Python 转换为估计器时，LSTM无效RGUMERROR Tensorflow 2.0/Keras

我正在尝试构建一个

LSTM

网络，它接收一系列单词并将其转换为嵌入向量。我已经将每个单词序列转换为词汇向量

我使用的批量大小是32，每个词汇表向量的大小是50。这是我到目前为止创建模型并将其转换为估计器的Keras函数API代码

input_layer = keras.layers.Input(shape=(50,), name='search')
embedding_layer = keras.layers.Embedding(input_dim=32, output_dim=256, input_length=50)(input_layer)
lstm_layer = keras.layers.LSTM(units=256)(embedding_layer)
model = keras.models.Model(inputs=input_layer, outputs=lstm_layer)
model.compile(loss='mean_squared_error', optimizer='adam')
estimator = keras.estimator.model_to_estimator(keras_model=model)

但是这个代码给出了错误

tensorflow.python.framework.errors_impl.InvalidArgumentError: Node 'Adam/gradients/lstm/StatefulPartitionedCall_grad/StatefulPartitionedCall': Connecting to invalid output 5 of source node lstm/StatefulPartitionedCall which has 5 outputs

当我运行

model.summary（）

时，这就是输出

Layer (type)                 Output Shape              Param #   
=================================================================
search (InputLayer)          [(None, 50)]              0         
_________________________________________________________________
embedding (Embedding)        (None, 50, 256)           8192      
_________________________________________________________________
lstm (LSTM)                  (None, 256)               525312    
=================================================================
Total params: 533,504
Trainable params: 533,504
Non-trainable params: 0
_________________________________________________________________

---

我想这就是我所期望的。我试着用相同形状的致密扁平层替换

LSTM

层，代码运行良好

我将自己回答这个问题…从7/24开始，tf.keras.layers.LSTM似乎有问题。我将模型更改为以下内容

input_layer = keras.layers.Input(shape=(50,), name='search')
embedding_layer = keras.layers.Embedding(input_dim=32, output_dim=256, 
input_length=50)(input_layer)
lstm_layer = keras.layers.RNN(cell=keras.layers.LSTMCell(units=256))(embedding_layer)
model = keras.models.Model(inputs=input_layer, outputs=lstm_layer)
model.compile(loss='mean_squared_error', optimizer='adam')
estimator = keras.estimator.model_to_estimator(keras_model=model)