复制特定图层的权重-Keras [英] Copying weights of a specific layer - keras

问题描述

根据此，以下副本权重从一种模型转换为另一种模型:

According to this the following copies weights from one model to another:

target_model.set_weights(model.get_weights())

复制特定图层的权重该怎么办?

What about copying the weights of a specific layer, would this work?

model_1.layers[0].set_weights(source_model.layers[0].get_weights())
model_2.layers[0].set_weights(source_model.layers[0].get_weights())

如果我训练model_1和model_2，它们的重量会分开吗? 文档没有说明此get_weights是否进行深拷贝或不是.如果这不起作用，该如何实现?

If I train model_1 and model_2 will they have separate weights? The documentation doesn't state whether if this get_weights makes a deep copy or not. If this doesn't work, how can this be achieved?

推荐答案

当然，它是砝码的副本.在两个单独的模型之间共享权重对象没有意义.您可以使用以下简单示例自己检查它:

Of course, it would be a copy of the weights. It does not make sense the weights object to be shared between two separate models. You can check it for yourself with a simple example like this:

model1 = Sequential()
model1.add(Dense(10, input_dim=2))

model2 = Sequential()
model2.add(Dense(10, input_dim=2))

model1.compile(loss='mse', optimizer='adam')
model2.compile(loss='mse', optimizer='adam')

测试:

>>> model1.layers[0].get_weights()
[array([[-0.42853734,  0.18648076, -0.47137827,  0.1792168 ,  0.0373047 ,
          0.2765705 ,  0.38383502,  0.09664273, -0.4971757 ,  0.41548246],
        [ 0.0403192 , -0.01309097,  0.6656211 , -0.0536288 ,  0.58677703,
          0.21625364,  0.26447064, -0.42619988,  0.17218047, -0.39748642]],
       dtype=float32),
 array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], dtype=float32)]

>>> model2.layers[0].get_weights()
[array([[-0.30062824, -0.3740575 , -0.3502644 ,  0.28050178, -0.68631136,
          0.1596322 ,  0.08288956, -0.20988202,  0.34323698,  0.2893324 ],
        [-0.29182747, -0.2754455 , -0.64082885,  0.29160154,  0.04342002,
         -0.4996035 ,  0.6608283 ,  0.10293472,  0.11375248, -0.43438092]],
       dtype=float32),
 array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], dtype=float32)]

>>> model2.layers[0].set_weights(model1.layers[0].get_weights())
>>> model2.layers[0].get_weights()
[array([[-0.42853734,  0.18648076, -0.47137827,  0.1792168 ,  0.0373047 ,
          0.2765705 ,  0.38383502,  0.09664273, -0.4971757 ,  0.41548246],
        [ 0.0403192 , -0.01309097,  0.6656211 , -0.0536288 ,  0.58677703,
          0.21625364,  0.26447064, -0.42619988,  0.17218047, -0.39748642]],
       dtype=float32),
 array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], dtype=float32)]

>>> id(model1.layers[0].get_weights()[0])
140494823634144

>>> id(model2.layers[0].get_weights()[0])
140494823635664

内核权重数组的id不同，因此它们是不同的对象，但具有相同的值.

The ids of kernel weights arrays are different so they are different objects, but with the same value.

这篇关于复制特定图层的权重-Keras的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！