如何在函数式 API 中使用嵌入层和文本矢量化

Question

刚开始张量流

处理 imdb 数据集。过程：使用文本矢量化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性 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，这会给出以下错误：

~anaconda3libsite-packageskerasbackend.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>

在制作这样的顺序 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)
])

我不确定为什么会发生这种情况。函数式 API 是否需要具有输入？请帮忙！

Answer 1

您有两个选择。要么您使用Sequential模型，它将像您确认的那样工作，因为您不必定义Input层，要么您使用functionalAPI，您必须在其中定义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)