Python tensorflow2.x keras嵌入层处理tf.dataset报错

您不能将tf.data.Dataset直接馈送到Embedding层，您可以使用.map(...):

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
import re
import string 
def standardize(input_data):

    input_data = tf.strings.lower(input_data)
    input_data = tf.strings.regex_replace(input_data, f"[{re.escape(string.punctuation)}]", " ")
    return input_data

input_data = tf.constant([["SWIM 2008-07 Baseball"], ["Football"]], shape=(2, 1), dtype=tf.string)

text_layer = tf.keras.layers.TextVectorization( standardize = standardize, max_tokens = 10, output_mode = 'int', output_sequence_length=10 )

dataset = tf.data.Dataset.from_tensors( input_data )

dataset = dataset.batch(2).map(lambda x: tf.squeeze(x, axis=0))

text_layer.adapt(dataset)

process_text = dataset.map(text_layer)

emb_layer = layers.Embedding(10, 10)
process_text = process_text.map(emb_layer)

或者定义模型并将数据集输入model.fit(...):

import tensorflow as tf
import re
import string 
def standardize(input_data):

    input_data = tf.strings.lower(input_data)
    input_data = tf.strings.regex_replace(input_data, f"[{re.escape(string.punctuation)}]", " ")
    return input_data

input_data = tf.constant([["SWIM 2008-07 Baseball"], ["Football"]], shape=(2, 1), dtype=tf.string)

text_layer = tf.keras.layers.TextVectorization( standardize = standardize, max_tokens = 10, output_mode = 'int', output_sequence_length=10 )

dataset = tf.data.Dataset.from_tensors( input_data )

dataset = dataset.batch(2)

text_layer.adapt(dataset)

process_text = dataset.map(lambda x: (text_layer(tf.squeeze(x, axis=0)), tf.random.uniform((2, ), maxval=2, dtype=tf.int32))) # add random label to each entry

inputs = tf.keras.layers.Input((10, ))
emb_layer = tf.keras.layers.Embedding(10, 10)
x = emb_layer(inputs)
x = tf.keras.layers.GlobalAveragePooling1D()(x)
outputs = tf.keras.layers.Dense(1, 'sigmoid')(x)
model = tf.keras.Model(inputs, outputs)
model.compile(optimizer='adam', loss='binary_crossentropy')
model.fit(process_text)