def __init__(self, init_x, init_y, index_nav): super().__init__() self.x = init_x self.y = init_y self.status = random.randint(0, 2) self.IMAGES = [ loader.load_image("green_light.png"), loader.load_image("yellow_light.png"), loader.load_image("red_light.png") ] self.image = self.IMAGES[self.status] self.remaining_time = self.cal_remain_time() self.index_nav = index_nav self.rect = self.image.get_rect() self.rect.center = self.x, self.y
def generate(self, source, destination = None, samples = 20, grid_width=480, grid_height=240): # Load the input and output of the graph input = self.graph.get_tensor_by_name("en_input:0" ) output = self.graph.get_tensor_by_name("decoder/main_out:0") # For generating a single image for a source image if os.path.isfile(source): image = loader.load_image(source, self.image_size, self.image_size) batch = np.asarray([image for _ in range(self.batch_size)]) preds = self.session.run(output, feed_dict = {input: batch}) batch[0] = utils.add_border(batch[0],color = [1.0,0.0,0.0]) grid = np.concatenate((batch[0], preds[0]), axis=1) grid = (grid * 255.0).astype(np.uint8) # For generating a grid of images from a directory of images elif os.path.isdir(source): data = loader.DataSet(images_dir = source, hard_load = False, width = self.image_size, height = self.image_size) batch,_= data.next_batch(self.batch_size) preds = self.session.run(output, feed_dict={input: batch}) for i in range(samples): batch[i] = utils.add_border(batch[i],color = [1.0,0.0,0.0]) grid = self.construct_image_grid(batch,preds,samples,grid_width,grid_height) else: print(source,"must be an image pathname or a directory of images") sys.exit() if destination: cv2.imwrite(destination, grid) else: cv2.imshow("images", grid) cv2.waitKey()
def __init__(self, init_x, init_y): super().__init__() self.image = loader.load_image("map.png") self.rect = self.image.get_rect() self.x = init_x self.y = init_y self.get_map_nav() self.get_edges() self.shortest_paths = self.find_shortest_paths() self.get_light_pos()
def __init__(self, init_x, init_y, index_nav): super().__init__() self.x = init_x self.y = init_y self.image_ori = loader.load_image('stone.png') self.image = self.image_ori self.rect = self.image.get_rect() self.rect.center = self.x, self.y self.index_nav = index_nav self.status = config.HIDDEN self.time_appearance = 0
def __init__(self, image, label=""): """ Initialize the detector with an image an a label :type image: numpy.ndarray :param image: Image to be processed :type label: str :param label: Optional label for the image """ self.image = loader.load_image(image) self.label = label
def __init__(self, image, label=""): """ Initialize the detector with an image an a label :type image: numpy.ndarray :param image: Image to be processed :type label: str :param label: Optional label for the image """ self.image = loader.load_image(image) self.label = label
def predict(self, image_path, label=4, max_labels=10): image = loader.load_image(image_path, self.image_size, self.image_size) x_batch = np.asarray([image for _ in range(self.batch_size)]) labels = np.zeros(max_labels) labels[label] = 1.0 y_batch = np.asarray([labels for _ in range(self.batch_size)]) output = self.graph.get_tensor_by_name("decoder/main_out:0") input = self.graph.get_tensor_by_name("en_input:0") label = self.graph.get_tensor_by_name("labels:0") preds = self.session.run(output, feed_dict={ input: x_batch, label: y_batch }) return x_batch[0], preds[0]
def __init__(self): super().__init__() self.fuzzy_monitor = fuzzy_controller.FuzzyController() self.path = [] self.image = loader.load_image("car.png", False) self.image_ori = self.image self.color = config.BLACK self.x = MAP_NAVS[0][0] - config.PARA self.y = MAP_NAVS[0][1] + config.PARA self.dir = 90.0 self.speed = 0.3 self.deviation = 0.0 self.angle_deviation = 0.0 self.acceleration = 0 self.lights = [] self.desired_dir = 90.0 self.cur_nav = 0 self.turn = config.STRAIGHT self.central_point = (0, 0) self.rect = self.image.get_rect(center=(self.x, self.y)) self.image, self.rect = rot_center(self.image_ori, self.rect, self.dir)
from utils.options import parser from utils.loader import load_model, load_image, tensor2im from PIL import Image if __name__ == "__main__": args = parser.parse_args() model = load_model(args.model) model.setup() image = load_image(args.image, args.model) model.set_input(image) model.test() fake = model.get_generated() fake = tensor2im(fake) image_pil = Image.fromarray(fake) image_pil.save(f'{args.save_to}/{args.model}.jpg')
def __init__(self, image): self.image = loader.load_image(image)