如何在函数 API 中使用嵌入层和文本向量化

Question

刚开始使用tensorflow

正在处理 imdb 数据集。过程：使用textvectorization层进行文本编码，并将其传递给嵌入层：

# Create a custom standardization function to strip HTML break tags '<br />'.
def custom_standardization(input_data):
  lowercase = tf.strings.lower(input_data)
  stripped_html = tf.strings.regex_replace(lowercase, '<br />', ' ')
  return tf.strings.regex_replace(stripped_html,
                              '[%s]' % re.escape(string.punctuation), '')


# Vocabulary size and number of words in a sequence.
vocab_size = 10000
sequence_length = 100

# Use the text vectorization layer to normalize, split, and map strings to
# integers. Note that the layer uses the custom standardization defined above.
# Set maximum_sequence length as all samples are not of the same length.
vectorize_layer = TextVectorization(
standardize=custom_standardization,
max_tokens=vocab_size,
output_mode='int',
output_sequence_length=sequence_length)

# Make a text-only dataset (no labels) and call adapt to build the vocabulary.
text_ds = train_ds.map(lambda x, y: x)
vectorize_layer.adapt(text_ds)

然后我尝试构建一个功能 API:

embedding_dim=16
text_model_catprocess2 = vectorize_layer
text_model_embedd = tf.keras.layers.Embedding(vocab_size, embedding_dim, name = 'embedding')(text_model_catprocess2)
text_model_embed_proc = tf.keras.layers.Lambda(embedding_mean_standard)(text_model_embedd)
text_model_dense1 = tf.keras.layers.Dense(2, activation = 'relu')(text_model_embed_proc)
text_model_dense2 = tf.keras.layers.Dense(2, activation = 'relu')(text_model_dense1)
text_model_output = tf.keras.layers.Dense(1, activation = 'sigmoid')(text_model_dense2)

但是，这给出了以下错误：

~\anaconda3\lib\site-packages\keras\backend.py in dtype(x)
1496 
1497   """
-> 1498   return x.dtype.base_dtype.name
1499 
1500 

AttributeError: Exception encountered when calling layer "embedding" (type Embedding).

'str' object has no attribute 'base_dtype'

Call arguments received:
  • inputs=<keras.layers.preprocessing.text_vectorization.TextVectorization object at 0x0000029B483AADC0>

像这样制作顺序 API 后，它工作正常：

embedding_dim=16
modelcheck = tf.keras.Sequential([
vectorize_layer,
tf.keras.layers.Embedding(vocab_size, embedding_dim, name="embedding"),
tf.keras.layers.GlobalAveragePooling1D(),
tf.keras.layers.Dense(16, activation='relu'),
tf.keras.layers.Dense(1)
])

我不确定为什么会这样。函数 API 是否需要输入？请帮忙！

Answer 1

你有两个选择。您可以使用 Sequential 模型，它会像您确认的那样工作，因为您不必定义 Input 层，或者您使用 functional API定义一个 Input 层：

embedding_dim = 16
text_model_input = tf.keras.layers.Input(dtype=tf.string, shape=(1,))
text_model_catprocess2 = vectorize_layer(text_model_input)
text_model_embedd = tf.keras.layers.Embedding(vocab_size, embedding_dim, name = 'embedding')(text_model_catprocess2)
text_model_embed_proc = tf.keras.layers.Lambda(embedding_mean_standard)(text_model_embedd)
text_model_dense1 = tf.keras.layers.Dense(2, activation = 'relu')(text_model_embed_proc)
text_model_dense2 = tf.keras.layers.Dense(2, activation = 'relu')(text_model_dense1)
text_model_output = tf.keras.layers.Dense(1, activation = 'sigmoid')(text_model_dense2)
model = tf.keras.Model(text_model_input, text_model_output)

如何在函数 API 中使用嵌入层和文本向量化

How to use Embedding Layer along with textvectorization in functional API

python

tensorflow

tf.keras

word-embedding

functional-api