def loading_embedding(self, imagepath, model, data, layer_num):
"""
:param imagepath: path to the image folder
:param model: model
:param data: dataset
:param layer_num: position of the layer starting from the end of the summary. Determine where to cut the model
This function takes a model, cut the layer and save the embedding for each images in a dataset
"""
model = Model(inputs=model.input, outputs=model.layers[-layer_num].output)
list_x = []
for img in data['files'].tolist():
if self.model_name not in ['vgg19', 'MobileNetV2', 'vggface', 'vgg16']:
img = image.load_img(os.path.join(imagepath, img), target_size=(160, 160))
else:
img = image.load_img(os.path.join(imagepath, img), target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
if self.model_name == 'vgg19':
x = preprocess_input_VGG19(x)
elif self.model_name == 'MobileNetV2':
x = preprocess_input_MNV2(x)
elif self.model_name == 'vgg16':
x = preprocess_input_VGG16(x)
elif self.model_name == 'ResNet50':
x = Preprocess_RESNET50(x)
else:
x = x.astype('float32') / 255.
list_x.append(x)
feature_x = np.vstack(list_x)
label = data['label'].tolist()
feature = model.predict(feature_x)
return feature, label
def predict_label_multi(model, labels, imagepath, preprocess=None):
img = tf.keras.preprocessing.image.load_img(os.path.join(imagepath), target_size=(224, 224))
img_array = tf.keras.preprocessing.image.img_to_array(img)
img_array = np.expand_dims(img_array, 0) # Create batch axis
if preprocess == 'vgg16':
img_array = preprocess_input_VGG16(img_array)
elif preprocess == 'vgg19':
img_array = preprocess_input_VGG19(img_array)
elif preprocess == 'MobileNetV2':
img_array = preprocess_input_MNV2(img_array)
elif preprocess == 'ResNet50':
img_array = Preprocess_RESNET50(img_array)
predictions = model.predict(img_array)[0]
index = np.argmax(predictions)
score = predictions[int(index)]
result = list(labels.values())[int(index)]
# imge = mpimg.imread(imagepath)
# plt.figure(figsize=(5, 5))
# plt.imshow(imge)
# plt.title(list(labels.keys())[int(score)])
# plt.xticks([])
# plt.yticks([])
# plt.show()
return result, score
def read_and_prep_image(image_path, model_name, img_width=IMAGE_WIDTH, img_height=IMAGE_HEIGHT):
image_raw = load_img(image_path, target_size=(img_height, img_width))
image_array = np.array([img_to_array(image_raw)])
if model_name == "ResNet50":
image = preprocess_input_ResNet50(image_array)
elif model_name == "VGG16":
image = preprocess_input_VGG16(image_array)
elif model_name == "VGG19":
image = preprocess_input_VGG19(image_array)
return image