我希望对CNN的层进行正则化处理。
|(W^T * W - I)|
我该如何在Keras中实现这个功能?
我希望对CNN的层进行正则化处理。
|(W^T * W - I)|
文档中指出:
任何接受权重矩阵并返回损失贡献张量的函数都可以作为正则化器使用。
下面是实现的示例:
from keras import backend as K
def l1_reg(weight_matrix):
return 0.01 * K.sum(K.abs(weight_matrix))
model.add(Dense(64, input_dim=64,
kernel_regularizer=l1_reg)
from keras import backend as K
def fro_norm(w):
return K.sqrt(K.sum(K.square(K.abs(w))))
def cust_reg(w):
m = K.dot(K.transpose(w), w) - np.eye(w.shape)
return fro_norm(m)
import numpy as np
from keras import backend as K
from keras.models import Sequential
from keras.layers import Dense, Activation
X = np.random.randn(100, 100)
y = np.random.randint(2, size=(100, 1))
model = Sequential()
# apply regularization here. applies regularization to the
# output (activation) of the layer
model.add(Dense(32, input_shape=(100,),
activity_regularizer=fro_norm))
model.add(Dense(1))
model.add(Activation('softmax'))
model.compile(loss="binary_crossentropy",
optimizer='sgd',
metrics=['accuracy'])
model.fit(X, y, epochs=1, batch_size=32)
@Marcin评论所暗示的下面的方法不可行,因为正则化器必须返回张量,而LA.norm()
并不能返回。
def orth_norm(w)
m = K.dot(k.transpose(w), w) - np.eye(w.shape)
return LA.norm(m, 'fro')
from keras import backend as K
import numpy as np
def orth_norm(w)
m = K.dot(k.transpose(w), w) - np.eye(w.shape)
return LA.norm(m, 'fro')
keras.backend
函数? - Marcin Możejkocust_reg
似乎无法工作:https://pastebin.com/CgX5rdvE 和 https://gist.github.com/MartinThoma/f29b640caa237e413e05c98d8c334ddd - Martin Thomam = K.dot(K.transpose(w), w) - K.eye(w[1].shape[0])
。我可以替换它吗? - Martin Thoma我认为对于卷积层,您可以使用以下代码。虽然效率不高,但我认为它是可行的:
最初的回答:
import keras.backend as K
import tensorflow as tf
def orthogonality_regularization(weight_matrix):
identity = K.eye(int(weight_matrix.shape[-1]))
orthogonality_reg_mat = []
for i in range(weight_matrix.shape[-1]):
for j in range(weight_matrix.shape[-1]):
orthogonality_reg_mat.extend([K.sum(tf.multiply(K.flatten(weight_matrix[:,:,:,i]), K.flatten(weight_matrix[:,:,:,j]))) - identity[i, j]])
orthogonality_reg = tf.linalg.norm(tf.convert_to_tensor(orthogonality_reg_mat))
return orthogonality_reg
现如今(在{{link1:tensorflow 2.9.0
}}中),keras提供了一种正则化运算符,即正交正则化OrthogonalRegularizer。它允许在列和行之间强制实施正交性,不确定哪个是您的特定情况。
因此,您可以像这样调用它:
import tensorflow as tf
reg = tf.keras.regularizers.OrthogonalRegularizer(factor=0.01, mode="rows")
# now you can use reg in your layer(s)