tf_models.py 文件源码

def ED_TCN_atrous(n_nodes, conv_len, n_classes, n_feat, max_len, 
                loss='categorical_crossentropy', causal=False, 
                optimizer="rmsprop", activation='norm_relu',
                return_param_str=False):
    n_layers = len(n_nodes)

    inputs = Input(shape=(None,n_feat))
    model = inputs

    # ---- Encoder ----
    for i in range(n_layers):
        # Pad beginning of sequence to prevent usage of future data
        if causal: model = ZeroPadding1D((conv_len//2,0))(model)
        model = AtrousConvolution1D(n_nodes[i], conv_len, atrous_rate=i+1, border_mode='same')(model)
        if causal: model = Cropping1D((0,conv_len//2))(model)

        model = SpatialDropout1D(0.3)(model)

        if activation=='norm_relu': 
            model = Activation('relu')(model)            
            model = Lambda(channel_normalization, name="encoder_norm_{}".format(i))(model)
        elif activation=='wavenet': 
            model = WaveNet_activation(model) 
        else:
            model = Activation(activation)(model)            

    # ---- Decoder ----
    for i in range(n_layers):
        if causal: model = ZeroPadding1D((conv_len//2,0))(model)
        model = AtrousConvolution1D(n_nodes[-i-1], conv_len, atrous_rate=n_layers-i, border_mode='same')(model)      
        if causal: model = Cropping1D((0,conv_len//2))(model)

        model = SpatialDropout1D(0.3)(model)

        if activation=='norm_relu': 
            model = Activation('relu')(model)
            model = Lambda(channel_normalization, name="decoder_norm_{}".format(i))(model)
        elif activation=='wavenet': 
            model = WaveNet_activation(model) 
        else:
            model = Activation(activation)(model)

    # Output FC layer
    model = TimeDistributed(Dense(n_classes, activation="softmax" ))(model)

    model = Model(input=inputs, output=model)

    model.compile(loss=loss, optimizer=optimizer, sample_weight_mode="temporal", metrics=['accuracy'])

    if return_param_str:
        param_str = "ED-TCNa_C{}_L{}".format(conv_len, n_layers)
        if causal:
            param_str += "_causal"

        return model, param_str
    else:
        return model