ValueError：层“lstm”的输入 0 与层不兼容：预期 ndim=3，发现 ndim=2。收到的完整形状：（无，1024）

原文标题 ：ValueError: Input 0 of layer “lstm” is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 1024)

我正在关注使用 YAMNet 进行迁移学习的环境声音分类教程。这里是链接：https://www.tensorflow.org/tutorials/audio/transfer_learning_audio 在教程中，他们定义了一个具有一个隐藏层和两个输出的序列模型来识别猫狗从声。

如何使用/添加其他层，如 LSTM、BiLSTM？

现在，我想开发一个模型，使用 LSTM 对来自音频源的十种不同声音进行分类。

esc50_csv = './datasets/ESC-50-master/meta/esc50.csv'
base_data_path = './datasets/ESC-50-master/audio/'
my_classes = ['airplane', 'breathing']
map_class_to_id = {'airplane':0, 'breathing':1}
filtered_pd = pd_data[pd_data.category.isin(my_classes)]
class_id = filtered_pd['category'].apply(lambdaname: 
        map_class_to_id[name])
filtered_pd = filtered_pd.assign(target=class_id)
full_path = filtered_pd['filename'].apply(lambda row: 
        os.path.join(base_data_path, row))
filtered_pd = filtered_pd.assign(filename=full_path)
filenames = filtered_pd['filename']
targets = filtered_pd['target']
folds = filtered_pd['fold']
main_ds = tf.data.Dataset.from_tensor_slices((filenames, targets, 
        folds))
main_ds.element_spec
def load_wav_for_map(filename, label, fold):
        return load_wav_16k_mono(filename), label, fold
main_ds = main_ds.map(load_wav_for_map)
main_ds.element_spec

# applies the embedding extraction model to a wav data
def extract_embedding(wav_data, label, fold):
         scores, embeddings, spectrogram = yamnet_model(wav_data)
         num_embeddings = tf.shape(embeddings)[0]
         return (embeddings, tf.repeat(label, num_embeddings),
                 tf.repeat(fold, num_embeddings))
# extract embedding
main_ds = main_ds.map(extract_embedding).unbatch()
main_ds.element_spec

cached_ds = main_ds.cache()
train_ds = cached_ds.filter(lambda embedding, label, fold: fold<4)
val_ds = cached_ds.filter(lambda embedding, label, fold: fold == 4)
test_ds = cached_ds.filter(lambda embedding, label, fold: fold == 5)

# remove the folds column now that it's not needed anymore
remove_fold_column = lambda embedding, label, fold: (embedding,label)
train_ds = train_ds.map(remove_fold_column)
val_ds = val_ds.map(remove_fold_column)
test_ds = test_ds.map(remove_fold_column)

train_ds = 
  train_ds.cache().shuffle(1000).batch(32).prefetch(tf.data.AUTOTUNE)

val_ds = val_ds.cache().batch(32).prefetch(tf.data.AUTOTUNE)
test_ds = test_ds.cache().batch(32).prefetch(tf.data.AUTOTUNE)

model = tf.keras.Sequential()
model.add(LSTM(32, input_shape=(1024, 16)))
model.add(tf.keras.layers.Dense(512, activation='relu'))
model.add(tf.keras.layers.Dense(len(my_classes)))
model.summary()
model.compile(loss=tf.keras.losses.SparseCategoricalCrossentropy(       
   from_logits=True), optimizer="adam", metrics=['accuracy'])
callback = tf.keras.callbacks.EarlyStopping(monitor='loss',
                                        patience=3,
                                        restore_best_weights=True)
history = model.fit(train_ds, epochs=150, validation_data=val_ds, 
                                       callbacks=callback)

我收到以下错误：

   Epoch 1/150
WARNING:tensorflow:Model was constructed with shape (None, 1024, 16) for input KerasTensor(type_spec=TensorSpec(shape=(None, 1024, 16), dtype=tf.float32, name='lstm_input'), name='lstm_input', description="created by layer 'lstm_input'"), but it was called on an input with incompatible shape (None, 1024).
WARNING:tensorflow:Model was constructed with shape (None, 1024, 16) for input KerasTensor(type_spec=TensorSpec(shape=(None, 1024, 16), dtype=tf.float32, name='lstm_input'), name='lstm_input', description="created by layer 'lstm_input'"), but it was called on an input with incompatible shape (None, 1024).
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-20-d976cb77f840> in <module>()
      7                                             restore_best_weights=True)
      8 
----> 9 history = model.fit(train_ds, epochs=150, callbacks=callback)

1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in autograph_handler(*args, **kwargs)
   1145           except Exception as e:  # pylint:disable=broad-except
   1146             if hasattr(e, "ag_error_metadata"):
-> 1147               raise e.ag_error_metadata.to_exception(e)
   1148             else:
   1149               raise

ValueError: in user code:

    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1021, in train_function  *
        return step_function(self, iterator)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1010, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1000, in run_step  **
        outputs = model.train_step(data)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 859, in train_step
        y_pred = self(x, training=True)
    File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler
        raise e.with_traceback(filtered_tb) from None
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/input_spec.py", line 214, in assert_input_compatibility
        raise ValueError(f'Input {input_index} of layer "{layer_name}" '

    ValueError: Exception encountered when calling layer "sequential_1" (type Sequential).
    
    Input 0 of layer "lstm" is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 1024)
    
    Call arguments received:
      • inputs=tf.Tensor(shape=(None, 1024), dtype=float32)
      • training=True
      • mask=None

我该如何解决这个错误？