def __getitem__(self, idx):
batch_x = self.x[idx * self.batch_size:(idx + 1) * self.batch_size]
if self.y_col != None:
batch_y = self.y[idx * self.batch_size:(idx + 1) * self.batch_size]
images_list = []
for i, file_name in enumerate(batch_x):
image = skimage.io.imread(file_name)
image = skimage.color.gray2rgb(image)
# Perform random data augmentation
np.random.seed(self.random_state + idx + i)
rotation_angle = np.random.uniform(-self.rotation_range,
self.rotation_range)
image = skimage.transform.rotate(image, rotation_angle)
# Randomize the occurence of horizontal flip
if self.horizontal_flip and np.random.random_integers(0, 1):
image = image[:, ::-1]
image = skimage.transform.resize(image,
self.target_size,
anti_aliasing=True,
mode='constant')
images_list.append(image)
images_array = np.array(images_list)
if self.preprocess_for == 'resnet50':
images_array = resnet50_preprocess_input(images_array)
if self.y_col != None:
y_onehot = np_utils.to_categorical(batch_y,
num_classes=self.num_classes)
return (images_array, y_onehot)
else:
return images_array
def preprocess_input(image, model_type):
if model_type == "vgg19":
return vgg19_preprocess_input(image)
if model_type == "resnet50":
return resnet50_preprocess_input(image)
if model_type == "xception":
return xception_preprocess_input(image)
print(f"Using fallback for model type {model_type}")
return image
def _dog_prediction(self, img_path):
"""For given image path returns flag whether it contains dog or not.
Parameters:
-----------
img_path: str
Filepath to image file.
Returns:
-----------
result: int
Value 1 if image contains human, 0 otherwise.
"""
img = self._path_to_tensor(img_path)
img = resnet50_preprocess_input(img)
result = np.argmax(self.dog_predictor.predict(img))
result = int((result <= 268) and (result >= 151))
return result
def find_faces(data, model, show_boxes=False):
global num_faces
# Arrays to hold all cropped face images and their corresponding labels
faces = []
labels = []
# Check that the model provided is one of the expected models
assert model in ("MobileNetV2", "VGG16", "ResNet50")
# Iterate through each image in the provided data
for image in data:
# Read the image using OpenCV
bgr_image = cv2.imread(filename=data_directory_prefix + "images/" + image["name"])
# For each face in the image (most images contain multiple faces) load the bounding box and label
for bndbox, label in zip(image["bndboxes"], image["classes"]):
# Obtain bounding box values
xmin = bndbox[0]
ymin = bndbox[1]
xmax = bndbox[2]
ymax = bndbox[3]
# Many images have tiny labelled faces, exclude them here to reduce training time later
limit = 30
if (xmax - xmin) > limit and (ymax - ymin) > limit:
# Crop the selected face out of the original image
face_image = bgr_image[ymin:ymax, xmin:xmax]
# Resize the face image with OpenCV to the selected image size
face_image = cv2.resize(src=face_image, dsize=(IMG_SIZE, IMG_SIZE))
if show_boxes:
cv2.imshow("Cropped", face_image)
cv2.waitKey(0)
# Convert the cropped image to an array
face_image = img_to_array(img=face_image)
# Preprocess the image according to the selected model to be used
if model == "ResNet50":
face_image = resnet50_preprocess_input(face_image)
elif model == "VGG16":
face_image = vgg16_preprocess_input(face_image)
elif model == "MobileNetV2":
face_image = mobilenet_preprocess_input(face_image)
# Add the cropped face and its label to the corresponding arrays
faces.append(face_image)
labels.append(label)
# Optionally show the bounding boxes around the selected faces on the orignial image
if show_boxes:
# Choose a color based on the class
if label == 0:
color = (0, 255, 0)
elif label == 1:
color = (0, 0, 255)
else:
color = (0, 255, 255)
# Draw a rectangle around the face
bgr_image = cv2.rectangle(img=bgr_image,
pt1=(xmin, ymin),
pt2=(xmax, ymax),
color=color,
thickness=2)
# Display the image
if show_boxes:
cv2.imshow("image", bgr_image)
cv2.waitKey(0)
# Convert the faces and labels arrays to np arrays
faces = np.array(faces, dtype=np.float32)
labels = np.array(labels)
print(num_faces)
# Return the new data arrays
return faces, labels
def resnet50_preprocess_image(resized_image):
preprocessed_image = resnet50_preprocess_input(resized_image)
return preprocessed_image