我正在尝试使用keras中的Model子类化来实现WideResnet。我无法理解我的代码中出了什么问题：
class ResidualBlock(layers.Layer):
def __init__(self, filters, kernel_size, dropout, dropout_percentage, strides=1, **kwargs):
super(ResidualBlock, self).__init__(**kwargs)
self.conv_1 = layers.Conv2D(filters, (1, 1), strides=strides)
self.bn_1 = layers.BatchNormalization()
self.rel_1 = layers.ReLU()
self.conv_2 = layers.Conv2D(filters, kernel_size, padding="same", strides=strides)
self.dropout = layers.Dropout(dropout_percentage)
self.bn_2 = layers.BatchNormalization()
self.rel_2 = layers.ReLU()
self.conv_3 = layers.Conv2D(filters, kernel_size, padding="same")
self.add = layers.Add()
self.dropout = dropout
self.strides = strides
def call(self, inputs):
x = inputs
if self.strides > 1:
x = self.conv_1(x)
res_x = self.bn_1(x)
res_x = self.rel_1(x)
res_x = self.conv_2(x)
if self.dropout:
res_x = self.dropout(x)
res_x = self.bn_2(x)
res_x = self.rel_2(x)
res_x = self.conv_3(x)
inputs = self.add([x, res_x])
return inputs
class WideResidualNetwork(models.Model):
def __init__(self, input_shape, n_classes, d, k, kernel_size=(3, 3), dropout=False, dropout_percentage=0.3, strides=1, **kwargs):
super(WideResidualNetwork, self).__init__(**kwargs)
if (d-4)%6 != 0:
raise ValueError('Please choose a correct depth!')
self.rel_1 = layers.ReLU()
self.conv_1 = layers.Conv2D(16, (3, 3), padding='same')
self.conv_2 = layers.Conv2D(16*k, (1, 1))
self.dense = layers.Dense(n_classes)
self.dropout = dropout
self.dropout_percentage = dropout_percentage
self.N = int((d - 4) / 6)
self.k = k
self.d = d
self.kernel_size = kernel_size
def build(self, input_shape):
self.bn_1 = layers.BatchNormalization(input_shape=input_shape)
def call(self, inputs):
x = self.bn_1(inputs)
x = self.rel_1(x)
x = self.conv_1(x)
x = self.conv_2(x)
for _ in range(self.N):
x = ResidualBlock(16*self.k, self.kernel_size, self.dropout, self.dropout_percentage)(x)
x = ResidualBlock( 32*self.k, self.kernel_size, self.dropout, self.dropout_percentage, strides=2)(x)
for _ in range(self.N-1):
x = ResidualBlock( 32*self.k, self.kernel_size, self.dropout, self.dropout_percentage)(x)
x = ResidualBlock( 64*self.k, self.kernel_size, self.dropout, self.dropout_percentage, strides=2)(x)
for _ in range(self.N-1):
x = ResidualBlock( 64*self.k, self.kernel_size, self.dropout, self.dropout_percentage)(x)
x = layers.GlobalAveragePooling2D()(x)
x = self.dense(x)
x = layers.Activation("softmax")(x)
return x
当我尝试以这种方式拟合模型时：
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()
model = WideResidualNetwork(x_train[0].shape, 10, 28, 1)
x_train, x_test = x_train/255. , x_test/255.
model = WideResidualNetwork(x_train[0].shape, 10, 28, 1)
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
epochs = 40
batch_size = 64
validation_split = 0.2
h = model.fit(x_train, y_train, epochs=epochs, batch_size=batch_size, validation_split=validation_split)
我得到以下错误：
...
<ipython-input-26-61c1bdb3546c>:31 call *
x = ResidualBlock(16*self.k, self.kernel_size, self.dropout, self.dropout_percentage)(x)
<ipython-input-9-3fea1e77cb6e>:23 call *
res_x = self.bn_1(x)
...
ValueError: tf.function-decorated function tried to create variables on non-first call.
所以我不明白问题出在哪里，我也试图将初始化转移到构建中，但没有结果，错误仍然存在。也许我的知识有差距提前感谢
您正在将ResidualBlocks、GlobalAveragePooling2D和Activation层初始化到调用方法中。试着把它们移到init中，就像你对其他层所做的那样，它不应该给你那个错误。