def load_model(self, model_path):
"""
This is a custom function for loading resnet model.
ARGS:
model_path: The relative path to trained model.
"""
img_width, img_height = IMG_SIZE, IMG_SIZE
num_channels = 3
num_classes = NUM_CLASSES
model = resnet152_model(img_height, img_width, num_channels,
num_classes)
model.load_weights(model_path, by_name=True)
return model
y_val = keras.utils.to_categorical(y_val, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
print("Preprocess data.")
x_test = x_test[
..., ::
-1] # What this does? Changes the order of last layer - RGB to BGR
x_val = x_val[..., ::-1]
for i in range(3):
x_test[:, :, :, i] -= MEAN[i]
x_val[:, :, :, i] -= MEAN[i]
model = resnet152_model()
sgd = SGD(lr=1e-2, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(optimizer=sgd,
loss='categorical_crossentropy',
metrics=['accuracy'])
print("Start evaluation!")
evaluate_model(model,
weights_file_resnet,
x_test,
y_test,
bins=15,
verbose=True,
pickle_file="probs_resnet152_imgnet",
x_val=x_val,
y_val=y_val)
def get_image_features(self, image_directory):
from keras.preprocessing import image
from keras.models import Model
if self.cnn_extractor == 'vgg16':
from keras.applications.vgg16 import preprocess_input
from keras.applications import VGG16
self.IMG_FEATS = 4096
base_model = VGG16(weights='imagenet')
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('fc2').output)
self.extracted_features = []
self.image_feature_files = list(set(self.image_files))
number_of_images = len(self.image_feature_files)
for image_arg, image_file in tqdm(
enumerate(self.image_feature_files)):
image_path = image_directory + image_file
# if image_arg%100 == 0:
# print('%.2f %% completed' %
# round(100*image_arg/number_of_images,2))
img = image.load_img(image_path, target_size=(224, 224))
img = image.img_to_array(img)
img = np.expand_dims(img, axis=0)
img = preprocess_input(img)
CNN_features = model.predict(img)
self.extracted_features.append(np.squeeze(CNN_features))
self.extracted_features = np.asarray(self.extracted_features)
elif self.cnn_extractor == 'vgg19':
from keras.applications.vgg19 import preprocess_input
from keras.applications import VGG19
self.IMG_FEATS = 4096
base_model = VGG19(weights='imagenet')
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('fc2').output)
self.extracted_features = []
self.image_feature_files = list(set(self.image_files))
number_of_images = len(self.image_feature_files)
for image_arg, image_file in enumerate(self.image_feature_files):
image_path = image_directory + image_file
if image_arg % 100 == 0:
print('%.2f %% completed' %
round(100 * image_arg / number_of_images, 2))
img = image.load_img(image_path, target_size=(224, 224))
img = image.img_to_array(img)
img = np.expand_dims(img, axis=0)
img = preprocess_input(img)
CNN_features = model.predict(img)
self.extracted_features.append(np.squeeze(CNN_features))
self.extracted_features = np.asarray(self.extracted_features)
elif self.cnn_extractor == 'inception':
from keras.applications.inception_v3 import preprocess_input
from keras.applications import InceptionV3
self.IMG_FEATS = 2048
base_model = InceptionV3(weights='imagenet')
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('avg_pool').output)
self.extracted_features = []
self.image_feature_files = list(set(self.image_files))
number_of_images = len(self.image_feature_files)
for image_arg, image_file in tqdm(
enumerate(self.image_feature_files)):
image_path = image_directory + image_file
# if image_arg%100 == 0:
# print('%.2f %% completed' %
# round(100*image_arg/number_of_images,2))
img = image.load_img(image_path, target_size=(299, 299))
img = image.img_to_array(img)
img = np.expand_dims(img, axis=0)
img = preprocess_input(img)
CNN_features = model.predict(img)
self.extracted_features.append(np.squeeze(CNN_features))
self.extracted_features = np.asarray(self.extracted_features)
elif self.cnn_extractor == 'vgg16_places':
from VGG_Place205 import VGG16_places
from keras.applications.vgg16 import preprocess_input
self.IMG_FEATS = 4096
base_model = VGG16_places()
base_model.load_weights(
"VGG_Place205/vgg_tensorflow_channels_last.h5")
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('fc7').output)
self.extracted_features = []
self.image_feature_files = list(set(self.image_files))
number_of_images = len(self.image_feature_files)
for image_arg, image_file in enumerate(self.image_feature_files):
image_path = image_directory + image_file
if image_arg % 100 == 0:
print('%.2f %% completed' %
round(100 * image_arg / number_of_images, 2))
img = image.load_img(image_path, target_size=(224, 224))
img = image.img_to_array(img)
img = np.expand_dims(img, axis=0)
img = preprocess_input(img)
CNN_features = model.predict(img)
self.extracted_features.append(np.squeeze(CNN_features))
self.extracted_features = np.asarray(self.extracted_features)
elif self.cnn_extractor == 'inceptionresnetv2':
from keras.applications.inception_resnet_v2 import InceptionResNetV2, preprocess_input
base_model = InceptionResNetV2(weights="imagenet")
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('avg_pool').output)
self.extracted_features = []
self.image_feature_files = list(set(self.image_files))
number_of_images = len(self.image_feature_files)
for image_arg, image_file in enumerate(self.image_feature_files):
image_path = image_directory + image_file
if image_arg % 100 == 0:
print('%.2f %% completed' %
round(100 * image_arg / number_of_images, 2))
img = image.load_img(image_path, target_size=(229, 229))
img = image.img_to_array(img)
img = np.expand_dims(img, axis=0)
img = preprocess_input(img)
CNN_features = model.predict(img)
self.extracted_features.append(np.squeeze(CNN_features))
self.extracted_features = np.asarray(self.extracted_features)
elif self.cnn_extractor == 'resnet50':
from keras.applications.resnet50 import ResNet50, preprocess_input
base_model = ResNet50(weights="imagenet")
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('avg_pool').output)
self.extracted_features = []
self.image_feature_files = list(set(self.image_files))
number_of_images = len(self.image_feature_files)
for image_arg, image_file in tqdm(
enumerate(self.image_feature_files)):
image_path = image_directory + image_file
# if image_arg%100 == 0:
# print('%.2f %% completed' %
# round(100*image_arg/number_of_images,2))
img = image.load_img(image_path, target_size=(224, 224))
img = image.img_to_array(img)
img = np.expand_dims(img, axis=0)
img = preprocess_input(img)
CNN_features = model.predict(img)
self.extracted_features.append(np.squeeze(CNN_features))
self.extracted_features = np.asarray(self.extracted_features)
elif self.cnn_extractor == 'xception':
from keras.applications.xception import Xception, preprocess_input
base_model = Xception(weights="imagenet")
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('avg_pool').output)
self.extracted_features = []
self.image_feature_files = list(set(self.image_files))
number_of_images = len(self.image_feature_files)
for image_arg, image_file in enumerate(self.image_feature_files):
image_path = image_directory + image_file
if image_arg % 100 == 0:
print('%.2f %% completed' %
round(100 * image_arg / number_of_images, 2))
img = image.load_img(image_path, target_size=(224, 224))
img = image.img_to_array(img)
img = np.expand_dims(img, axis=0)
img = preprocess_input(img)
CNN_features = model.predict(img)
self.extracted_features.append(np.squeeze(CNN_features))
self.extracted_features = np.asarray(self.extracted_features)
elif self.cnn_extractor == 'resnet152':
from resnet152 import resnet152_model
base_model = resnet152_model("resnet152_weights_tf.h5")
model = Model(inputs=base_model.input,
outputs=base_model.get_layer('avg_pool').output)
self.extracted_features = []
self.image_feature_files = list(set(self.image_files))
number_of_images = len(self.image_feature_files)
for image_arg, image_file in enumerate(self.image_feature_files):
image_path = image_directory + image_file
if image_arg % 100 == 0:
print('%.2f %% completed' %
round(100 * image_arg / number_of_images, 2))
# img = image.load_img(image_path, target_size=(224, 224))
# img = image.img_to_array(img)
img = cv2.resize(cv2.imread(image_path),
(224, 224)).astype(np.float32)
# Remove train image mean
img[:, :, 0] -= 103.939
img[:, :, 1] -= 116.779
img[:, :, 2] -= 123.68
img = np.expand_dims(img, axis=0)
# img = preprocess_input(img)
CNN_features = model.predict(img)
self.extracted_features.append(np.squeeze(CNN_features))
self.extracted_features = np.asarray(self.extracted_features)
def build_resnet152_model():
"""
Builds resnet152 model. Code partially used from another gist.
"""
return resnet152_model(IMG_SIZE, IMG_SIZE, 3, NUM_CLASSES)