tensorflow - tf.data.Dataset：不能为给定的输入类型指定 `batch_size` 参数

Question

我正在使用Talos和 Google colab TPU运行 Keras 模型的超参数调整。请注意，我使用的是 Tensorflow 1.15.0 和 Keras 2.2.4-tf。

import os
import tensorflow as tf
import talos as ta
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.optimizers import Adam
from sklearn.model_selection import train_test_split

def iris_model(x_train, y_train, x_val, y_val, params):

    # Specify a distributed strategy to use TPU
    resolver = tf.contrib.cluster_resolver.TPUClusterResolver(tpu='grpc://' + os.environ['COLAB_TPU_ADDR'])
    tf.contrib.distribute.initialize_tpu_system(resolver)
    strategy = tf.contrib.distribute.TPUStrategy(resolver)

    # Use the strategy to create and compile a Keras model
    with strategy.scope():
      model = Sequential()
      model.add(Dense(32, input_shape=(4,), activation=tf.nn.relu, name="relu"))
      model.add(Dense(3, activation=tf.nn.softmax, name="softmax"))
      model.compile(optimizer=Adam(learning_rate=0.1), loss=params['losses'])

    # Convert data type to use TPU
    x_train = x_train.astype('float32')
    x_val = x_val.astype('float32')

    dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
    dataset = dataset.cache()
    dataset = dataset.shuffle(1000, reshuffle_each_iteration=True).repeat()
    dataset = dataset.batch(params['batch_size'], drop_remainder=True)

    # Fit the Keras model on the dataset
    out = model.fit(dataset, batch_size=params['batch_size'], epochs=params['epochs'], validation_data=[x_val, y_val], verbose=0, steps_per_epoch=2)

    return out, model

# Load dataset
X, y = ta.templates.datasets.iris()

# Train and test set
x_train, x_val, y_train, y_val = train_test_split(X, y, test_size=0.30, shuffle=False)

# Create a hyperparameter distributions 
p = {'losses': ['logcosh'], 'batch_size': [128, 256, 384, 512, 1024], 'epochs': [10, 20]}

# Use Talos to scan the best hyperparameters of the Keras model
scan_object = ta.Scan(x_train, y_train, params=p, model=iris_model, experiment_name='test', x_val=x_val, y_val=y_val, fraction_limit=0.1)

使用将训练集转换为数据集后，使用tf.data.Dataset拟合模型时出现以下错误out = model.fit：

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-3-c812209b95d0> in <module>()
      8 
      9 # Use Talos to scan the best hyperparameters of the Keras model
---> 10 scan_object = ta.Scan(x_train, y_train, params=p, model=iris_model, experiment_name='test', x_val=x_val, y_val=y_val, fraction_limit=0.1)

8 frames
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training.py in _validate_or_infer_batch_size(self, batch_size, steps, x)
   1813             'The `batch_size` argument must not be specified for the given '
   1814             'input type. Received input: {}, batch_size: {}'.format(
-> 1815                 x, batch_size))
   1816       return
   1817 

ValueError: The `batch_size` argument must not be specified for the given input type. Received input: <DatasetV1Adapter shapes: ((512, 4), (512, 3)), types: (tf.float32, tf.float32)>, batch_size: 512

然后，如果我按照这些说明操作并且不将批量大小参数设置为model.fit. 我收到另一个错误：

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-3-c812209b95d0> in <module>()
      8 
      9 # Use Talos to scan the best hyperparameters of the Keras model
---> 10 scan_object = ta.Scan(x_train, y_train, params=p, model=iris_model, experiment_name='test', x_val=x_val, y_val=y_val, fraction_limit=0.1)

8 frames
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/training.py in _distribution_standardize_user_data(self, x, y, sample_weight, class_weight, batch_size, validation_split, shuffle, epochs, allow_partial_batch)
   2307             strategy) and not drop_remainder:
   2308           dataset_size = first_x_value.shape[0]
-> 2309           if dataset_size % batch_size == 0:
   2310             drop_remainder = True
   2311 

TypeError: unsupported operand type(s) for %: 'int' and 'NoneType'

score 2 · Accepted Answer

在我看来，您的代码的问题在于训练和验证数据的格式不同。您正在批处理训练数据而不是验证示例。

iris_model您可以通过将函数的下半部分替换为以下内容来确保它们的格式相同：

def fix_data(x, y):
    x = x.astype('float32')
    ds = Dataset.from_tensor_slices((x, y))
    ds = ds.cache()
    ds = ds.shuffle(1000, reshuffle_each_iteration = True)
    ds = ds.repeat()
    ds = ds.batch(params['batch_size'], drop_remainder = True)
    return ds
train = fix_data(x_train, y_train)
val = fix_data(x_val, y_val)

# Fit the Keras model on the dataset
out = model.fit(x = train, epochs = params['epochs'],
                steps_per_epoch = 2,
                validation_data = val,
                validation_steps = 2)

至少这对我有用，你的代码运行没有错误。

score 0 · Accepted Answer

_distribution_standardize_user_data当您没有通过batch_sizeto fit时，您会得到第二个错误。

您为该功能运行的代码在这里：

https://github.com/tensorflow/tensorflow/blob/r1.15/tensorflow/python/keras/engine/training.py#L2192

您没有发布回溯，但我敢打赌它在第 2294 行失败了，因为这是唯一batch_size乘以某物的地方。

if shuffle:
          # We want a buffer size that is larger than the batch size provided by
          # the user and provides sufficient randomness. Note that larger
          # numbers introduce more memory usage based on the size of each
          # sample.
          ds = ds.shuffle(max(1024, batch_size * 8))

看起来你可以通过设置来关闭它shuffle=False。

fit(ds, shuffle=False,...)

那样有用吗？

score 0 · Accepted Answer

您能否从您的代码中删除这些行并尝试：

    dataset = dataset.cache()
    dataset = dataset.shuffle(1000, reshuffle_each_iteration=True).repeat()
    dataset = dataset.batch(params['batch_size'], drop_remainder=True)
WITH THESE:
    dataset = dataset.repeat()
    dataset = dataset.batch(128, drop_remainder=True)
    dataset = dataset.prefetch(1)

否则你写的tf.data.Dataset.from_tensor_slices内容与错误有关。

score 0 · Accepted Answer

来自github代码：

x如果是生成器或Sequence实例，则会引发 ValueError ，并且batch_size我们希望用户提供批处理数据集。

尝试使用batch_size = None

score 0 · Accepted Answer

不确定以下是否适合您的账单，但可以尝试一下。我所做的只是从数据集中删除了 repeat() 并从 model.fit 中删除了 batch_size=params['batch_size']

如果以上不是您准备牺牲的，请忽略该帖子。

import os
import tensorflow as tf
import talos as ta
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

def iris_model(x_train, y_train, x_val, y_val, params):

    # Specify a distributed strategy to use TPU
    resolver = tf.distribute.cluster_resolver.TPUClusterResolver(tpu='grpc://' + os.environ['COLAB_TPU_ADDR'])
    tf.config.experimental_connect_to_host(resolver.master())
    tf.tpu.experimental.initialize_tpu_system(resolver)
    strategy = tf.distribute.experimental.TPUStrategy(resolver)

    with strategy.scope():
        model = Sequential()
        model.add(Dense(32, input_dim=4, activation=params['activation']))
        model.add(Dense(3, activation='softmax'))
        model.compile(optimizer=params['optimizer'], loss=params['losses'])

    # Convert the train set to a Dataset to use TPU
    dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
    dataset = dataset.cache().shuffle(1000, reshuffle_each_iteration=True).batch(params['batch_size'], drop_remainder=True)

    out = model.fit(dataset, epochs=params['epochs'], validation_data=[x_val, y_val], verbose=0)

    return out, model

x, y = ta.templates.datasets.iris()

p = {'activation': ['relu', 'elu'],
       'optimizer': ['Nadam', 'Adam'],
       'losses': ['logcosh'],
       'batch_size': (20, 50, 5),
       'epochs': [10, 20]}

scan_object = ta.Scan(x, y, model=iris_model, params=p, fraction_limit=0.1, experiment_name='first_test')

tensorflow - tf.data.Dataset：不能为给定的输入类型指定 `batch_size` 参数

5 回答 5

Related

Reference