Tensorflow 运行CNN-LSTM模型时出错：ValueError:层LSTM_13的输入0与层不兼容：预期ndim=3

运行以下代码时，我收到一个错误：

model = tf.keras.Sequential([
    tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length=max_length),
    tf.keras.layers.Conv1D(128, 5, activation='relu'),
    tf.keras.layers.GlobalAveragePooling1D(),
    tf.keras.layers.LSTM(32),
    tf.keras.layers.Dense(6, activation='relu'),
    tf.keras.layers.Dense(2, activation='sigmoid')
   ])

错误：

ValueError: Input 0 of layer lstm_13 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: [None, 128]

---

将tf.keras.layers.globalaveragepoolg1d更改为tf.keras.layers.averagepoolg1d

有任何特殊原因吗？是的。。。必须保持LSTM图层的三维尺寸。是工作吗？