最简单的方法是获取所需的输入和输出层，并使用它们创建一个新模型。在本例中，请确保指定输入形状：

model = keras.Sequential([
    layers.Dense(128, activation="relu", input_shape=(15,)),
    layers.Dense(64, activation="relu"),
    layers.Dense(32, activation="relu"),
    layers.Dense(16, activation="relu"),
    layers.Dense(8, activation="relu", name="latent_space"),
    layers.Dense(16, activation="relu"),
    layers.Dense(32, activation="relu", name="decode_32"),
    layers.Dense(64, activation="relu"),
    layers.Dense(128, activation="sigmoid"),
])

model.compile(...)
model.fit(...)

in_layer = model.get_layer("latent_space")
out_layer = model.get_layer("decode_32")

sub_model = keras.Model(inputs=in_layer.input, outputs=out_layer.output)

sub_model将是一个只包含您所选图层的模型，就像您想要的那样。

this answer符合您的问题吗？

def extract_layers(main_model, starting_layer_ix, ending_layer_ix) :
  # create an empty model
  new_model = Sequential()
  for ix in range(starting_layer_ix, ending_layer_ix + 1):
    curr_layer = main_model.get_layer(index=ix)
    # copy this layer over to the new model
    new_model.add(curr_layer)
  return new_model

如果您喜欢使用第一个和最后一个层的名称来选择子网，get_layer方法也有一个用于层名称的参数，但更简单的解决方案是检索要选择的层的索引，这要归功于layer.name参数。
这样，您只需通过添加

layer_names = [layer.name for layer in main_model.layers]
starting_layer_ix = layer_names.index(starting_layer_name)
ending_layer_ix = layer_names.index(ending_layer_name)