当前位置: 首页>>代码示例>>Python>>正文


Python backend.sigmoid方法代码示例

本文整理汇总了Python中keras.backend.sigmoid方法的典型用法代码示例。如果您正苦于以下问题:Python backend.sigmoid方法的具体用法?Python backend.sigmoid怎么用?Python backend.sigmoid使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在keras.backend的用法示例。


在下文中一共展示了backend.sigmoid方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: weather_l2

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def weather_l2(hidden_nums=100,l2=0.01): 
    input_img = Input(shape=(37,))
    hn = Dense(hidden_nums, activation='relu')(input_img)
    hn = Dense(hidden_nums, activation='relu',
               kernel_regularizer=regularizers.l2(l2))(hn)
    out_u = Dense(37, activation='sigmoid',                 
                  name='ae_part')(hn)
    out_sig = Dense(37, activation='linear', 
                    name='pred_part')(hn)
    out_both = concatenate([out_u, out_sig], axis=1, name = 'concatenate')

    #weather_model = Model(input_img, outputs=[out_ae, out_pred])
    mve_model = Model(input_img, outputs=[out_both])
    mve_model.compile(optimizer='adam', loss=mve_loss, loss_weights=[1.])
    
    return mve_model 
开发者ID:BruceBinBoxing,项目名称:Deep_Learning_Weather_Forecasting,代码行数:18,代码来源:weather_model.py

示例2: CausalCNN

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def CausalCNN(n_filters, lr, decay, loss, 
               seq_len, input_features, 
               strides_len, kernel_size,
               dilation_rates):

    inputs = Input(shape=(seq_len, input_features), name='input_layer')   
    x=inputs
    for dilation_rate in dilation_rates:
        x = Conv1D(filters=n_filters,
               kernel_size=kernel_size, 
               padding='causal',
               dilation_rate=dilation_rate,
               activation='linear')(x) 
        x = BatchNormalization()(x)
        x = Activation('relu')(x)

    #x = Dense(7, activation='relu', name='dense_layer')(x)
    outputs = Dense(3, activation='sigmoid', name='output_layer')(x)
    causalcnn = Model(inputs, outputs=[outputs])

    return causalcnn 
开发者ID:BruceBinBoxing,项目名称:Deep_Learning_Weather_Forecasting,代码行数:23,代码来源:weather_model.py

示例3: weather_ae

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def weather_ae(layers, lr, decay, loss, 
               input_len, input_features):
    
    inputs = Input(shape=(input_len, input_features), name='input_layer')
    
    for i, hidden_nums in enumerate(layers):
        if i==0:
            hn = Dense(hidden_nums, activation='relu')(inputs)
        else:
            hn = Dense(hidden_nums, activation='relu')(hn)

    outputs = Dense(3, activation='sigmoid', name='output_layer')(hn)

    weather_model = Model(inputs, outputs=[outputs])

    return weather_model 
开发者ID:BruceBinBoxing,项目名称:Deep_Learning_Weather_Forecasting,代码行数:18,代码来源:weather_model.py

示例4: get_model

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def get_model(num_users, num_items, latent_dim, regs=[0,0]):
    # Input variables
    user_input = Input(shape=(1,), dtype='int32', name = 'user_input')
    item_input = Input(shape=(1,), dtype='int32', name = 'item_input')

    MF_Embedding_User = Embedding(input_dim = num_users, output_dim = latent_dim, name = 'user_embedding',
                                  init = init_normal, W_regularizer = l2(regs[0]), input_length=1)
    MF_Embedding_Item = Embedding(input_dim = num_items, output_dim = latent_dim, name = 'item_embedding',
                                  init = init_normal, W_regularizer = l2(regs[1]), input_length=1)   
    
    # Crucial to flatten an embedding vector!
    user_latent = Flatten()(MF_Embedding_User(user_input))
    item_latent = Flatten()(MF_Embedding_Item(item_input))
    
    # Element-wise product of user and item embeddings 
    predict_vector = merge([user_latent, item_latent], mode = 'mul')
    
    # Final prediction layer
    #prediction = Lambda(lambda x: K.sigmoid(K.sum(x)), output_shape=(1,))(predict_vector)
    prediction = Dense(1, activation='sigmoid', init='lecun_uniform', name = 'prediction')(predict_vector)
    
    model = Model(input=[user_input, item_input], 
                output=prediction)

    return model 
开发者ID:hexiangnan,项目名称:neural_collaborative_filtering,代码行数:27,代码来源:GMF.py

示例5: __init__

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def __init__(self, halt_epsilon=0.01, time_penalty=0.01, **kwargs):
        """
        :param halt_epsilon: a small constant that allows computation to halt
            after a single update (sigmoid never reaches exactly 1.0)
        :param time_penalty: parameter that weights the relative cost
            of computation versus error. The larger it is, the less
            computational steps the network will try to make and vice versa.
            The default value of 0.01 works well for Transformer.
        :param kwargs: Any standard parameters for a layer in Keras (like name)
        """
        self.halt_epsilon = halt_epsilon
        self.time_penalty = time_penalty
        self.ponder_cost = None
        self.weighted_output = None
        self.zeros_like_input = None
        self.zeros_like_halting = None
        self.ones_like_halting = None
        self.halt_budget = None
        self.remainder = None
        self.active_steps = None
        super().__init__(**kwargs) 
开发者ID:kpot,项目名称:keras-transformer,代码行数:23,代码来源:transformer.py

示例6: step

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def step(self, inputs, states):
        h_tm1 = states[0]  # previous memory
        #B_U = states[1]  # dropout matrices for recurrent units
        #B_W = states[2]
        h_tm1a = K.dot(h_tm1, self.Wa)
        eij = K.dot(K.tanh(h_tm1a + K.dot(inputs[:, :self.h_dim], self.Ua)), self.Va)
        eijs = K.repeat_elements(eij, self.h_dim, axis=1)

        #alphaij = K.softmax(eijs) # batchsize * lenh       h batchsize * lenh * ndim
        #ci = K.permute_dimensions(K.permute_dimensions(self.h, [2,0,1]) * alphaij, [1,2,0])
        #cisum = K.sum(ci, axis=1)
        cisum = eijs*inputs[:, :self.h_dim]
        #print(K.shape(cisum), cisum.shape, ci.shape, self.h.shape, alphaij.shape, x.shape)

        zr = K.sigmoid(K.dot(inputs[:, self.h_dim:], self.Wzr) + K.dot(h_tm1, self.Uzr) + K.dot(cisum, self.Czr))
        zi = zr[:, :self.units]
        ri = zr[:, self.units: 2 * self.units]
        si_ = K.tanh(K.dot(inputs[:, self.h_dim:], self.W) + K.dot(ri*h_tm1, self.U) + K.dot(cisum, self.C))
        si = (1-zi) * h_tm1 + zi * si_
        return si, [si] #h_tm1, [h_tm1] 
开发者ID:wentaozhu,项目名称:recurrent-attention-for-QA-SQUAD-based-on-keras,代码行数:22,代码来源:rnnlayer.py

示例7: call

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def call(self, inputs):
        if self.data_format == 'channels_first':
            sq = K.mean(inputs, [2, 3])
        else:
            sq = K.mean(inputs, [1, 2])

        ex = K.dot(sq, self.kernel1)
        if self.use_bias:
            ex = K.bias_add(ex, self.bias1)
        ex= K.relu(ex)

        ex = K.dot(ex, self.kernel2)
        if self.use_bias:
            ex = K.bias_add(ex, self.bias2)
        ex= K.sigmoid(ex)

        if self.data_format == 'channels_first':
            ex = K.expand_dims(ex, -1)
            ex = K.expand_dims(ex, -1)
        else:
            ex = K.expand_dims(ex, 1)
            ex = K.expand_dims(ex, 1)

        return inputs * ex 
开发者ID:DingKe,项目名称:nn_playground,代码行数:26,代码来源:layers.py

示例8: call

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def call(self, x):
        # input shape: (nb_samples, time (padded with zeros), input_dim)
        # note that the .build() method of subclasses MUST define
        # self.input_spec with a complete input shape.
        input_shape = self.input_spec[0].shape

        if self.window_size > 1:
            x = K.temporal_padding(x, (self.window_size-1, 0))
        x = K.expand_dims(x, 2)  # add a dummy dimension

        # z, g
        output = K.conv2d(x, self.kernel, strides=self.strides,
                          padding='valid',
                          data_format='channels_last')
        output = K.squeeze(output, 2)  # remove the dummy dimension
        if self.use_bias:
            output = K.bias_add(output, self.bias, data_format='channels_last')
        z  = output[:, :, :self.output_dim]
        g = output[:, :, self.output_dim:]

        return self.activation(z) * K.sigmoid(g) 
开发者ID:DingKe,项目名称:nn_playground,代码行数:23,代码来源:gcnn.py

示例9: step

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def step(self, inputs, states):
        vP_t = inputs
        hP_tm1 = states[0]
        _ = states[1:3] # ignore internal dropout/masks 
        vP, WP_v, WPP_v, v, W_g2 = states[3:8]
        vP_mask, = states[8:]

        WP_v_Dot = K.dot(vP, WP_v)
        WPP_v_Dot = K.dot(K.expand_dims(vP_t, axis=1), WPP_v)

        s_t_hat = K.tanh(WPP_v_Dot + WP_v_Dot)
        s_t = K.dot(s_t_hat, v)
        s_t = K.batch_flatten(s_t)

        a_t = softmax(s_t, mask=vP_mask, axis=1)

        c_t = K.batch_dot(a_t, vP, axes=[1, 1])
        
        GRU_inputs = K.concatenate([vP_t, c_t])
        g = K.sigmoid(K.dot(GRU_inputs, W_g2))
        GRU_inputs = g * GRU_inputs
        
        hP_t, s = super(SelfAttnGRU, self).step(GRU_inputs, states)

        return hP_t, s 
开发者ID:YerevaNN,项目名称:R-NET-in-Keras,代码行数:27,代码来源:SelfAttnGRU.py

示例10: step

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def step(self, inputs, states):
        uP_t = inputs
        vP_tm1 = states[0]
        _ = states[1:3] # ignore internal dropout/masks
        uQ, WQ_u, WP_v, WP_u, v, W_g1 = states[3:9]
        uQ_mask, = states[9:10]

        WQ_u_Dot = K.dot(uQ, WQ_u) #WQ_u
        WP_v_Dot = K.dot(K.expand_dims(vP_tm1, axis=1), WP_v) #WP_v
        WP_u_Dot = K.dot(K.expand_dims(uP_t, axis=1), WP_u) # WP_u

        s_t_hat = K.tanh(WQ_u_Dot + WP_v_Dot + WP_u_Dot)

        s_t = K.dot(s_t_hat, v) # v
        s_t = K.batch_flatten(s_t)
        a_t = softmax(s_t, mask=uQ_mask, axis=1)
        c_t = K.batch_dot(a_t, uQ, axes=[1, 1])

        GRU_inputs = K.concatenate([uP_t, c_t])
        g = K.sigmoid(K.dot(GRU_inputs, W_g1))  # W_g1
        GRU_inputs = g * GRU_inputs
        vP_t, s = super(QuestionAttnGRU, self).step(GRU_inputs, states)

        return vP_t, s 
开发者ID:YerevaNN,项目名称:R-NET-in-Keras,代码行数:26,代码来源:QuestionAttnGRU.py

示例11: weather_mve

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def weather_mve(hidden_nums=100): 
    input_img = Input(shape=(37,))
    hn = Dense(hidden_nums, activation='relu')(input_img)
    hn = Dense(hidden_nums, activation='relu')(hn)
    out_u = Dense(37, activation='sigmoid', name='ae_part')(hn)
    out_sig = Dense(37, activation='linear', name='pred_part')(hn)
    out_both = concatenate([out_u, out_sig], axis=1, name = 'concatenate')

    #weather_model = Model(input_img, outputs=[out_ae, out_pred])
    mve_model = Model(input_img, outputs=[out_both])
    mve_model.compile(optimizer='adam', loss=mve_loss, loss_weights=[1.])
    
    return mve_model 
开发者ID:BruceBinBoxing,项目名称:Deep_Learning_Weather_Forecasting,代码行数:15,代码来源:weather_model.py

示例12: weather_mse

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def weather_mse():
    input_img = Input(shape=(37,))
    hn = Dense(100, activation='relu')(input_img)
    hn = Dense(100, activation='relu')(hn)
    out_pred = Dense(37, activation='sigmoid', name='pred_part')(hn)
    weather_model = Model(input_img, outputs=[out_pred])
    weather_model.compile(optimizer='adam', loss='mse',loss_weights=[1.])
    
    return weather_model 
开发者ID:BruceBinBoxing,项目名称:Deep_Learning_Weather_Forecasting,代码行数:11,代码来源:weather_model.py

示例13: weather_fusion

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def weather_fusion():
    input_img = Input(shape=(37,))
    hn = Dense(100, activation='relu')(input_img)
    hn = Dense(100, activation='relu')(hn)
    #out_ae = Dense(37, activation='sigmoid', name='ae_part')(hn)
    out_pred = Dense(37, activation='sigmoid', name='pred_part')(hn)

    weather_model = Model(input_img, outputs=[out_ae, out_pred])
    weather_model.compile(optimizer='adam', loss='mse',loss_weights=[1.5, 1.])

    return weather_model 
开发者ID:BruceBinBoxing,项目名称:Deep_Learning_Weather_Forecasting,代码行数:13,代码来源:weather_model.py

示例14: swish

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def swish(x):
        return (K.sigmoid(x) * x) 
开发者ID:BruceBinBoxing,项目名称:Deep_Learning_Weather_Forecasting,代码行数:4,代码来源:Load_model_and_predict.py

示例15: pair_loss

# 需要导入模块: from keras import backend [as 别名]
# 或者: from keras.backend import sigmoid [as 别名]
def pair_loss(y_true, y_pred):
    y_true = tf.cast(y_true, tf.int32)
    parts = tf.dynamic_partition(y_pred, y_true, 2)
    y_pos = parts[1]
    y_neg = parts[0]
    y_pos = tf.expand_dims(y_pos, 0)
    y_neg = tf.expand_dims(y_neg, -1)
    out = K.sigmoid(y_neg - y_pos)
    return K.mean(out) 
开发者ID:minerva-ml,项目名称:steppy-toolkit,代码行数:11,代码来源:contrib.py


注:本文中的keras.backend.sigmoid方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。