如何将顺序模型更改为自定义类模型答案

【问题标题】：How to change Sequential model to Custom Class model如何将顺序模型更改为自定义类模型
【发布时间】：2019-08-24 12:32:41
【问题描述】：

我正在从旧版本中学习 tensorflow 2.0。我发现 tensorflow 模型从 Class-base 更改为 Sequential-base。但我想使用基于类的模型，因为它对我来说很容易阅读。

我想尝试翻译：https://www.tensorflow.org/beta/tutorials/keras/basic_text_classification_with_tfhub

embedding = 'https://tfhub.dev/google/tf2-preview/gnews-swivel-20dim/1'
hub_layer = hub.KerasLayer(embedding,
                           input_shape=[],
                           dtype=tf.string,
                           trainable=True)
# hub_layer(train_example_batch[:3])


# model = tf.keras.Sequential()
# model.add(hub_layer)
# model.add(tf.keras.layers.Dense(16, activation='relu'))
# model.add(tf.keras.layers.Dense(1, activation='sigmoid'))


class MyModel(keras.Model):
    def __init__(self, embedding):
        super(MyModel, self).__init__()
        self.embedding = embedding
        self.d1 = keras.layers.Dense(16, activation='relu')
        self.d2 = keras.layers.Dense(1, activation='sigmoid')

    def call(self, x):
        print(x.shape)
        return reduce(lambda x, f: f(x), [x, self.embedding, self.d1, self.d2])


model = MyModel(hub_layer)

我收到以下错误消息。

InvalidArgumentError: 2 root error(s) found.
  (0) Invalid argument:  input must be a vector, got shape: [512,1]
     [[{{node my_model_48/keras_layer_7/StatefulPartitionedCall/StatefulPartitionedCall/StatefulPartitionedCall/tokenize/StringSplit}}]]
  (1) Invalid argument:  input must be a vector, got shape: [512,1]
     [[{{node my_model_48/keras_layer_7/StatefulPartitionedCall/StatefulPartitionedCall/StatefulPartitionedCall/tokenize/StringSplit}}]]
     [[my_model_48/keras_layer_7/StatefulPartitionedCall/StatefulPartitionedCall/StatefulPartitionedCall/SparseFillEmptyRows/SparseFillEmptyRows/_24]]
0 successful operations.
0 derived errors ignored. [Op:__inference_keras_scratch_graph_303077]

Function call stack:
keras_scratch_graph -> keras_scratch_graph

为什么会出现这个错误？另外，请回答我们是否需要丢弃基于类的模型？

【问题讨论】：

你在哪里定义模型的输入形状？
没有。我没有定义输入形状，因为本专家教程* 没有定义形状... (*tensorflow.org/beta/tutorials/quickstart/advanced)。我应该定义输入形状吗？

标签： tensorflow keras keras-layer

【解决方案1】：

这是正确的代码。

# model = tf.keras.Sequential()
# model.add(hub_layer)
# model.add(tf.keras.layers.Dense(16, activation='relu'))
# model.add(tf.keras.layers.Dense(1, activation='sigmoid'))


class MyModel(keras.Model):
    def __init__(self, embedding):
        super(MyModel, self).__init__()
        self.embedding = embedding
        self.d1 = keras.layers.Dense(16, activation='relu')
        self.d2 = keras.layers.Dense(1, activation='sigmoid')

    def call(self, x):
        # tf.sequeeze is needed! because x's dimention is [None, 1]. (1 was inserted without permission ...)
        return reduce(lambda x, f: f(x), [x, tf.squeeze, self.embedding, self.d1, self.d2])


model = MyModel(hub_layer)

# model.summary()
model.layers

是因为官方框架自己添加了额外的功能......

我不喜欢这个属性，但是我觉得喜欢tensorflow的人渴望去做...

【讨论】：