Python visualizer.Visualizer() Examples

def initialize(self, opt):
        self.opt = opt
        self.visual = Visualizer()
        self.visual.initialize(self.opt) 

def gtsrb_visualize_label_scan_bottom_right_white_4():

    print('loading dataset')
    X_test, Y_test = load_dataset()
    # transform numpy arrays into data generator
    test_generator = build_data_loader(X_test, Y_test)

    print('loading model')
    model_file = '%s/%s' % (MODEL_DIR, MODEL_FILENAME)
    model = load_model(model_file)

    # initialize visualizer
    visualizer = Visualizer(
        model, intensity_range=INTENSITY_RANGE, regularization=REGULARIZATION,
        input_shape=INPUT_SHAPE,
        init_cost=INIT_COST, steps=STEPS, lr=LR, num_classes=NUM_CLASSES,
        mini_batch=MINI_BATCH,
        upsample_size=UPSAMPLE_SIZE,
        attack_succ_threshold=ATTACK_SUCC_THRESHOLD,
        patience=PATIENCE, cost_multiplier=COST_MULTIPLIER,
        img_color=IMG_COLOR, batch_size=BATCH_SIZE, verbose=2,
        save_last=SAVE_LAST,
        early_stop=EARLY_STOP, early_stop_threshold=EARLY_STOP_THRESHOLD,
        early_stop_patience=EARLY_STOP_PATIENCE)

    log_mapping = {}

    # y_label list to analyze
    y_target_list = list(range(NUM_CLASSES))
    y_target_list.remove(Y_TARGET)
    y_target_list = [Y_TARGET] + y_target_list
    for y_target in y_target_list:

        print('processing label %d' % y_target)

        _, _, logs = visualize_trigger_w_mask(
            visualizer, test_generator, y_target=y_target,
            save_pattern_flag=True)

        log_mapping[y_target] = logs

    pass 

def __init__(self, rl_method='rl', stock_code=None, 
                chart_data=None, training_data=None,
                min_trading_unit=1, max_trading_unit=2, 
                delayed_reward_threshold=.05,
                net='dnn', num_steps=1, lr=0.001,
                value_network=None, policy_network=None,
                output_path='', reuse_models=True):
        # 인자 확인
        assert min_trading_unit > 0
        assert max_trading_unit > 0
        assert max_trading_unit >= min_trading_unit
        assert num_steps > 0
        assert lr > 0
        # 강화학습 기법 설정
        self.rl_method = rl_method
        # 환경 설정
        self.stock_code = stock_code
        self.chart_data = chart_data
        self.environment = Environment(chart_data)
        # 에이전트 설정
        self.agent = Agent(self.environment,
                    min_trading_unit=min_trading_unit,
                    max_trading_unit=max_trading_unit,
                    delayed_reward_threshold=delayed_reward_threshold)
        # 학습 데이터
        self.training_data = training_data
        self.sample = None
        self.training_data_idx = -1
        # 벡터 크기 = 학습 데이터 벡터 크기 + 에이전트 상태 크기
        self.num_features = self.agent.STATE_DIM
        if self.training_data is not None:
            self.num_features += self.training_data.shape[1]
        # 신경망 설정
        self.net = net
        self.num_steps = num_steps
        self.lr = lr
        self.value_network = value_network
        self.policy_network = policy_network
        self.reuse_models = reuse_models
        # 가시화 모듈
        self.visualizer = Visualizer()
        # 메모리
        self.memory_sample = []
        self.memory_action = []
        self.memory_reward = []
        self.memory_value = []
        self.memory_policy = []
        self.memory_pv = []
        self.memory_num_stocks = []
        self.memory_exp_idx = []
        self.memory_learning_idx = []
        # 에포크 관련 정보
        self.loss = 0.
        self.itr_cnt = 0
        self.exploration_cnt = 0
        self.batch_size = 0
        self.learning_cnt = 0
        # 로그 등 출력 경로
        self.output_path = output_path