)
+#             x_ls.append(im)
+#         raw_x = np.array(x_ls)
+#         return preprocess_input(raw_x)
+#
+#     def build_data_mapping(self):
+#         label2path_train = {}
+#         label2path_test = {}
+#         idx = 0
+#         path2idx = {}
+#         for label_name in self.all_labels:
+#             full_path_train = os.path.join(self.train_data_dir, label_name)
+#             full_path_test = os.path.join(self.test_data_dir, label_name)
+#             label2path_train[full_path_train] = list(os.listdir(full_path_train))
+#             label2path_test[full_path_test] = list(os.listdir(full_path_test))
+#             for img_file in os.listdir(full_path_train):
+#                 path2idx[os.path.join(full_path_train, img_file)] = idx
+#             for img_file in os.listdir(full_path_test):
+#                 path2idx[os.path.join(full_path_test, img_file)] = idx
+#             idx += 1
+#         return label2path_train, label2path_test, path2idx
+#
+#     def generate_data_post_cloak(self, sybil=False):
+#         assert self.cloaked_protect_train_X is not None
+#         while True:
+#             batch_X = []
+#             batch_Y = []
+#             cur_batch_path = random.sample(self.all_training_path, 32)
+#             for p in cur_batch_path:
+#                 cur_y = self.path2idx[p]
+#                 if p in self.protect_class_path:
+#                     cur_x = random.choice(self.cloaked_protect_train_X)
+#                 elif sybil and (p in self.sybil_class):
+#                     cur_x = random.choice(self.cloaked_sybil_train_X)
+#                 else:
+#                     im = image.load_img(p, target_size=self.img_shape)
+#                     im = image.img_to_array(im)
+#                     cur_x = preprocess_input(im)
+#                 batch_X.append(cur_x)
+#                 batch_Y.append(cur_y)
+#             batch_X = np.array(batch_X)
+#             batch_Y = to_categorical(np.array(batch_Y), num_classes=self.number_classes)
+#             yield batch_X, batch_Y