我有一个模型可以处理一些数据。我在数据集中添加了一些标记化的单词数据（为简洁起见有些被截断）：
vocab_size = len(tokenizer.word_index) + 1
comment_texts = df.comment_text.values
tokenizer = Tokenizer(num_words=num_words)
tokenizer.fit_on_texts(comment_texts)
comment_seq = tokenizer.texts_to_sequences(comment_texts)
maxtrainlen = max_length(comment_seq)
comment_train = pad_sequences(comment_seq, maxlen=maxtrainlen, padding='post')
vocab_size = len(tokenizer.word_index) + 1
df.comment_text = comment_train
x = df.drop('label', 1) # the thing I'm training
labels = df['label'].values # Also known as Y
x_train, x_test, y_train, y_test = train_test_split(
x, labels, test_size=0.2, random_state=1337)
n_cols = x_train.shape[1]
embedding_dim = 100 # TODO: why?
model = Sequential([
Embedding(input_dim=vocab_size, output_dim=embedding_dim, input_shape=(n_cols,)),
LSTM(32),
Dense(32, activation='relu'),
Dense(512, activation='relu'),
Dense(12, activation='softmax'), # for an unknown type, we don't account for that while training
])
model.summary()
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['acc'])
# convert the y_train to a one hot encoded variable
encoder = LabelEncoder()
encoder.fit(labels) # fit on all the labels
encoded_Y = encoder.transform(y_train) # encode on y_train
one_hot_y = np_utils.to_categorical(encoded_Y)
model.fit(x_train, one_hot_y, epochs=10, batch_size=16)
现在，我收到此错误：
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding (Embedding) (None, 12, 100) 4040500
_________________________________________________________________
lstm (LSTM) (None, 32) 17024
_________________________________________________________________
dense (Dense) (None, 32) 1056
_________________________________________________________________
dense_1 (Dense) (None, 512) 16896
_________________________________________________________________
dense_2 (Dense) (None, 12) 6156
=================================================================
Total params: 4,081,632
Trainable params: 4,081,632
Non-trainable params: 0
_________________________________________________________________
Train on 4702 samples
Epoch 1/10
2020-03-04 22:37:59.499238: W tensorflow/core/common_runtime/base_collective_executor.cc:217] BaseCollectiveExecutor::StartAbort Invalid argument: indices[0,0] = -4 is not in [0, 40405)
我认为这一定来自我的 comment_text 列，因为这是我添加的唯一内容。
Here is what comment_text looks like before I make the substitution:
And here is after:
我的完整代码（在进行更改之前）在这里：https://colab.research.google.com/drive/1y8Lhxa_DROZg0at3VR98fi5WCcunUhyc#scrollTo=hpEoqR4ne9TO https://colab.research.google.com/drive/1y8Lhxa_DROZg0at3VR98fi5WCcunUhyc#scrollTo=hpEoqR4ne9TO
你应该训练comment_train，不与x它正在采取未知的一切df.
The embedding_dim=100可以自由选择。这就像隐藏层中的单元数。您可以调整此参数来找到最适合您的模型的参数，也可以调整隐藏层中的单元数量。
在您的情况下，您将需要一个具有两个或多个输入的模型：
在某些时候，您将连接这两个分支并继续前进。
这个链接有一个很好的教程函数式API模型并显示具有两个文本输入和一个额外输入的模型：https://www.tensorflow.org/guide/keras/functional https://www.tensorflow.org/guide/keras/functional