我试图获得图层的权重。当使用keras层并且输入连接到它时,它似乎正常工作。但是,在将其包装到我的自定义图层时,这不再起作用。这是一个错误还是我错过了什么?
编辑:注意事项:
我读到可以在自定义层的build()中定义可训练变量。但是,由于自定义图层由keras图层Dense(以及之后可能更多的keras图层)组成,因此这些图层应该已经定义了可训练变量和权重/偏差初始值设定项。 (我没有看到在TestLayer的init()中使用将在TestLayer的build()中定义的变量覆盖它们的方法。
class TestLayer(layers.Layer):
def __init__(self):
super(TestLayer, self).__init__()
self.test_nn = layers.Dense(3)
def build(self, input_shape):
super(TestLayer, self).build(input_shape)
def call(self, inputs, **kwargs):
test_out = test_nn(inputs) # which is test_in
return test_out
test_in = layers.Input((2,))
test_nn = layers.Dense(3)
print(test_nn.get_weights()) # empty, since no connection to the layer
test_out = test_nn(test_in)
print(test_nn.get_weights()) # layer returns weights+biases
testLayer = TestLayer()
features = testLayer(test_in)
print(testLayer.get_weights()) # Problem: still empty, even though connected to input.
documentation说,build()
方法应该调用你没有的add_weight()
:
应该调用add_weight(),然后调用super的build()
如果要继承layers.Layer
,也不需要在类中定义密集层。这是你应该如何子类:
import tensorflow as tf
from tensorflow.keras import layers
class TestLayer(layers.Layer):
def __init__(self, outshape=3):
super(TestLayer, self).__init__()
self.outshape = outshape
def build(self, input_shape):
self.kernel = self.add_weight(name='kernel',
shape=(int(input_shape[1]), self.outshape),
trainable=True)
super(TestLayer, self).build(input_shape)
def call(self, inputs, **kwargs):
return tf.matmul(inputs, self.kernel)
test_in = layers.Input((2,))
testLayer = TestLayer()
features = testLayer(test_in)
print(testLayer.get_weights())
#[array([[-0.68516827, -0.01990592, 0.88364804],
# [-0.459718 , 0.19161093, 0.39982545]], dtype=float32)]
Here是继承Layer
类的更多例子。
但是,如果你坚持以你的方式实现它,如果你想使用get_weights()
,你必须覆盖它(在这种情况下,你可以创建一个没有子类的类):
import tensorflow as tf
from tensorflow.keras import layers
class TestLayer(layers.Layer):
def __init__(self, outshape=3):
super(TestLayer, self).__init__()
self.test_nn = layers.Dense(outshape)
self.outshape = outshape
def build(self, input_shape):
super(TestLayer, self).build(input_shape)
def call(self, inputs, **kwargs):
return self.test_nn(inputs)
def get_weights(self):
with tf.Session() as sess:
sess.run([x.initializer for x in self.test_nn.trainable_variables])
return sess.run(self.test_nn.trainable_variables)
test_in = layers.Input((2,))
testLayer = TestLayer()
features = testLayer(test_in)
print(testLayer.get_weights())
#[array([[ 0.5692867 , 0.726858 , 0.37790012],
# [ 0.2897135 , -0.7677493 , -0.58776844]], dtype=float32), #array([0., 0., 0.], dtype=float32)]
不幸的是,Keras不支持在其他图层中使用图层。我在过去遇到过这个问题,并开了一个问题here,但团队向我证实这是故意的。
您可以在自定义图层中定义方法,如:
def dense(X, f_in, f_out):
W = self.add_weight(name='kernel',
shape=(f_in, f_out))
b = self.add_weight(name='bias',
shape=(f_out, ))
return K.dot(X, W) + b
或者继承Dense图层并使用super().call()
的输出。