我在尝试按照Francois Chollet的书中一个教程，在TensorFlow中构建一个文本分类模型。我首先尝试创建一个嵌入层，但在这一阶段总是出错。
我的逻辑如下：
-
从文本字符串列表X和整数列表y开始。
-
对文本数据进行分词、向量化，并填充到最长序列长度。
-
将每个整数标签转换为独热编码数组。
- 将数据输入到嵌入层，输入参数包括：
- input_dim = 唯一标记/词的总数（在我的例子中是1499）
- output_dim = 嵌入向量的维度大小（从32开始）
- input_length = 最大序列长度，与序列填充的维度相同（在我的例子中是295）
- 将嵌入结果传递到具有32个隐藏单元和relu激活函数的密集层
- 然后传递到具有3个隐藏单元和softmax激活函数的密集层，以预测3个类别
能有人解释一下我哪里做错了么？我以为我已经理解了如何实例化嵌入层，但这是不是我的理解有误？
这是我的代码：
# read in raw datadf = pd.read_csv('text_dataset.csv')samples = df.data.tolist() # list of strings of textlabels = df.sentiment.to_list() # list of integers# tokenize and vectorize text data to prepare for embeddingtokenizer = Tokenizer()tokenizer.fit_on_texts(samples)sequences = tokenizer.texts_to_sequences(samples)word_index = tokenizer.word_indexprint(f'Found {len(word_index)} unique tokens.')# setting variablesvocab_size = len(word_index) # 1499# Input_dim: This is the size of the vocabulary in the text data.input_dim = vocab_size # 1499# This is the size of the vector space in which words will be embedded.output_dim = 32 # recommended by tf# This is the length of input sequencesmax_sequence_length = len(max(sequences, key=len)) # 295# train/test index splice variabletraining_samples = round(len(samples)*.8)# data = pad_sequences(sequences, maxlen=max_sequence_length) # shape (499, 295)# keras automatically pads to maxlen if left without inputdata = pad_sequences(sequences)# preprocess labels into one hot encoded array of 3 classes ([1., 0., 0.])labels = to_categorical(labels, num_classes=3, dtype='float32') # shape (499, 3)# Create test/train data (80% train, 20% test)x_train = data[:training_samples]y_train = labels[:training_samples]x_test = data[training_samples:]y_test = labels[training_samples:]model = Sequential()model.add(Embedding(input_dim, output_dim, input_length=max_sequence_length))model.add(Dense(32, activation='relu'))model.add(Dense(3, activation='softmax'))model.summary()model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])model.fit(x_train, y_train, epochs=10, batch_size=32, validation_data=(x_test, y_test))当我运行这段代码时，我得到了以下错误：
Found 1499 unique tokens.Model: "sequential_23"_________________________________________________________________Layer (type) Output Shape Param # =================================================================embedding_21 (Embedding) (None, 295, 32) 47968 _________________________________________________________________dense_6 (Dense) (None, 295, 32) 1056 _________________________________________________________________dense_7 (Dense) (None, 295, 3) 99 =================================================================Total params: 49,123Trainable params: 49,123Non-trainable params: 0_________________________________________________________________---------------------------------------------------------------------------ValueError Traceback (most recent call last)<ipython-input-144-f29ef892e38d> in <module>() 51 epochs=10, 52 batch_size=32,---> 53 validation_data=(x_test, y_test))2 frames/usr/local/lib/python3.6/dist-packages/keras/engine/training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix) 129 ': expected ' + names[i] + ' to have ' + 130 str(len(shape)) + ' dimensions, but got array '--> 131 'with shape ' + str(data_shape)) 132 if not check_batch_axis: 133 data_shape = data_shape[1:]ValueError: Error when checking target: expected dense_7 to have 3 dimensions, but got array with shape (399, 3)为了排查问题，我一直在注释掉层以查看发生了什么。我发现问题一直持续到第一层，这让我认为我对嵌入层的理解不够。见下文：
model = Sequential()model.add(Embedding(input_dim, output_dim, input_length=max_sequence_length))# model.add(Dense(32, activation='relu'))# model.add(Dense(3, activation='softmax'))model.summary()这会导致以下结果：
Found 1499 unique tokens.Model: "sequential_24"_________________________________________________________________Layer (type) Output Shape Param # =================================================================embedding_22 (Embedding) (None, 295, 32) 47968 =================================================================Total params: 47,968Trainable params: 47,968Non-trainable params: 0_________________________________________________________________---------------------------------------------------------------------------ValueError Traceback (most recent call last)<ipython-input-150-63d1b96db467> in <module>() 51 epochs=10, 52 batch_size=32,---> 53 validation_data=(x_test, y_test))2 frames/usr/local/lib/python3.6/dist-packages/keras/engine/training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix) 129 ': expected ' + names[i] + ' to have ' + 130 str(len(shape)) + ' dimensions, but got array '--> 131 'with shape ' + str(data_shape)) 132 if not check_batch_axis: 133 data_shape = data_shape[1:]ValueError: Error when checking target: expected embedding_22 to have 3 dimensions, but got array with shape (399, 3)回答：
Keras中的Dense层期望接收一个只有2个维度的平面输入，格式为[BATCH_SIZE, N]。对于一个句子的嵌入层输出有3个维度：[BS, SEN_LENGTH, EMBEDDING_SIZE]。
解决这个问题有两种方法：
- 在第一个Dense层之前展平嵌入层的输出：
model.add(Flatten())； - 使用卷积层（推荐这种方法）：
model.add(Conv1D(filters=32, kernel_size=8, activation='relu'))。
