TensorFLow 不同大小图片的TFrecords存取实例

yipeiwu_com5年前Python基础

全部存入一个TFrecords文件,然后读取并显示第一张。

不多写了,直接贴代码。

from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf


IMAGE_PATH = 'test/'
tfrecord_file = IMAGE_PATH + 'test.tfrecord'
writer = tf.python_io.TFRecordWriter(tfrecord_file)


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]))

def get_image_binary(filename):
  """ You can read in the image using tensorflow too, but it's a drag
    since you have to create graphs. It's much easier using Pillow and NumPy
  """
  image = Image.open(filename)
  image = np.asarray(image, np.uint8)
  shape = np.array(image.shape, np.int32)
  return shape, image.tobytes() # convert image to raw data bytes in the array.

def write_to_tfrecord(label, shape, binary_image, tfrecord_file):
  """ This example is to write a sample to TFRecord file. If you want to write
  more samples, just use a loop.
  """
  # write label, shape, and image content to the TFRecord file
  example = tf.train.Example(features=tf.train.Features(feature={
        'label': _int64_feature(label),
        'h': _int64_feature(shape[0]),
        'w': _int64_feature(shape[1]),
        'c': _int64_feature(shape[2]),
        'image': _bytes_feature(binary_image)
        }))
  writer.write(example.SerializeToString())


def write_tfrecord(label, image_file, tfrecord_file):
  shape, binary_image = get_image_binary(image_file)
  write_to_tfrecord(label, shape, binary_image, tfrecord_file)
  # print(shape)



def main():
  # assume the image has the label Chihuahua, which corresponds to class number 1
  label = [1,2]
  image_files = [IMAGE_PATH + 'a.jpg', IMAGE_PATH + 'b.jpg']

  for i in range(2):
    write_tfrecord(label[i], image_files[i], tfrecord_file)
  writer.close()

  batch_size = 2

  filename_queue = tf.train.string_input_producer([tfrecord_file]) 
  reader = tf.TFRecordReader() 
  _, serialized_example = reader.read(filename_queue) 

  img_features = tf.parse_single_example( 
                    serialized_example, 
                    features={ 
                        'label': tf.FixedLenFeature([], tf.int64), 
                        'h': tf.FixedLenFeature([], tf.int64),
                        'w': tf.FixedLenFeature([], tf.int64),
                        'c': tf.FixedLenFeature([], tf.int64),
                        'image': tf.FixedLenFeature([], tf.string), 
                        }) 

  h = tf.cast(img_features['h'], tf.int32)
  w = tf.cast(img_features['w'], tf.int32)
  c = tf.cast(img_features['c'], tf.int32)

  image = tf.decode_raw(img_features['image'], tf.uint8) 
  image = tf.reshape(image, [h, w, c])

  label = tf.cast(img_features['label'],tf.int32) 
  label = tf.reshape(label, [1])

 # image = tf.image.resize_images(image, (500,500))
  #image, label = tf.train.batch([image, label], batch_size= batch_size) 


  with tf.Session() as sess:
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)
    image, label=sess.run([image, label])
    coord.request_stop()
    coord.join(threads)

    print(label)

    plt.figure()
    plt.imshow(image)
    plt.show()


if __name__ == '__main__':
  main()

全部存入一个TFrecords文件,然后按照batch_size读取,注意需要将图片变成一样大才能按照batch_size读取。

from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf


IMAGE_PATH = 'test/'
tfrecord_file = IMAGE_PATH + 'test.tfrecord'
writer = tf.python_io.TFRecordWriter(tfrecord_file)


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]))

def get_image_binary(filename):
  """ You can read in the image using tensorflow too, but it's a drag
    since you have to create graphs. It's much easier using Pillow and NumPy
  """
  image = Image.open(filename)
  image = np.asarray(image, np.uint8)
  shape = np.array(image.shape, np.int32)
  return shape, image.tobytes() # convert image to raw data bytes in the array.

def write_to_tfrecord(label, shape, binary_image, tfrecord_file):
  """ This example is to write a sample to TFRecord file. If you want to write
  more samples, just use a loop.
  """
  # write label, shape, and image content to the TFRecord file
  example = tf.train.Example(features=tf.train.Features(feature={
        'label': _int64_feature(label),
        'h': _int64_feature(shape[0]),
        'w': _int64_feature(shape[1]),
        'c': _int64_feature(shape[2]),
        'image': _bytes_feature(binary_image)
        }))
  writer.write(example.SerializeToString())


def write_tfrecord(label, image_file, tfrecord_file):
  shape, binary_image = get_image_binary(image_file)
  write_to_tfrecord(label, shape, binary_image, tfrecord_file)
  # print(shape)



def main():
  # assume the image has the label Chihuahua, which corresponds to class number 1
  label = [1,2]
  image_files = [IMAGE_PATH + 'a.jpg', IMAGE_PATH + 'b.jpg']

  for i in range(2):
    write_tfrecord(label[i], image_files[i], tfrecord_file)
  writer.close()

  batch_size = 2

  filename_queue = tf.train.string_input_producer([tfrecord_file]) 
  reader = tf.TFRecordReader() 
  _, serialized_example = reader.read(filename_queue) 

  img_features = tf.parse_single_example( 
                    serialized_example, 
                    features={ 
                        'label': tf.FixedLenFeature([], tf.int64), 
                        'h': tf.FixedLenFeature([], tf.int64),
                        'w': tf.FixedLenFeature([], tf.int64),
                        'c': tf.FixedLenFeature([], tf.int64),
                        'image': tf.FixedLenFeature([], tf.string), 
                        }) 

  h = tf.cast(img_features['h'], tf.int32)
  w = tf.cast(img_features['w'], tf.int32)
  c = tf.cast(img_features['c'], tf.int32)

  image = tf.decode_raw(img_features['image'], tf.uint8) 
  image = tf.reshape(image, [h, w, c])

  label = tf.cast(img_features['label'],tf.int32) 
  label = tf.reshape(label, [1])

  image = tf.image.resize_images(image, (224,224))
  image = tf.reshape(image, [224, 224, 3])
  image, label = tf.train.batch([image, label], batch_size= batch_size) 


  with tf.Session() as sess:
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)
    image, label=sess.run([image, label])
    coord.request_stop()
    coord.join(threads)

    print(image.shape)
    print(label)

    plt.figure()
    plt.imshow(image[0,:,:,0])
    plt.show()

    plt.figure()
    plt.imshow(image[0,:,:,1])
    plt.show()

    image1 = image[0,:,:,:]
    print(image1.shape)
    print(image1.dtype)
    im = Image.fromarray(np.uint8(image1)) #参考numpy和图片的互转:http://blog.csdn.net/zywvvd/article/details/72810360
    im.show()

if __name__ == '__main__':
  main()

输出是

(2, 224, 224, 3)
[[1]
 [2]]

第一张图片的三种显示(略)

封装成函数:

# -*- coding: utf-8 -*-
"""
Created on Fri Sep 8 14:38:15 2017

@author: wayne


"""


'''
本文参考了以下代码,在多个不同大小图片存取方面做了重新开发:
https://github.com/chiphuyen/stanford-tensorflow-tutorials/blob/master/examples/09_tfrecord_example.py
http://blog.csdn.net/hjxu2016/article/details/76165559
https://stackoverflow.com/questions/41921746/tensorflow-varlenfeature-vs-fixedlenfeature
https://github.com/tensorflow/tensorflow/issues/10492

后续:
-存入多个TFrecords文件的例子见
http://blog.csdn.net/xierhacker/article/details/72357651
-如何作shuffle和数据增强
string_input_producer (需要理解tf的数据流,标签队列的工作方式等等)
http://blog.csdn.net/liuchonge/article/details/73649251
'''

from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf


IMAGE_PATH = 'test/'
tfrecord_file = IMAGE_PATH + 'test.tfrecord'
writer = tf.python_io.TFRecordWriter(tfrecord_file)


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]))

def get_image_binary(filename):
  """ You can read in the image using tensorflow too, but it's a drag
    since you have to create graphs. It's much easier using Pillow and NumPy
  """
  image = Image.open(filename)
  image = np.asarray(image, np.uint8)
  shape = np.array(image.shape, np.int32)
  return shape, image.tobytes() # convert image to raw data bytes in the array.

def write_to_tfrecord(label, shape, binary_image, tfrecord_file):
  """ This example is to write a sample to TFRecord file. If you want to write
  more samples, just use a loop.
  """
  # write label, shape, and image content to the TFRecord file
  example = tf.train.Example(features=tf.train.Features(feature={
        'label': _int64_feature(label),
        'h': _int64_feature(shape[0]),
        'w': _int64_feature(shape[1]),
        'c': _int64_feature(shape[2]),
        'image': _bytes_feature(binary_image)
        }))
  writer.write(example.SerializeToString())


def write_tfrecord(label, image_file, tfrecord_file):
  shape, binary_image = get_image_binary(image_file)
  write_to_tfrecord(label, shape, binary_image, tfrecord_file)


def read_and_decode(tfrecords_file, batch_size): 
  '''''read and decode tfrecord file, generate (image, label) batches 
  Args: 
    tfrecords_file: the directory of tfrecord file 
    batch_size: number of images in each batch 
  Returns: 
    image: 4D tensor - [batch_size, width, height, channel] 
    label: 1D tensor - [batch_size] 
  ''' 
  # make an input queue from the tfrecord file 

  filename_queue = tf.train.string_input_producer([tfrecord_file]) 
  reader = tf.TFRecordReader() 
  _, serialized_example = reader.read(filename_queue) 

  img_features = tf.parse_single_example( 
                    serialized_example, 
                    features={ 
                        'label': tf.FixedLenFeature([], tf.int64), 
                        'h': tf.FixedLenFeature([], tf.int64),
                        'w': tf.FixedLenFeature([], tf.int64),
                        'c': tf.FixedLenFeature([], tf.int64),
                        'image': tf.FixedLenFeature([], tf.string), 
                        }) 

  h = tf.cast(img_features['h'], tf.int32)
  w = tf.cast(img_features['w'], tf.int32)
  c = tf.cast(img_features['c'], tf.int32)

  image = tf.decode_raw(img_features['image'], tf.uint8) 
  image = tf.reshape(image, [h, w, c])

  label = tf.cast(img_features['label'],tf.int32) 
  label = tf.reshape(label, [1])

  ########################################################## 
  # you can put data augmentation here  
#  distorted_image = tf.random_crop(images, [530, 530, img_channel])
#  distorted_image = tf.image.random_flip_left_right(distorted_image)
#  distorted_image = tf.image.random_brightness(distorted_image, max_delta=63)
#  distorted_image = tf.image.random_contrast(distorted_image, lower=0.2, upper=1.8)
#  distorted_image = tf.image.resize_images(distorted_image, (imagesize,imagesize))
#  float_image = tf.image.per_image_standardization(distorted_image)

  image = tf.image.resize_images(image, (224,224))
  image = tf.reshape(image, [224, 224, 3])
  #image, label = tf.train.batch([image, label], batch_size= batch_size) 

  image_batch, label_batch = tf.train.batch([image, label], 
                        batch_size= batch_size, 
                        num_threads= 64,  
                        capacity = 2000) 
  return image_batch, tf.reshape(label_batch, [batch_size]) 

def read_tfrecord2(tfrecord_file, batch_size):
  train_batch, train_label_batch = read_and_decode(tfrecord_file, batch_size)

  with tf.Session() as sess:
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)
    train_batch, train_label_batch = sess.run([train_batch, train_label_batch])
    coord.request_stop()
    coord.join(threads)
  return train_batch, train_label_batch


def main():
  # assume the image has the label Chihuahua, which corresponds to class number 1
  label = [1,2]
  image_files = [IMAGE_PATH + 'a.jpg', IMAGE_PATH + 'b.jpg']

  for i in range(2):
    write_tfrecord(label[i], image_files[i], tfrecord_file)
  writer.close()

  batch_size = 2
  # read_tfrecord(tfrecord_file) # 读取一个图
  train_batch, train_label_batch = read_tfrecord2(tfrecord_file, batch_size)

  print(train_batch.shape)
  print(train_label_batch)

  plt.figure()
  plt.imshow(train_batch[0,:,:,0])
  plt.show()

  plt.figure()
  plt.imshow(train_batch[0,:,:,1])
  plt.show()

  train_batch1 = train_batch[0,:,:,:]
  print(train_batch.shape)
  print(train_batch1.dtype)
  im = Image.fromarray(np.uint8(train_batch1)) #参考numpy和图片的互转:http://blog.csdn.net/zywvvd/article/details/72810360
  im.show()

if __name__ == '__main__':
  main()

以上这篇TensorFLow 不同大小图片的TFrecords存取实例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持【听图阁-专注于Python设计】。

相关文章

在Python中处理XML的教程

XML虽然比JSON复杂,在Web中应用也不如以前多了,不过仍有很多地方在用,所以,有必要了解如何操作XML。 DOM vs SAX 操作XML有两种方法:DOM和SAX。DOM会把整个...

Python中time模块与datetime模块在使用中的不同之处

Python 中提供了对时间日期的多种多样的处理方式,主要是在 time 和 datetime 这两个模块里。今天稍微梳理一下这两个模块在使用上的一些区别和联系。 time 在 Pyth...

python+webdriver自动化环境搭建步骤详解

python+webdriver自动化环境搭建步骤详解

python是一个很好脚本语言工具,现在也比较流行的一个脚本语言工具,对目前web自动化可以用的比较是webdriver框架进行自动化测试,脚本写起来较简单,运行的占用的内容较小。那么对...

python实现上传文件到linux指定目录的方法

python实现上传文件到linux指定目录的方法

今天接到一个小需求,就是想在windows环境下,上传压缩文件到linux指定的目录位置并且解压出来,然后我想了一下,这个可以用python试试写下。 环境: 1.linux操作系统一台...

Python实现的科学计算器功能示例

本文实例讲述了Python实现的科学计算器功能。分享给大家供大家参考,具体如下: import wx import re import math # begin wxGlade: e...