如何使用来自一个预先训练的MLP的最后一个隐藏层权重作为Keras的新MLP(转移学习)的输入?

时间:2019-01-05 17:52:28

标签: python machine-learning keras keras-layer transfer-learning

我想使用简单的MLP模型进行迁移学习。首先,我针对大数据训练了一个1层隐藏层前馈网络:

net = Sequential()
net.add(Dense(500, input_dim=2048, kernel_initializer='normal', activation='relu'))
net.add(Dense(1, kernel_initializer='normal'))
net.compile(loss='mean_absolute_error', optimizer='adam')
net.fit(x_transf, 
        y_transf,
        epochs=1000, 
        batch_size=8, 
        verbose=0)

然后,我要将唯一的隐藏层作为输入传递到新网络,在该网络中我想添加第二层。重用的图层不应是可训练的。

idx = 1  # index of desired layer
input_shape = net.layers[idx].get_input_shape_at(0) # get the input shape of desired layer
input_layer = net.layers[idx]
input_layer.trainable = False

transf_model = Sequential()
transf_model.add(input_layer)
transf_model.add(Dense(input_shape[1], activation='relu'))
transf_model.compile(loss='mean_absolute_error', optimizer='adam')
transf_model.fit(x, 
                 y,
                 epochs=10, 
                 batch_size=8, 
                 verbose=0)

编辑: 上面的代码返回:

ValueError: Error when checking target: expected dense_9 to have shape (None, 500) but got array with shape (436, 1)

完成这项工作的诀窍是什么?

1 个答案:

答案 0 :(得分:1)

我只会使用Functional API来建立这样的模型:

shared_layer = net.layers[0] # you want the first layer, so index = 0
shared_layer.trainable = False

inp = Input(the_shape_of_one_input_sample) # e.g. (2048,)
x = shared_layer(inp)
x = Dense(800, ...)(x)
out = Dense(1, ...)(x)

model = Model(inp, out)

# the rest is the same...