Question

我正在尝试冻结一些选定重量的东西。举个例子

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])

这会将输入打印到隐藏层权重。

# 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)

我想从这个权重矩阵中冻结(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重量？

Answer 1

您需要使用tf.identity，它用于在设备之间显式传输张量时使用。

matrixVariable = tf.Variable(<your matrix>)
matrixVariableSliced = matrixVariable[<sliced matrix>] #take out your required weights
matrixVariable_stop = tf.stop_gradient(tf.identity(matrixVariableSliced)) 
matrixVariable = tf.concat((matrixVariableSliced, matrixVariable_stop), axis=1)

如何在keras或tf.keras中冻结选定的权重？

1 个答案: