错误：子类化 `Model` 类时，您应该实现 `call` 方法。在 tensorflow 自定义模型上

Question

我正在尝试在 Cifar 10 数据集上训练我的自定义模型。 我的模型代码如下：-

class cifar10Model(keras.Model):
  def __init__(self):
    super(cifar10Model, self).__init__()
    self.conv1 = keras.layers.Conv2D(32, 3, activation='relu', input_shape=(32, 32, 3))
    self.pool1 = keras.layers.MaxPool2D((3, 3))
    self.batch_norm1 = keras.layers.BatchNormalization()
    self.dropout1 = keras.layers.Dropout(0.1)

    self.conv2 = keras.layers.Conv2D(64, 3, activation='relu')
    self.pool2 = keras.layers.MaxPool2D((3, 3))
    self.batch_norm2 = keras.layers.BatchNormalization()
    self.dropout2 = keras.layers.Dropout(0.2)

    self.conv3 = keras.layers.Conv2D(128, 3, activation='relu')
    self.pool3 = keras.layers.MaxPool2D((3, 3))
    self.batch_norm3 = keras.layers.BatchNormalization()
    self.dropout3 = keras.layers.Dropout(0.3)

    self.flatten = keras.layers.Flatten()
    self.dense1 = keras.layers.Dense(128, activation='relu')
    self.dense2 = keras.layers.Dense(10)

    def call(self, x):
      x = self.conv1(x)
      x = self.pool1(x)
      x = self.batch_norm1(X)
      x = self.dropout1(x)

      x = self.conv2(x)
      x = self.pool2(x)
      x = self.batch_norm2(X)
      x = self.dropout2(x)

      x = self.conv3(x)
      x = self.pool3(x)
      x = self.batch_norm3(x)
      x = self.dropout3(x)

      x = self.flatten(x)
      x = self.dense1(x)
      return self.dense2(x)

model = cifar10Model()

当我运行这段代码时，这不会给我任何错误。

然后我定义了我的训练循环

loss_object = keras.losses.SparseCategoricalCrossentropy(from_logits=True)

optimizer = keras.optimizers.Adam()

train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')

test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')

@tf.function
def train_step(images, labels):
  with tf.GradientTape() as tape:
    predictions = model(images, training=True)
    loss = loss_object(labels, predictions)
  grad = tape.gradient(loss, model.trainable_variables)
  optimizer.apply_gradients(zip(grad, model.trainable_variables))
  train_loss(loss)
  train_accuracy(labels, predictions)

@tf.function
def test_step(images, labels):
  predictions = model(images)
  t_loss = loss_object(labels, predictions)

  test_loss(t_loss)
  test_accuracy(labels, predictions)

epochs = 10

for epoch in range(epochs):
  train_loss.reset_states()
  train_accuracy.reset_states()
  test_loss.reset_states()
  test_accuracy.reset_states()

  for images, labels in train_dataset:
    train_step(images, labels)

  for images, labels in test_dataset:
    test_step(images, labels)

  template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
  print(template.format(epoch + 1,
                        train_loss.result(),
                        train_accuracy.result() * 100,
                        test_loss.result(),
                        test_accuracy.result() * 100))

当我运行这段代码时，我得到以下错误

NotImplementedError: When subclassing the `Model` class, you should implement a `call` method.

我目前正在 google colab 上运行我的代码。

我的 colab 链接是https://colab.research.google.com/drive/1sOlbRpPRdyOCJI0zRFfIA-Trj1vrIbWY?usp=sharing

我在 colab 上的 tensorflow 版本是 2.2.0

此外，当我尝试通过此代码从未经训练的模型中预测标签时：-

print(model(train_images))

这也给了我同样的错误。 错误是说我没有在模型上实现调用方法。 但是，我已经定义了调用方法。

我也试过把调用方法改成__call__方法。

但是，它仍然给我同样的错误。

提前致谢：-

Answer 1

问题在于缩进。您已经在 __init__ 中定义了 call 方法。尝试在__init__ 方法之外定义它，如下所示：

class cifar10Model(keras.Model):
  def __init__(self):
    super(cifar10Model, self).__init__()
    self.conv1 = keras.layers.Conv3D(32, 3, activation='relu', input_shape=(32, 32, 3))
    self.pool1 = keras.layers.MaxPool3D((3, 3, 3))
    self.batch_norm1 = keras.layers.BatchNormalization()
    self.dropout1 = keras.layers.Dropout(0.1)

    self.conv2 = keras.layers.Conv3D(64, 3, activation='relu')
    self.pool2 = keras.layers.MaxPool3D((3, 3, 3))
    self.batch_norm2 = keras.layers.BatchNormalization()
    self.dropout2 = keras.layers.Dropout(0.2)

    self.conv3 = keras.layers.Conv3D(128, 3, activation='relu')
    self.pool3 = keras.layers.MaxPool3D((3, 3, 3))
    self.batch_norm3 = keras.layers.BatchNormalization()
    self.dropout3 = keras.layers.Dropout(0.3)

    self.flatten = keras.layers.Flatten()
    self.dense1 = keras.layers.Dense(128, activation='relu')
    self.dense2 = keras.layers.Dense(10)

  def call(self, x):
    x = self.conv1(x)
    x = self.pool1(x)
    x = self.batch_norm1(X)
    x = self.dropout1(x)

    x = self.conv2(x)
    x = self.pool2(x)
    x = self.batch_norm2(X)
    x = self.dropout2(x)

    x = self.conv3(x)
    x = self.pool3(x)
    x = self.batch_norm3(X)
    x = self.dropout3(x)

    x = self.flatten(x)
    x = self.dense1(x)
    return self.dense2(x)

model = cifar10Model()

希望这会有所帮助。