Python backend.placeholder方法代码示例

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def reverse_generator(generator, X_sample, y_sample, title):
    """Gradient descent to map images back to their latent vectors."""

    latent_vec = np.random.normal(size=(1, 100))

    # Function for figuring out how to bump the input.
    target = K.placeholder()
    loss = K.sum(K.square(generator.outputs[0] - target))
    grad = K.gradients(loss, generator.inputs[0])[0]
    update_fn = K.function(generator.inputs + [target], [grad])

    # Repeatedly apply the update rule.
    xs = []
    for i in range(60):
        print('%d: latent_vec mean=%f, std=%f'
              % (i, np.mean(latent_vec), np.std(latent_vec)))
        xs.append(generator.predict_on_batch([latent_vec, y_sample]))
        for _ in range(10):
            update_vec = update_fn([latent_vec, y_sample, X_sample])[0]
            latent_vec -= update_vec * update_rate

    # Plots the samples.
    xs = np.concatenate(xs, axis=0)
    plot_as_gif(xs, X_sample, title) 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def optimizer(self):
        a = K.placeholder(shape=(None,), dtype='int32')
        y = K.placeholder(shape=(None,), dtype='float32')

        prediction = self.model.output

        a_one_hot = K.one_hot(a, self.action_size)
        q_value = K.sum(prediction * a_one_hot, axis=1)
        error = K.abs(y - q_value)

        quadratic_part = K.clip(error, 0.0, 1.0)
        linear_part = error - quadratic_part
        loss = K.mean(0.5 * K.square(quadratic_part) + linear_part)

        optimizer = RMSprop(lr=0.00025, epsilon=0.01)
        updates = optimizer.get_updates(self.model.trainable_weights, [], loss)
        train = K.function([self.model.input, a, y], [loss], updates=updates)

        return train

    # 상태가 입력, 큐함수가 출력인 인공신경망 생성 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def setup_summary(self):
        episode_total_reward = tf.Variable(0.)
        episode_avg_max_q = tf.Variable(0.)
        episode_duration = tf.Variable(0.)
        episode_avg_loss = tf.Variable(0.)

        tf.summary.scalar('Total Reward/Episode', episode_total_reward)
        tf.summary.scalar('Average Max Q/Episode', episode_avg_max_q)
        tf.summary.scalar('Duration/Episode', episode_duration)
        tf.summary.scalar('Average Loss/Episode', episode_avg_loss)

        summary_vars = [episode_total_reward, episode_avg_max_q,
                        episode_duration, episode_avg_loss]
        summary_placeholders = [tf.placeholder(tf.float32) for _ in
                                range(len(summary_vars))]
        update_ops = [summary_vars[i].assign(summary_placeholders[i]) for i in
                      range(len(summary_vars))]
        summary_op = tf.summary.merge_all()
        return summary_placeholders, update_ops, summary_op


# 학습속도를 높이기 위해 흑백화면으로 전처리 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def actor_optimizer(self):
        action = K.placeholder(shape=[None, self.action_size])
        advantages = K.placeholder(shape=[None, ])

        policy = self.actor.output

        # 정책 크로스 엔트로피 오류함수
        action_prob = K.sum(action * policy, axis=1)
        cross_entropy = K.log(action_prob + 1e-10) * advantages
        cross_entropy = -K.sum(cross_entropy)

        # 탐색을 지속적으로 하기 위한 엔트로피 오류
        entropy = K.sum(policy * K.log(policy + 1e-10), axis=1)
        entropy = K.sum(entropy)

        # 두 오류함수를 더해 최종 오류함수를 만듬
        loss = cross_entropy + 0.01 * entropy

        optimizer = RMSprop(lr=self.actor_lr, rho=0.99, epsilon=0.01)
        updates = optimizer.get_updates(self.actor.trainable_weights, [],loss)
        train = K.function([self.actor.input, action, advantages],
                           [loss], updates=updates)
        return train

    # 가치신경망을 업데이트하는 함수 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def setup_summary(self):
        episode_total_reward = tf.Variable(0.)
        episode_avg_max_q = tf.Variable(0.)
        episode_duration = tf.Variable(0.)

        tf.summary.scalar('Total Reward/Episode', episode_total_reward)
        tf.summary.scalar('Average Max Prob/Episode', episode_avg_max_q)
        tf.summary.scalar('Duration/Episode', episode_duration)

        summary_vars = [episode_total_reward,
                        episode_avg_max_q,
                        episode_duration]

        summary_placeholders = [tf.placeholder(tf.float32)
                                for _ in range(len(summary_vars))]
        update_ops = [summary_vars[i].assign(summary_placeholders[i])
                      for i in range(len(summary_vars))]
        summary_op = tf.summary.merge_all()
        return summary_placeholders, update_ops, summary_op


# 액터러너 클래스(쓰레드) 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def generate(self):
        model_path = os.path.expanduser(self.model_path)
        assert model_path.endswith('.h5'), 'Keras model must be a .h5 file.'

        self.yolo_model = load_model(model_path, compile=False)
        print('{} model, anchors, and classes loaded.'.format(model_path))

        # Generate colors for drawing bounding boxes.
        hsv_tuples = [(x / len(self.class_names), 1., 1.)
                      for x in range(len(self.class_names))]
        self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
        self.colors = list(
            map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
                self.colors))
        random.seed(10101)  # Fixed seed for consistent colors across runs.
        random.shuffle(self.colors)  # Shuffle colors to decorrelate adjacent classes.
        random.seed(None)  # Reset seed to default.

        # Generate output tensor targets for filtered bounding boxes.
        self.input_image_shape = K.placeholder(shape=(2, ))
        boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
                len(self.class_names), self.input_image_shape,
                score_threshold=self.score, iou_threshold=self.iou)
        return boxes, scores, classes 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def optimizer(self):
        a = K.placeholder(shape=(None, ), dtype='int32')
        y = K.placeholder(shape=(None, ), dtype='float32')

        py_x = self.model.output

        a_one_hot = K.one_hot(a, self.action_size)
        q_value = K.sum(py_x * a_one_hot, axis=1)
        error = K.abs(y - q_value)

        quadratic_part = K.clip(error, 0.0, 1.0)
        linear_part = error - quadratic_part
        loss = K.mean(0.5 * K.square(quadratic_part) + linear_part)

        optimizer = RMSprop(lr=0.00025, epsilon=0.01)
        updates = optimizer.get_updates(self.model.trainable_weights, [], loss)
        train = K.function([self.model.input, a, y], [loss], updates=updates)

        return train

    # approximate Q function using Convolution Neural Network
    # state is input and Q Value of each action is output of network 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def setup_summary(self):
        episode_total_reward = tf.Variable(0.)
        episode_avg_max_q = tf.Variable(0.)
        episode_duration = tf.Variable(0.)
        episode_avg_loss = tf.Variable(0.)

        tf.summary.scalar('Total Reward/Episode', episode_total_reward)
        tf.summary.scalar('Average Max Q/Episode', episode_avg_max_q)
        tf.summary.scalar('Duration/Episode', episode_duration)
        tf.summary.scalar('Average Loss/Episode', episode_avg_loss)

        summary_vars = [episode_total_reward, episode_avg_max_q,
                        episode_duration, episode_avg_loss]
        summary_placeholders = [tf.placeholder(tf.float32) for _ in
                                range(len(summary_vars))]
        update_ops = [summary_vars[i].assign(summary_placeholders[i]) for i in
                      range(len(summary_vars))]
        summary_op = tf.summary.merge_all()
        return summary_placeholders, update_ops, summary_op


# 210*160*3(color) --> 84*84(mono)
# float --> integer (to reduce the size of replay memory) 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def optimizer(self):
        a = K.placeholder(shape=(None,), dtype='int32')
        y = K.placeholder(shape=(None,), dtype='float32')

        py_x = self.model.output

        a_one_hot = K.one_hot(a, self.action_size)
        q_value = K.sum(py_x * a_one_hot, axis=1)
        error = K.abs(y - q_value)

        quadratic_part = K.clip(error, 0.0, 1.0)
        linear_part = error - quadratic_part
        loss = K.mean(0.5 * K.square(quadratic_part) + linear_part)

        optimizer = RMSprop(lr=0.00025, epsilon=0.01)
        updates = optimizer.get_updates(self.model.trainable_weights, [], loss)
        train = K.function([self.model.input, a, y], [loss], updates=updates)

        return train

    # approximate Q function using Convolution Neural Network
    # state is input and Q Value of each action is output of network 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def actor_optimizer(self):
        action = K.placeholder(shape=[None, self.action_size])
        advantages = K.placeholder(shape=[None, ])

        policy = self.actor.output

        good_prob = K.sum(action * policy, axis=1)
        eligibility = K.log(good_prob + 1e-10) * advantages
        actor_loss = -K.sum(eligibility)

        entropy = K.sum(policy * K.log(policy + 1e-10), axis=1)
        entropy = K.sum(entropy)

        loss = actor_loss + 0.01*entropy
        optimizer = RMSprop(lr=self.actor_lr, rho=0.99, epsilon=0.01)
        updates = optimizer.get_updates(self.actor.trainable_weights, [], loss)
        train = K.function([self.actor.input, action, advantages], [loss], updates=updates)

        return train

    # make loss function for Value approximation 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def setup_summary(self):
        episode_total_reward = tf.Variable(0.)
        episode_avg_max_q = tf.Variable(0.)
        episode_duration = tf.Variable(0.)

        tf.summary.scalar('Total Reward/Episode', episode_total_reward)
        tf.summary.scalar('Average Max Prob/Episode', episode_avg_max_q)
        tf.summary.scalar('Duration/Episode', episode_duration)

        summary_vars = [episode_total_reward, episode_avg_max_q, episode_duration]
        summary_placeholders = [tf.placeholder(tf.float32) for _ in range(len(summary_vars))]
        update_ops = [summary_vars[i].assign(summary_placeholders[i]) for i in range(len(summary_vars))]
        summary_op = tf.summary.merge_all()
        return summary_placeholders, update_ops, summary_op

# make agents(local) and start training 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def optimizer(self):
        a = K.placeholder(shape=(None, ), dtype='int32')
        y = K.placeholder(shape=(None, ), dtype='float32')

        py_x = self.model.output

        a_one_hot = K.one_hot(a, self.action_size)
        q_value = K.sum(py_x * a_one_hot, axis=1)
        error = K.abs(y - q_value)

        quadratic_part = K.clip(error, 0.0, 1.0)
        linear_part = error - quadratic_part
        loss = K.mean(0.5 * K.square(quadratic_part) + linear_part)

        optimizer = RMSprop(lr=0.00025, epsilon=0.01)
        updates = optimizer.get_updates(self.model.trainable_weights, [], loss)
        train = K.function([self.model.input, a, y], [loss], updates=updates)

        return train

    # approximate Q function using Convolution Neural Network
    # state is input and Q Value of each action is output of network
    # dueling network's Q Value is sum of advantages and state value 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def optimizer(self):
        action = K.placeholder(shape=[None, 5])
        discounted_rewards = K.placeholder(shape=[None, ])

        # Calculate cross entropy error function
        action_prob = K.sum(action * self.model.output, axis=1)
        cross_entropy = K.log(action_prob) * discounted_rewards
        loss = -K.sum(cross_entropy)

        # create training function
        optimizer = Adam(lr=self.learning_rate)
        updates = optimizer.get_updates(self.model.trainable_weights, [],
                                        loss)
        train = K.function([self.model.input, action, discounted_rewards], [],
                           updates=updates)

        return train

    # get action from policy network 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def actor_optimizer(self):
        action = K.placeholder(shape=(None, self.action_size))
        advantages = K.placeholder(shape=(None, ))

        policy = self.actor.output

        good_prob = K.sum(action * policy, axis=1)
        eligibility = K.log(good_prob + 1e-10) * K.stop_gradient(advantages)
        loss = -K.sum(eligibility)

        entropy = K.sum(policy * K.log(policy + 1e-10), axis=1)

        actor_loss = loss + 0.01*entropy

        optimizer = Adam(lr=self.actor_lr)
        updates = optimizer.get_updates(self.actor.trainable_weights, [], actor_loss)
        train = K.function([self.actor.input, action, advantages], [], updates=updates)
        return train

    # make loss function for Value approximation 

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import placeholder [as 别名]
def optimizer(self):
        action = K.placeholder(shape=[None, 5])
        discounted_rewards = K.placeholder(shape=[None, ])
        
        # 크로스 엔트로피 오류함수 계산
        action_prob = K.sum(action * self.model.output, axis=1)
        cross_entropy = K.log(action_prob) * discounted_rewards
        loss = -K.sum(cross_entropy)
        
        # 정책신경망을 업데이트하는 훈련함수 생성
        optimizer = Adam(lr=self.learning_rate)
        updates = optimizer.get_updates(self.model.trainable_weights,[],
                                        loss)
        train = K.function([self.model.input, action, discounted_rewards], [],
                           updates=updates)

        return train

    # 정책신경망으로 행동 선택