Python layers.add方法代码示例

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def channel_spatial_squeeze_excite(input_tensor, ratio=16):
    """ Create a spatial squeeze-excite block

    Args:
        input_tensor: input Keras tensor
        ratio: number of output filters

    Returns: a Keras tensor

    References
    -   [Squeeze and Excitation Networks](https://arxiv.org/abs/1709.01507)
    -   [Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks](https://arxiv.org/abs/1803.02579)
    """

    cse = squeeze_excite_block(input_tensor, ratio)
    sse = spatial_squeeze_excite_block(input_tensor)

    x = add([cse, sse])
    return x 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def add(self, s, a, r, d, s2):
        """Add an experience to the buffer"""
        # S represents current state, a is action,
        # r is reward, d is whether it is the end, 
        # and s2 is next state
        if np.any(~np.isfinite(s)) or np.any(~np.isfinite(s2)):
            # TODO proper handling of infinite values somewhere !!!!
            return

        experience = (s, a, r, d, s2)
        if self.count < self.buffer_size:
            self.buffer.append(experience)
            self.count += 1
        else:
            self.buffer.popleft()
            self.buffer.append(experience) 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def __init__(self, action_size, observation_size, lr=1e-5,
                 training_param=TrainingParam()):
        RLQvalue.__init__(self, action_size, observation_size, lr, training_param)
        # TODO add as meta param the number of "Q" you want to use (here 2)
        # TODO add as meta param size and types of the networks
        self.average_reward = 0
        self.life_spent = 1
        self.qvalue_evolution = np.zeros((0,))
        self.Is_nan = False

        self.model_value_target = None
        self.model_value = None
        self.model_Q = None
        self.model_Q2 = None
        self.model_policy = None

        self.construct_q_network() 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def expanding_layer_2D(input, neurons, concatenate_link, ba_norm,
                       ba_norm_momentum):
    up = concatenate([Conv2DTranspose(neurons, (2, 2), strides=(2, 2),
                     padding='same')(input), concatenate_link], axis=-1)
    conv1 = Conv2D(neurons, (3, 3,), activation='relu', padding='same')(up)
    if ba_norm : conv1 = BatchNormalization(momentum=ba_norm_momentum)(conv1)
    conv2 = Conv2D(neurons, (3, 3), activation='relu', padding='same')(conv1)
    if ba_norm : conv2 = BatchNormalization(momentum=ba_norm_momentum)(conv2)
    shortcut = Conv2D(neurons, (1, 1), activation='relu', padding="same")(up)
    add_layer = add([shortcut, conv2])
    return add_layer

#-----------------------------------------------------#
#                   Subroutines 3D                    #
#-----------------------------------------------------#
# Create a contracting layer 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def residual(x, num_filters,
             kernel_size=(3, 3),
             activation='relu',
             pool_strides=(2, 2),
             max_pooling=True):
    "Residual block."
    if max_pooling:
        res = layers.Conv2D(num_filters, kernel_size=(
            1, 1), strides=pool_strides, padding='same')(x)
    elif num_filters != keras.backend.int_shape(x)[-1]:
        res = layers.Conv2D(num_filters, kernel_size=(1, 1), padding='same')(x)
    else:
        res = x

    x = sep_conv(x, num_filters, kernel_size, activation)
    x = sep_conv(x, num_filters, kernel_size, activation)
    if max_pooling:
        x = layers.MaxPooling2D(
            kernel_size, strides=pool_strides, padding='same')(x)

    x = layers.add([x, res])
    return x 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def channel_spatial_squeeze_excite(input, ratio=16):
    ''' Create a spatial squeeze-excite block

    Args:
        input: input tensor
        filters: number of output filters

    Returns: a keras tensor

    References
    -   [Squeeze and Excitation Networks](https://arxiv.org/abs/1709.01507)
    -   [Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks](https://arxiv.org/abs/1803.02579)
    '''

    cse = squeeze_excite_block(input, ratio)
    sse = spatial_squeeze_excite_block(input)

    x = add([cse, sse])
    return x 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def bottleneck_block(input, filters=64, cardinality=8, strides=1, weight_decay=5e-4):
    init = input
    grouped_channels = int(filters / cardinality)

    if init.shape[-1] != 2 * filters:
        init = Conv2D(filters * 2, (1, 1), padding='same', strides=(strides, strides),
                      use_bias=False, kernel_initializer='he_normal', kernel_regularizer=l2(weight_decay))(init)
        init = BatchNormalization(axis=3)(init)

    x = Conv2D(filters, (1, 1), padding='same', use_bias=False,
               kernel_initializer='he_normal', kernel_regularizer=l2(weight_decay))(input)
    x = BatchNormalization(axis=3)(x)
    x = Activation('relu')(x)

    x = grouped_convolution_block(x, grouped_channels, cardinality, strides, weight_decay)
    x = Conv2D(filters * 2, (1, 1), padding='same', use_bias=False, kernel_initializer='he_normal',
               kernel_regularizer=l2(weight_decay))(x)
    x = BatchNormalization(axis=3)(x)

    x = add([init, x])
    x = Activation('relu')(x)
    return x 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def construct_q_network(self):
        # Uses the network architecture found in DeepMind paper
        # The inputs and outputs size have changed, as well as replacing the convolution by dense layers.
        self.model = Sequential()
        
        input_layer = Input(shape=(self.observation_size*self.training_param.NUM_FRAMES,))
        lay1 = Dense(self.observation_size*self.training_param.NUM_FRAMES)(input_layer)
        lay1 = Activation('relu')(lay1)
        
        lay2 = Dense(self.observation_size)(lay1)
        lay2 = Activation('relu')(lay2)
        
        lay3 = Dense(2*self.action_size)(lay2)
        lay3 = Activation('relu')(lay3)
        
        fc1 = Dense(self.action_size)(lay3)
        advantage = Dense(self.action_size)(fc1)
        fc2 = Dense(self.action_size)(lay3)
        value = Dense(1)(fc2)
        
        meaner = Lambda(lambda x: K.mean(x, axis=1) )
        mn_ = meaner(advantage)  
        tmp = subtract([advantage, mn_])
        policy = add([tmp, value])

        self.model = Model(inputs=[input_layer], outputs=[policy])
        self.model.compile(loss='mse', optimizer=Adam(lr=self.lr_))

        self.target_model = Model(inputs=[input_layer], outputs=[policy])
        self.target_model.compile(loss='mse', optimizer=Adam(lr=self.lr_))
        print("Successfully constructed networks.")


# This class implements the "Sof Actor Critic" model.
# It is a custom implementation, courtesy to Clement Goubet
# The original paper is: https://arxiv.org/abs/1801.01290 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def identity_block(self, input_tensor, kernel_size, filters, stage, block):
        conv_name_base = f'res{stage}_{block}_branch'

        x = Conv2D(filters,
                   kernel_size=kernel_size,
                   strides=1,
                   activation=None,
                   padding='same',
                   kernel_initializer='glorot_uniform',
                   kernel_regularizer=regularizers.l2(l=0.0001),
                   name=conv_name_base + '_2a')(input_tensor)
        x = BatchNormalization(name=conv_name_base + '_2a_bn')(x)
        x = self.clipped_relu(x)

        x = Conv2D(filters,
                   kernel_size=kernel_size,
                   strides=1,
                   activation=None,
                   padding='same',
                   kernel_initializer='glorot_uniform',
                   kernel_regularizer=regularizers.l2(l=0.0001),
                   name=conv_name_base + '_2b')(x)
        x = BatchNormalization(name=conv_name_base + '_2b_bn')(x)

        x = self.clipped_relu(x)

        x = layers.add([x, input_tensor])
        x = self.clipped_relu(x)
        return x 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def build_model(board_size=4, board_layers=16, outputs=4, filters=64, residual_blocks=4):
  # Functional API model
  inputs = layers.Input(shape=(board_size * board_size * board_layers,))
  x = layers.Reshape((board_size, board_size, board_layers))(inputs)

  # Initial convolutional block
  x = layers.Conv2D(filters=filters, kernel_size=(3, 3), padding='same')(x)
  x = layers.BatchNormalization()(x)
  x = layers.Activation('relu')(x)

  # residual blocks
  for i in range(residual_blocks):
    # x at the start of a block
    temp_x = layers.Conv2D(filters=filters, kernel_size=(3, 3), padding='same')(x)
    temp_x = layers.BatchNormalization()(temp_x)
    temp_x = layers.Activation('relu')(temp_x)
    temp_x = layers.Conv2D(filters=filters, kernel_size=(3, 3), padding='same')(temp_x)
    temp_x = layers.BatchNormalization()(temp_x)
    x = layers.add([x, temp_x])
    x = layers.Activation('relu')(x)

  # policy head
  x = layers.Conv2D(filters=2, kernel_size=(1, 1), padding='same')(x)
  x = layers.BatchNormalization()(x)
  x = layers.Activation('relu')(x)
  x = layers.Flatten()(x)
  predictions = layers.Dense(outputs, activation='softmax')(x)

  # Create model
  return models.Model(inputs=inputs, outputs=predictions) 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def contracting_layer_2D(input, neurons, ba_norm, ba_norm_momentum):
    conv1 = Conv2D(neurons, (3,3), activation='relu', padding='same')(input)
    if ba_norm : conv1 = BatchNormalization(momentum=ba_norm_momentum)(conv1)
    conv2 = Conv2D(neurons, (3,3), activation='relu', padding='same')(conv1)
    if ba_norm : conv2 = BatchNormalization(momentum=ba_norm_momentum)(conv2)
    shortcut = Conv2D(neurons, (1, 1), activation='relu', padding="same")(input)
    add_layer = add([shortcut, conv2])
    pool = MaxPooling2D(pool_size=(2, 2))(add_layer)
    return pool, add_layer

# Create the middle layer between the contracting and expanding layers 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def middle_layer_2D(input, neurons, ba_norm, ba_norm_momentum):
    conv_m1 = Conv2D(neurons, (3, 3), activation='relu', padding='same')(input)
    if ba_norm : conv_m1 = BatchNormalization(momentum=ba_norm_momentum)(conv_m1)
    conv_m2 = Conv2D(neurons, (3, 3), activation='relu', padding='same')(conv_m1)
    if ba_norm : conv_m2 = BatchNormalization(momentum=ba_norm_momentum)(conv_m2)
    shortcut = Conv2D(neurons, (1, 1), activation='relu', padding="same")(input)
    add_layer = add([shortcut, conv_m2])
    return add_layer

# Create an expanding layer 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def contracting_layer_3D(input, neurons, ba_norm, ba_norm_momentum):
    conv1 = Conv3D(neurons, (3,3,3), activation='relu', padding='same')(input)
    if ba_norm : conv1 = BatchNormalization(momentum=ba_norm_momentum)(conv1)
    conv2 = Conv3D(neurons, (3,3,3), activation='relu', padding='same')(conv1)
    if ba_norm : conv2 = BatchNormalization(momentum=ba_norm_momentum)(conv2)
    shortcut = Conv3D(neurons, (1, 1, 1), activation='relu', padding="same")(input)
    add_layer = add([shortcut, conv2])
    pool = MaxPooling3D(pool_size=(2, 2, 2))(add_layer)
    return pool, add_layer

# Create the middle layer between the contracting and expanding layers 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def middle_layer_3D(input, neurons, ba_norm, ba_norm_momentum):
    conv_m1 = Conv3D(neurons, (3, 3, 3), activation='relu', padding='same')(input)
    if ba_norm : conv_m1 = BatchNormalization(momentum=ba_norm_momentum)(conv_m1)
    conv_m2 = Conv3D(neurons, (3, 3, 3), activation='relu', padding='same')(conv_m1)
    if ba_norm : conv_m2 = BatchNormalization(momentum=ba_norm_momentum)(conv_m2)
    shortcut = Conv3D(neurons, (1, 1, 1), activation='relu', padding="same")(input)
    add_layer = add([shortcut, conv_m2])
    return add_layer

# Create an expanding layer 

# 需要导入模块: from tensorflow.keras import layers [as 别名]
# 或者: from tensorflow.keras.layers import add [as 别名]
def MultiResBlock_3D(U, inp, alpha = 1.67):
    '''
    MultiRes Block

    Arguments:
        U {int} -- Number of filters in a corrsponding UNet stage
        inp {keras layer} -- input layer

    Returns:
        [keras layer] -- [output layer]
    '''

    W = alpha * U

    shortcut = inp

    shortcut = conv3d_bn(shortcut, int(W*0.167) + int(W*0.333) + int(W*0.5), 1, 1, 1, activation=None, padding='same')

    conv3x3 = conv3d_bn(inp, int(W*0.167), 3, 3, 3, activation='relu', padding='same')

    conv5x5 = conv3d_bn(conv3x3, int(W*0.333), 3, 3, 3, activation='relu', padding='same')

    conv7x7 = conv3d_bn(conv5x5, int(W*0.5), 3, 3, 3, activation='relu', padding='same')

    out = concatenate([conv3x3, conv5x5, conv7x7], axis=4)
    out = BatchNormalization(axis=4)(out)

    out = add([shortcut, out])
    out = Activation('relu')(out)
    out = BatchNormalization(axis=4)(out)

    return out