在尝试将LSTM与Dense层连接时，会在训练过程中报错：

input = Input(shape=(x_train.shape[1], None))X = Embedding(num_words, max_article_len)(input)X = LSTM(128, return_sequences=True, dropout = 0.5)(X)X = LSTM(128)(X)X = Dense(32, activation='softmax')(X)model = Model(inputs=[input], outputs=[X])...>>> ValueError: Error when checking target: expected dense to have shape (32,) but got array with shape (1,)

我尝试了不同的连接方式，但错误依然存在：

X, h, c = LSTM(128, return_sequences=False, return_state=True, dropout = 0.5)(X)X = Dense(32, activation='softmax')(X)>>> ValueError: Error when checking target: expected dense to have shape (32,) but got array with shape (1,)

有什么关于函数式API或Sequential模型的解决方案吗？

数据转换代码：

train = pd.read_csv('train.csv')articles = train['text']y_train = train['lang']num_words = 50000max_article_len = 20tokenizer = Tokenizer(num_words=num_words)tokenizer.fit_on_texts(articles)sequences = tokenizer.texts_to_sequences(articles)x_train = pad_sequences(sequences, maxlen=max_article_len, padding='post')x_train.shape>>> (18974, 100)y_train.shape>>> (18974,)

回答：

最后一个参数必须设置为False;

X = LSTM(128, return_sequences=True, dropout = 0.5)(X)X = LSTM(128, return_sequences=False)(X)

如果问题依然存在，那么问题可能出在你的输入形状上。