具有tf数据集输入的Tensorflow keras

Question

我是tensorflow keras和数据集的新手。任何人都可以帮助我理解为什么以下代码不起作用？

import tensorflow as tf
import tensorflow.keras as keras
import numpy as np
from tensorflow.python.data.ops import dataset_ops
from tensorflow.python.data.ops import iterator_ops
from tensorflow.python.keras.utils import multi_gpu_model
from tensorflow.python.keras import backend as K


data = np.random.random((1000,32))
labels = np.random.random((1000,10))
dataset = tf.data.Dataset.from_tensor_slices((data,labels))
print( dataset)
print( dataset.output_types)
print( dataset.output_shapes)
dataset.batch(10)
dataset.repeat(100)

inputs = keras.Input(shape=(32,))  # Returns a placeholder tensor

# A layer instance is callable on a tensor, and returns a tensor.
x = keras.layers.Dense(64, activation='relu')(inputs)
x = keras.layers.Dense(64, activation='relu')(x)
predictions = keras.layers.Dense(10, activation='softmax')(x)

# Instantiate the model given inputs and outputs.
model = keras.Model(inputs=inputs, outputs=predictions)

# The compile step specifies the training configuration.
model.compile(optimizer=tf.train.RMSPropOptimizer(0.001),
          loss='categorical_crossentropy',
          metrics=['accuracy'])

# Trains for 5 epochs
model.fit(dataset, epochs=5, steps_per_epoch=100)

它因以下错误而失败：

model.fit(x=dataset, y=None, epochs=5, steps_per_epoch=100)
File "/home/wuxinyu/pyEnv/lib/python3.5/site-packages/tensorflow/python/keras/engine/training.py", line 1510, in fit
validation_split=validation_split)
File "/home/wuxinyu/pyEnv/lib/python3.5/site-packages/tensorflow/python/keras/engine/training.py", line 994, in _standardize_user_data
class_weight, batch_size)
File "/home/wuxinyu/pyEnv/lib/python3.5/site-packages/tensorflow/python/keras/engine/training.py", line 1113, in _standardize_weights
exception_prefix='input')
File "/home/wuxinyu/pyEnv/lib/python3.5/site-packages/tensorflow/python/keras/engine/training_utils.py", line 325, in standardize_input_data
'with shape ' + str(data_shape))
ValueError: Error when checking input: expected input_1 to have 2 dimensions, but got array with shape (32,)

根据tf.keras指南，我应该能够直接将数据集传递给model.fit，如下例所示：

Input tf.data datasets

使用数据集API可扩展到大型数据集或多设备培训。将tf.data.Dataset实例传递给fit方法：

# Instantiates a toy dataset instance:
dataset = tf.data.Dataset.from_tensor_slices((data, labels))
dataset = dataset.batch(32)
dataset = dataset.repeat()

Don't forget to specify steps_per_epoch when calling fit on a dataset.

model.fit（dataset，epochs = 10，steps_per_epoch = 30）这里，fit方法使用steps_per_epoch参数 - 这是模型在移动到下一个纪元之前运行的训练步数。由于数据集生成批量数据，因此此代码段不需要batch_size。

数据集也可用于验证：

dataset = tf.data.Dataset.from_tensor_slices((data, labels))
dataset = dataset.batch(32).repeat()

val_dataset = tf.data.Dataset.from_tensor_slices((val_data, val_labels))
val_dataset = val_dataset.batch(32).repeat()

model.fit(dataset, epochs=10, steps_per_epoch=30,
      validation_data=val_dataset,
      validation_steps=3)

我的代码有什么问题，以及正确的方法是什么？

Answer 1

关于你为什么会收到错误的原始问题：

Error when checking input: expected input_1 to have 2 dimensions, but got array with shape (32,)

您的代码中断的原因是因为您没有将.batch()应用回dataset变量，如下所示：

dataset = dataset.batch(10)

你只需要打电话给dataset.batch()。

这打破了因为没有batch()输出张量没有批处理，即你得到形状(32,)而不是(1,32)。

Answer 2

您缺少定义迭代器，这就是出现错误的原因。

data = np.random.random((1000,32))
labels = np.random.random((1000,10))
dataset = tf.data.Dataset.from_tensor_slices((data,labels))
dataset = dataset.batch(10).repeat()
inputs = Input(shape=(32,))  # Returns a placeholder tensor

# A layer instance is callable on a tensor, and returns a tensor.
x = Dense(64, activation='relu')(inputs)
x = Dense(64, activation='relu')(x)
predictions = Dense(10, activation='softmax')(x)

# Instantiate the model given inputs and outputs.
model = keras.Model(inputs=inputs, outputs=predictions)

# The compile step specifies the training configuration.
model.compile(optimizer=tf.train.RMSPropOptimizer(0.001),
          loss='categorical_crossentropy',
          metrics=['accuracy'])

# Trains for 5 epochs
model.fit(dataset.make_one_shot_iterator(), epochs=5, steps_per_epoch=100)

大纪元1/5 100/100 [==============================] - 1s 8ms /步 - 损失：11.5787 - acc ：0.1010

Epoch 2/5 100/100 [==============================] - 0s 4ms /步 - 损失：11.4846 - acc ：0.0990

Epoch 3/5 100/100 [==============================] - 0s 4ms /步 - 损失：11.4690 - acc ：0.1270

Epoch 4/5 100/100 [==============================] - 0s 4ms /步 - 损失：11.4611 - acc ：0.1300

Epoch 5/5 100/100 [==============================] - 0s 4ms /步 - 损失：11.4546 - acc ：0.1360

这是我系统的结果。