0

我正在尝试建立一个结合了cnn和lstm的模型。我想对 cnn 的输入进行多变量化，并将输出顺序放入 LSTM 的输入中。但是，合并 cnn 输出时存在问题。如果您使用连接，它将拉伸到axis = -1，如图所示。但我会把它放在 lstm 结构中，所以我想依次增加它。但是除了连接之外，我没有找到任何要合并的函数。我想要的形状是下图中的 (None, 6, 1904)。我能做些什么？

下面是我的构建代码。

def build_model():
    in_layers, out_layers = [], []
    for i in range(in_len):
        inputs = Input(shape=(row,col, channel))
        conv1 = Conv2D(4, (12, 12), activation='relu')(inputs)
        pool1 = pooling.MaxPooling2D(pool_size=(4,4))(conv1)
        conv2 = Conv2D(4, (7, 7) , activation='relu')(pool1)
        pool2 = pooling.MaxPooling2D(pool_size=(3,3))(conv2)
        conv3 = Conv2D(8, (5, 5) , activation='relu')(pool2)
        pool3 = pooling.MaxPooling2D(pool_size=(2,2))(conv3)
        flat = Flatten()(pool3)
        # store layers
        in_layers.append(inputs)
        out_layers.append(flat)
        print(type(flat))
    merged = concatenate(out_layers)
    model = Model(inputs=in_layers, outputs=merged)
    plot_model(model, show_shapes=True, to_file='cnn_lstm_real.png')

    return model

在此处输入图像描述

4

1 回答 1

0

您想要的仍然是串联，但在不同的新轴上。连接层和函数允许指定轴，所以你可以这样做：

def build_model():
    in_layers, out_layers = [], []
    for i in range(in_len):
        inputs = Input(shape=(row,col, channel))
        conv1 = Conv2D(4, (12, 12), activation='relu')(inputs)
        pool1 = pooling.MaxPooling2D(pool_size=(4,4))(conv1)
        conv2 = Conv2D(4, (7, 7) , activation='relu')(pool1)
        pool2 = pooling.MaxPooling2D(pool_size=(3,3))(conv2)
        conv3 = Conv2D(8, (5, 5) , activation='relu')(pool2)
        pool3 = pooling.MaxPooling2D(pool_size=(2,2))(conv3)
        flat = Flatten()(pool3)
        flat = Reshape((1, -1))(flat)
        # store layers
        in_layers.append(inputs)
        out_layers.append(flat)

    merged = concatenate(out_layers, axis = 1)
    model = Model(inputs=in_layers, outputs=merged)
    plot_model(model, show_shapes=True, to_file='cnn_lstm_real.png')

    return model

唯一的大区别是您需要在每个分支的输出中显式添加新轴（因此是Reshape层），以便允许沿着该轴进行连接。

于 2019-08-14T09:00:07.690 回答