1. 模块列表
  2. 函数列表
  3. keras.initializers.RandomNormal()

Python keras.initializers 模块，RandomNormal() 实例源码

我们从Python开源项目中，提取了以下26个代码示例，用于说明如何使用keras.initializers.RandomNormal()。

项目：deform-conv    作者：felixlaumon    | 项目源码 | 文件源码 
def __init__(self, filters, init_normal_stddev=0.01, **kwargs):
        """Init

        Parameters
        ----------
        filters : int
            Number of channel of the input feature map
        init_normal_stddev : float
            Normal kernel initialization
        **kwargs:
            Pass to superclass. See Con2D layer in Keras
        """

        self.filters = filters
        super(ConvOffset2D, self).__init__(
            self.filters * 2, (3, 3), padding='same', use_bias=False,
            kernel_initializer=RandomNormal(0, init_normal_stddev),
            **kwargs
        )
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkSmall(inputDim, inputLength):
    baseNetwork = Sequential()
    baseNetwork.add(Embedding(input_dim=inputDim,
                              output_dim=inputDim, input_length=inputLength))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkLarge(inputDim, inputLength):
    baseNetwork = Sequential()
    baseNetwork.add(Embedding(input_dim=inputDim,
                              output_dim=inputDim, input_length=inputLength))
    baseNetwork.add(Conv1D(1024, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(1024, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(2048, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    baseNetwork.add(Dense(2048, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkSmall(inputDim, inputLength):
    baseNetwork = Sequential()
    baseNetwork.add(Embedding(input_dim=inputDim,
                              output_dim=inputDim, input_length=inputLength))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkLarge(inputDim, inputLength):
    baseNetwork = Sequential()
    baseNetwork.add(Embedding(input_dim=inputDim,
                              output_dim=inputDim, input_length=inputLength))
    baseNetwork.add(Conv1D(1024, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(1024, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(2048, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    baseNetwork.add(Dense(2048, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkSmall(inputLength, inputDim):
    baseNetwork = Sequential()
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu',  input_shape=(inputLength, inputDim),
                           kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkSmall(inputDim, inputLength):
    baseNetwork = Sequential()
    baseNetwork.add(Embedding(input_dim=inputDim,
                              output_dim=inputDim, input_length=inputLength))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkLarge(inputDim, inputLength):
    baseNetwork = Sequential()
    baseNetwork.add(Embedding(input_dim=inputDim,
                              output_dim=inputDim, input_length=inputLength))
    baseNetwork.add(Conv1D(1024, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(1024, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(2048, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    baseNetwork.add(Dense(2048, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkSmall(inputDim, inputLength):
    baseNetwork = Sequential()
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkLarge(inputDim, inputLength):
    baseNetwork = Sequential()
    baseNetwork.add(Conv1D(1024, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(1024, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(2048, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    baseNetwork.add(Dense(2048, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def netSigmoid(inputLength, inputDim):
    baseNetwork = Sequential()
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu',  input_shape=(inputLength, inputDim),
                           kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkSmall(inputLength, inputDim):
    baseNetwork = Sequential()
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu',  input_shape=(inputLength, inputDim),
                           kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    baseNetwork.add(Dense(1024, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkSmall(inputDim, inputLength):
        baseNetwork = Sequential()
        baseNetwork.add(Embedding(input_dim=inputDim, output_dim=inputDim, input_length=inputLength))
        baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
        baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
        baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
        baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
        baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
        baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
        baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
        baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
        baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
        baseNetwork.add(Flatten())
        baseNetwork.add(Dense(1024, activation='relu'))
        baseNetwork.add(Dropout(0.5))
        baseNetwork.add(Dense(1024, activation='relu'))
        baseNetwork.add(Dropout(0.5))
        return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkLarge(inputDim, inputLength):
        baseNetwork = Sequential()
        baseNetwork.add(Embedding(input_dim=inputDim, output_dim=inputDim, input_length=inputLength))
        baseNetwork.add(Conv1D(1024, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
        baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
        baseNetwork.add(Conv1D(1024, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
        baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
        baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
        baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
        baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
        baseNetwork.add(Conv1D(1024, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(mean=0.0, stddev=0.02), bias_initializer=RandomNormal(mean=0.0, stddev=0.02)))
        baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
        baseNetwork.add(Flatten())
        baseNetwork.add(Dense(2048, activation='relu'))
        baseNetwork.add(Dropout(0.5))
        baseNetwork.add(Dense(2048, activation='relu'))
        baseNetwork.add(Dropout(0.5))
        return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkSmall(inputLength, inputDim):
    baseNetwork = Sequential()
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu',  input_shape=(inputLength, inputDim),
                           kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(128, activation='relu'))
    baseNetwork.add(Dropout(0.2))
    baseNetwork.add(Dense(128, activation='relu'))
    baseNetwork.add(Dropout(0.2))
    return baseNetwork
项目：WGAN-in-Keras    作者：tonyabracadabra    | 项目源码 | 文件源码 
def __init__(self):
        self.x_dim = 784
        self.name = 'mnist/dcgan/discriminator'
        self.initializer = RandomNormal(mean=0.0, stddev=0.02, seed=None)
        self.regularizer = regularizers.l2(2.5e-5)
项目：WGAN-in-Keras    作者：tonyabracadabra    | 项目源码 | 文件源码 
def __init__(self):
        self.z_dim = 100
        self.x_dim = 784
        self.name = 'mnist/dcgan/generator'
        self.initializer = RandomNormal(mean=0.0, stddev=0.02, seed=None)
        self.regularizer = regularizers.l2(2.5e-5)
项目：WGAN-in-Keras    作者：tonyabracadabra    | 项目源码 | 文件源码 
def __init__(self):
        self.x_dim = 784
        self.name = 'mnist/dcgan/discriminator'
        self.initializer = RandomNormal(mean=0.0, stddev=0.02, seed=None)
        self.regularizer = regularizers.l2(2.5e-5)
项目：WGAN-in-Keras    作者：tonyabracadabra    | 项目源码 | 文件源码 
def __init__(self):
        self.z_dim = 100
        self.x_dim = 784
        self.name = 'mnist/dcgan/generator'
        self.initializer = RandomNormal(mean=0.0, stddev=0.02, seed=None)
        self.regularizer = regularizers.l2(2.5e-5)
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createSplitBaseNetworkSmall(inputLength, inputDim):
    baseNetwork = Sequential()
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', input_shape=(inputLength, inputDim), 
        kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def netC256P3C256P3C256P3f128(inputLength, inputDim):
    baseNetwork = Sequential()
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu',  input_shape=(inputLength, inputDim),
                           kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(128, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def netC256P3C256P3f32(inputLength, inputDim):
    baseNetwork = Sequential()
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu',  input_shape=(inputLength, inputDim),
                           kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(32, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def netC256P3C256P3f64(inputLength, inputDim):
    baseNetwork = Sequential()
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu',  input_shape=(inputLength, inputDim),
                           kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(64, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createBaseNetworkSmaller(inputLength, inputDim):
    baseNetwork = Sequential()
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu',  input_shape=(inputLength, inputDim),
                           kernel_initializer=RandomNormal(mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 3, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Flatten())
    baseNetwork.add(Dense(32, activation='relu'))
    baseNetwork.add(Dropout(0.5))
    return baseNetwork
项目：kaggle-quora-question-pairs    作者：voletiv    | 项目源码 | 文件源码 
def createSplitBaseNetworkSmall(inputDim, inputLength):
    baseNetwork = Sequential()
    baseNetwork.add(Embedding(input_dim=inputDim,
                              output_dim=inputDim, input_length=inputLength))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    baseNetwork.add(Conv1D(256, 7, strides=1, padding='valid', activation='relu', kernel_initializer=RandomNormal(
        mean=0.0, stddev=0.05), bias_initializer=RandomNormal(mean=0.0, stddev=0.05)))
    baseNetwork.add(MaxPooling1D(pool_size=3, strides=3))
    return baseNetwork
项目：gym-sandbox    作者：suqi    | 项目源码 | 文件源码 
def create_actor_network(self, state_size,action_dim):
        print("Now we build the model")
        S = Input(shape=[state_size])   
        h0 = Dense(HIDDEN1_UNITS, activation='relu')(S)
        h1 = Dense(HIDDEN2_UNITS, activation='relu')(h0)

        # ,init=lambda shape, name: RandomNormal(shape, scale=1e-4, name=name)
        V = Dense(action_dim,activation='tanh')(h1)
        model = Model(input=S,output=V)
        return model, model.trainable_weights, S