TensorFLow 不同大小图片的TFrecords存取实例


Posted in Python onJanuary 20, 2020

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三水点靠木。

Python 相关文章推荐
Python异常处理总结
Aug 15 Python
python执行shell获取硬件参数写入mysql的方法
Dec 29 Python
Python实现PS滤镜特效Marble Filter玻璃条纹扭曲效果示例
Jan 29 Python
Python实现的多进程拷贝文件并显示百分比功能示例
Apr 09 Python
Python3实现定时任务的四种方式
Jun 03 Python
Python 3.6打包成EXE可执行程序的实现
Oct 18 Python
pygame库实现俄罗斯方块小游戏
Oct 29 Python
python爬虫实现获取下一页代码
Mar 13 Python
如何解决安装python3.6.1失败
Jul 01 Python
OpenCV 使用imread()函数读取图片的六种正确姿势
Jul 09 Python
python 读取串口数据的示例
Nov 09 Python
Python代码实现双链表
May 25 Python
python各层级目录下import方法代码实例
Jan 20 #Python
Python 识别12306图片验证码物品的实现示例
Jan 20 #Python
如何基于python实现归一化处理
Jan 20 #Python
tensorflow入门:tfrecord 和tf.data.TFRecordDataset的使用
Jan 20 #Python
tensorflow入门:TFRecordDataset变长数据的batch读取详解
Jan 20 #Python
python如何通过pyqt5实现进度条
Jan 20 #Python
python super用法及原理详解
Jan 20 #Python
You might like
建立动态的WML站点(二)
2006/10/09 PHP
php 归并排序 数组交集
2011/05/10 PHP
解析CodeIgniter自定义配置文件
2013/06/18 PHP
php实现对两个数组进行减法操作的方法
2015/04/17 PHP
php实现的pdo公共类定义与用法示例
2017/07/19 PHP
PHP基于自定义函数生成笛卡尔积的方法示例
2017/09/30 PHP
PHP+MySQL使用mysql_num_rows实现模糊查询图书信息功能
2018/05/31 PHP
Thinkphp 框架配置操作之配置加载与读取配置实例分析
2020/05/15 PHP
PHP7 其他修改
2021/03/09 PHP
JavaScript实现Sleep函数的代码
2007/03/04 Javascript
javascript innerText和innerHtml应用
2010/01/28 Javascript
js如何获取兄弟、父类等节点
2014/01/06 Javascript
一个CSS+jQuery实现的放大缩小动画效果
2014/02/19 Javascript
Windows 系统下安装和部署Egret的开发环境
2014/07/31 Javascript
JS清除字符串中重复值的实现方法
2016/08/03 Javascript
BootStrap中Table分页插件使用详解
2016/10/09 Javascript
详解vue2.0 transition 多个元素嵌套使用过渡
2017/06/19 Javascript
浅谈react+es6+webpack的基础配置
2017/08/09 Javascript
详解js中Array的方法及技巧
2018/09/12 Javascript
用jQuery实现抽奖程序
2020/04/12 jQuery
[00:44]TI7不朽珍藏III——军团指挥官不朽展示
2017/07/15 DOTA
2019 Python最新面试题及答案16道题
2019/04/11 Python
Pandas-Cookbook 时间戳处理方式
2019/12/07 Python
python实现图像拼接
2020/03/05 Python
de Bijenkorf比利时官网:荷兰最知名的百货商店
2017/06/29 全球购物
美国女性奢华品牌精品店:INTERMIX
2017/10/12 全球购物
Moda Operandi官网:美国奢侈品电商,海淘秀场T台同款
2020/05/26 全球购物
大专毕业生自我鉴定
2013/11/21 职场文书
学生自我鉴定
2013/12/18 职场文书
机电一体化应届生求职信范文
2014/01/24 职场文书
2014自主招生自荐信策略
2014/01/27 职场文书
宝宝满月酒主持词和仪式流程
2014/03/27 职场文书
绿色学校实施方案
2014/03/31 职场文书
淘宝客服专员岗位职责
2014/04/11 职场文书
大学生就业指导课心得体会
2016/01/15 职场文书
Java实现多文件上传功能
2021/06/30 Java/Android