如何为张量流估计器输入正确的形状？

Question

我正在尝试构建一个Tensorflow估计器来使用SageMaker。主要功能是训练和评估估计器。尽管我尽了最大的努力，我还是犯了以下错误：

ValueError: Input 0 of layer inputs is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: [50, 41]

def keras_model_fn(hyperparameters):
    """keras_model_fn receives hyperparameters from the training job and returns a compiled keras model.
    The model will be transformed into a TensorFlow Estimator before training and it will be saved in a 
    TensorFlow Serving SavedModel at the end of training.

    Args:
        hyperparameters: The hyperparameters passed to the SageMaker TrainingJob that runs your TensorFlow 
                         training script.
    Returns: A compiled Keras model
    """
    model = tf.keras.models.Sequential()
    model.add(tf.keras.layers.LSTM(32, name='inputs', input_shape=( None, 41)))
    model.add(tf.keras.layers.Dense(11, activation='softmax', name='dense'))
    model.compile(loss='categorical_crossentropy',
                  optimizer='rmsprop',
                  metrics=['accuracy'])

    return model


def train_input_fn(training_dir=None, hyperparameters=None):
    # invokes _input_fn with training dataset
    dataset = tf.data.Dataset.from_tensors(({INPUT_TENSOR_NAME: x_train}, y_train))
    dataset = dataset.repeat()
    return dataset.make_one_shot_iterator().get_next()

def eval_input_fn(training_dir=None, hyperparameters=None):
    # invokes _input_fn with evaluation dataset

    dataset =  tf.data.Dataset.from_tensors(({INPUT_TENSOR_NAME: x_test}, y_test))
    return dataset.make_one_shot_iterator().get_next()

if __name__ == '__main__':
    print(x_train.shape, y_train.shape)
    tf.logging.set_verbosity(tf.logging.INFO)
    model = keras_model_fn(0)
    estimator = tf.keras.estimator.model_to_estimator(keras_model=model)
    train_spec = tf.estimator.TrainSpec(input_fn=train_input_fn, max_steps=1000)
    eval_spec = tf.estimator.EvalSpec(input_fn=eval_input_fn)
    tf.estimator.train_and_evaluate(estimator, train_spec, eval_spec)

我的输入和输出形状是：

(52388, 50, 41) (52388, 11)

Answer 1

^{}将输入张量转换为单个大张量。例如，如果运行以下示例：

import tensorflow as tf

tf.enable_eager_execution()

dataset2 = tf.data.Dataset.from_tensors(
    (tf.random_uniform([52388, 50, 41], maxval=10, dtype=tf.int32),
     tf.random_uniform([52388, 11], maxval=10, dtype=tf.int32)))

for i, item in enumerate(dataset2):
    print('element: ' + str(i), item[0], item[1])

您注意到，我们只迭代一次数据集，而我们期望它迭代52388次！在

现在假设我们要把这个大张量输入到我们的模型中。Tensorflow转换为[None, 1]，这是我们的批处理大小。另一方面，使用[None, 41]指定模型的输入，这意味着模型需要一个形状为[None, None, 41]的输入。因此，这种不一致性导致了错误。在

如何修复它？

使用^{}。在

仍然给我尺寸误差，如何修复？定义LSTM的输入维度：

^{pr2}$