如何冻结喀拉拉山或tf.keras中的选定重量？

Question

我正在尝试一些需要冻结一些选定重量的东西。举这个例子

from keras.models import Sequential
from keras.layers import Dense,Input

model = Sequential()
model.add(Dense(4, input_shape=(4,),activation='relu'))
model.add(Dense(3,name="hidden",activation='relu'))
model.add(Dense(2,activation='sigmoid'))
model.compile(loss='mse', optimizer='adam')

print(model.layers[1].get_weights()[0])

这会将输入输出到隐藏的图层权重。

# Weights input x hidden
# Freeze 2Rx3C and 4Rx2C
# 2Rx3C=0.14362943; 4Rx2C=-0.23868048
array([[-0.05557871,  0.10941017, -0.59108734],
       [ 0.37056673,  0.2968588 ,  0.14362943],
       [-0.05471832, -0.21425706,  0.6455065 ],
       [-0.7883829 , -0.23868048, -0.517396  ]], dtype=float32)

从这个权重矩阵，我想冻结(2nd Row, 3rd Column)和(4th Row, 2nd Column)中的值，分别是0.14362943和-0.23868048。我不想在backprop上更新这些值。如何冻结这些选定的砝码？

Answer 1