Keras：如何按顺序合并图层而不使用“连接”

Question

我正在尝试构建一个将cnn和lstm结合在一起的模型。 我想对cnn的输入进行多元处理，然后将输出顺序放入LSTM的输入中。但是，合并cnn输出时存在问题。如果使用串联，则它将延伸到axis = -1，如图所示。但是我将其放在lstm结构中，因此我想顺序地增加它。但是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）。我该怎么办？

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

Answer 1

您想要的仍然是串联，但在另一个新轴上。连接层和功能允许指定轴，因此您可以这样操作：

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

唯一的不同是，您需要在每个分支的输出中显式添加新轴（因此Reshape层），以便允许沿该轴进行级联。