class Linear(tf.keras.Model):
def __init__(self):
super().__init__()
self.d1 = tf.keras.layers.Dense(
units=10,
activation=None,
kernel_initializer=tf.zeros_initializer(),
bias_initializer=tf.zeros_initializer()
)
self.d2 = tf.keras.layers.Dense(
units=1,
activation=None,
kernel_initializer=tf.ones_initializer(),
bias_initializer=tf.ones_initializer()
)
def call(self, input):
output = self.d1(input)
output = self.d2(output)
return output
net = Linear()
net(X)
net.get_weights()
def my_init():
return tf.keras.initializers.Ones()
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Dense(64, kernel_initializer=my_init()))
Y = model(X)
model.weights[0]
4.3 参数共享
如下,构建模型,在call
方法中多次使用同一个self.dense
层,即共享Dense
层
# 构造一个复杂点的模型
class FancyMLP(tf.keras.Model):
def __init__(self):
super().__init__()
self.flatten = tf.keras.layers.Flatten()
self.rand_weight = tf.constant(
tf.random.uniform((20,20)))
self.dense = tf.keras.layers.Dense(units=20, activation=tf.nn.relu)
def call(self, inputs):
x = self.flatten(inputs)
x = tf.nn.relu(tf.matmul(x, self.rand_weight) + 1)
x = self.dense(x)
x = tf.nn.relu(tf.matmul(x, self.rand_weight) + 1)
x = self.dense(x)
while tf.norm(x) > 1:
x /= 2
if tf.norm(x) < 0.8:
x *= 10
return tf.reduce_sum(x)