def load_paths_to_images(self, paths):
images = np.empty(
[len(paths), IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNELS])
for k, path in enumerate(paths):
images[k] = utils.load_img_from_path(data_dir=self.data_dir,
image_name=path,
is_gray_scale=self.gray_scale)
return images
def predict(self, data, number_of_steps):
predictions = np.empty(shape=(number_of_steps,))
data_shape = data.shape
for i in range(predictions.shape[0]):
predicted_value = self.model.predict(data)
predictions[i] = predicted_value.item()
# remove first element and add the prediction
data = np.reshape(np.append(data[0][1:], predicted_value.item()), newshape=data_shape)
return predictions
def __getitem__(self, index):
start_index = index * self.batch_size
end_index = start_index + self.batch_size
batch_paths = self.path_to_pictures[start_index:end_index]
steering_angles = self.steering_angles[start_index:end_index]
images = np.empty([len(batch_paths), IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNELS])
steers = np.empty([len(batch_paths)])
for i, paths in enumerate(batch_paths):
center, left, right = batch_paths[i]
steering_angle = steering_angles[i]
# augmentation
if self.is_training and np.random.rand() < 0.6:
image, steering_angle = augment(self.args.data_dir, center, left, right, steering_angle)
else:
image = load_image(self.args.data_dir, center)
# add the image and steering angle to the batch
images[i] = preprocess(image)
steers[i] = steering_angle
return images, steers
def __getitem__(self, index):
start_index = index * self.batch_size
end_index = start_index + self.batch_size
batch_paths = self.path_to_pictures[start_index:end_index]
input_shape = self.model.get_input_shape()
x_shape = (len(batch_paths), ) + (input_shape)
x = np.empty(shape=x_shape)
for i, path in enumerate(batch_paths):
# apply augmentation to 60% of the images, if enabled
if APPLY_DATA_AUGMENTATION and np.random.rand() < 0.6:
# data augmentation
img = load_image(self.data_dir, path)
img = augment(img)
img = preprocess(img) # crop + resize + rgb2yuv
else:
img = load_image(self.data_dir, path)
img = resize(img)
x[i] = self.model.normalize_and_reshape(img)
return x, x
def empty_batch_array(self, this_batch_y_paths):
return np.empty([
len(this_batch_y_paths), self.sequence_length, IMAGE_HEIGHT,
IMAGE_WIDTH, IMAGE_CHANNELS
])