Question

我正在尝试构建一个Tensorflow估算器以用于SageMaker。主要功能训练和评估估计器。尽管尽了最大的努力，但我仍然遇到以下错误：

ValueError：图层输入的输入0与图层不兼容：预期ndim = 3，找到的ndim = 2。收到的完整图形：[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

from_tensors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])

您会注意到，我们仅迭代一次数据集，而我们希望将其迭代52388次！

现在假设我们要将此单个大张量馈入模型。 Tensorflow转换为[None, 1]是我们的批量大小的None。另一方面，用[None, 41]指定模型的输入，这意味着模型期望输入形状为[None, None, 41]的输入。因此，这种不一致会导致错误。

如何解决？

使用from_tensor_slices。

仍然给我尺寸错误，如何解决？定义LSTM的输入尺寸：

model = tf.keras.models.Sequential()
model.add(tf.keras.layers.LSTM(32, name='inputs', input_shape=(50, 41)))
model.add(tf.keras.layers.Dense(11, activation='softmax', name='dense'))
model.compile(loss='categorical_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])
model.compile(loss='categorical_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

如何为Tensorflow估算器输入正确的形状？

1 个答案: