[英]How can I convert mnist dataset into tfrecords in tensorflow 2.1.0
I saw many codes like the following gist , however, it prints out ModuleNotFoundError: No module named 'tensorflow.examples.tutorials'
in tensorflow 2.1.0.我看到很多类似下面要点的代码,但是,它打印出ModuleNotFoundError: No module named 'tensorflow.examples.tutorials'
in tensorflow 2.1.0。
When checking this question , I know I can load from keras with the following code.检查此问题时,我知道我可以使用以下代码从 keras 加载。
(train_images, train_labels), (test_images, test_labels) = tf.keras.datasets.mnist.load_data()
However, the result is a 3d ndarray, and I meet some errors when trying to create feature with the following codes但是,结果是 3d ndarray,我在尝试使用以下代码创建功能时遇到一些错误
(X_train_full, y_train_full), (X_test, y_test) = keras.datasets.fashion_mnist.load_data()
X_train_full = X_train_full / 255.0
X_test = X_test / 255.0
path = "train.tfrecord"
writer = tf.io.TFRecordWriter(path, options=None)
option = tf.io.TFRecordOptions(compression_type="GZIP")
feature_internal = {
"image":tf.train.Features(float_list=tf.train.FloatList(value=[X_train_full])),
"label":tf.train.Features(float_list=tf.train.FloatList(value=[y_train_full]))
}
it outputs它输出
TypeError: array([[[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
...,
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.]],
[[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
...,
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.]],
[[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
...,
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.]],
...,
[[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
...,
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.],
[0., 0., 0., ..., 0., 0., 0.]],
[[0., 0. has type <class 'numpy.ndarray'>, but expected one of: numbers.Real
I want to know how can I solve this error and convert mnist into tfrecord我想知道如何解决这个错误并将 mnist 转换为 tfrecord
To save your data to TFRecord files, the workflow is as follows: Step 1: Load the data with your own program.要将数据保存到 TFRecord 文件,工作流程如下: 第 1 步:使用您自己的程序加载数据。
Step 2: Open a TFRecord file with tf.python_io.TFRecordWriter.第 2 步:使用 tf.python_io.TFRecordWriter 打开一个 TFRecord 文件。
Step 3: Parse and save the data to TFRecord files.第 3 步:将数据解析并保存到 TFRecord 文件中。 Follow these steps:按着这些次序:
import gzip
import os
import numpy
from six.moves import urllib
import tensorflow as tf
params = {}
params['download_data_location'] = '/dbfs/ml/MNISTDemo/mnistData/'
params['tfrecord_location'] = '/dbfs/ml/MNISTDemo/mnistData/'
def download(directory, filename):
"""Download a file from the MNIST dataset if not already done."""
filepath = os.path.join(directory, filename)
if tf.gfile.Exists(filepath):
return filepath
if not tf.gfile.Exists(directory):
tf.gfile.MakeDirs(directory)
# CVDF mirror of http://yann.lecun.com/exdb/mnist/
url = 'https://storage.googleapis.com/cvdf-datasets/mnist/' + filename + '.gz'
temp_file_name, _ = urllib.request.urlretrieve(url)
tf.gfile.Copy(temp_file_name, filepath)
with tf.gfile.GFile(filepath) as f:
size = f.size()
print('Successfully downloaded', filename, size, 'bytes.')
return filepath
def _read32(bytestream):
dt = numpy.dtype(numpy.uint32).newbyteorder('>')
return numpy.frombuffer(bytestream.read(4), dtype=dt)[0]
def extract_images(f):
"""Extract the images into a 4D uint8 numpy array [index, y, x, depth].
Args:
f: A file object that can be passed into a gzip reader.
Returns:
data: A 4D uint8 numpy array [index, y, x, depth].
Raises:
ValueError: If the bytestream does not start with 2051.
"""
print('Extracting', f.name)
with gzip.GzipFile(fileobj=f) as bytestream:
magic = _read32(bytestream)
if magic != 2051:
raise ValueError('Invalid magic number %d in MNIST image file: %s' %
(magic, f.name))
num_images = _read32(bytestream)
rows = _read32(bytestream)
cols = _read32(bytestream)
buf = bytestream.read(rows * cols * num_images)
data = numpy.frombuffer(buf, dtype=numpy.uint8)
data = data.reshape(num_images, rows, cols, 1)
return data
def dense_to_one_hot(labels_dense, num_classes):
"""Convert class labels from scalars to one-hot vectors."""
num_labels = labels_dense.shape[0]
index_offset = numpy.arange(num_labels) * num_classes
labels_one_hot = numpy.zeros((num_labels, num_classes))
labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
return labels_one_hot
def extract_labels(f, one_hot=False, num_classes=10):
"""Extract the labels into a 1D uint8 numpy array [index].
Args:
f: A file object that can be passed into a gzip reader.
one_hot: Does one hot encoding for the result.
num_classes: Number of classes for the one hot encoding.
Returns:
labels: a 1D uint8 numpy array.
Raises:
ValueError: If the bystream doesn't start with 2049.
"""
print('Extracting', f.name)
with gzip.GzipFile(fileobj=f) as bytestream:
magic = _read32(bytestream)
if magic != 2049:
raise ValueError('Invalid magic number %d in MNIST label file: %s' %
(magic, f.name))
num_items = _read32(bytestream)
buf = bytestream.read(num_items)
labels = numpy.frombuffer(buf, dtype=numpy.uint8)
if one_hot:
return dense_to_one_hot(labels, num_classes)
return labels
def load_dataset(directory, images_file, labels_file):
"""Download and parse MNIST dataset."""
images_file = download(directory, images_file)
labels_file = download(directory, labels_file)
with tf.gfile.Open(images_file, 'rb') as f:
images = extract_images(f)
with tf.gfile.Open(labels_file, 'rb') as f:
labels = extract_labels(f)
return images, labels
directory = params['download_data_location']
validation_size=5000
train_images, train_labels = load_dataset(directory, 'train-images-idx3-ubyte', 'train-labels-idx1-ubyte')
test_images, test_labels = load_dataset(directory, 't10k-images-idx3-ubyte', 't10k-labels-idx1-ubyte')
validation_images = train_images[:validation_size]
validation_labels = train_labels[:validation_size]
train_images = train_images[validation_size:]
train_labels = train_labels[validation_size:]
name = "train.tfrecords"
filename = os.path.join(params['tfrecord_location'], name)
tfrecord_writer = tf.python_io.TFRecordWriter(filename)
def _int64_feature(value):
return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
train_images.shape[0]
num_examples = train_images.shape[0]
images = train_images
labels = train_labels
rows = images.shape[1]
cols = images.shape[2]
depth = images.shape[3]
for index in range(num_examples):
# 1. Convert your data into tf.train.Feature
image_raw = images[index].tostring()
feature = {
'height': _int64_feature(rows),
'width': _int64_feature(cols),
'depth': _int64_feature(depth),
'label': _int64_feature(int(labels[index])),
'image_raw': _bytes_feature(image_raw)
}
# 2. Create a tf.train.Features
features = tf.train.Features(feature=feature)
# 3. Createan example protocol
example = tf.train.Example(features=features)
# 4. Serialize the Example to string
example_to_string = example.SerializeToString()
# 5. Write to TFRecord
tfrecord_writer.write(example_to_string)
def convert_and_save_to(images, labels , name, params):
"""Converts a TF dataset to tfrecords."""
num_examples = images.shape[0]
rows = images.shape[1]
cols = images.shape[2]
depth = images.shape[3]
filename = os.path.join(params['tfrecord_location'], name + '.tfrecords')
print('Writing', filename)
with tf.python_io.TFRecordWriter(filename) as writer:
for index in range(num_examples):
image_raw = images[index].tostring()
feature={
'label': _int64_feature(int(labels[index])),
'image_raw': _bytes_feature(image_raw)
}
features=tf.train.Features(feature=feature)
example = tf.train.Example(features=features)
writer.write(example.SerializeToString())
# Convert to Examples and write the result to TFRecord files.
convert_and_save_to(train_images, train_labels, 'train', params)
convert_and_save_to(test_images, test_labels, 'test', params)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.