tensorflow实战 猫狗大战（三）制作tfrecords数据集并显示与训练

内容参考大神猫狗大战视频，推荐大家先观看视频

本文为参考http://i.youku.com/deeplearning101 这位大神的视频所写的一些笔记

大神的代码

https://github.com/kevin28520/My-TensorFlow-tutorials

跑完视频中的代码，发现视频中在猫狗大战中并没有制作tf官方数据文件，tfrecords数据

作者在后面有视频讲解tfrecords数据集介绍，废话不多说，直接上代码

首先建立一个create_records.py文件，内容如下

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Tue Jul 25 00:12:41 2017

@author: hjxu
"""
import cv2 
import tensorflow as tf
import numpy as np
import os
import matplotlib.pyplot as plt
import skimage.io as io
from skimage import transform

#%%

def get_files(file_dir):
    '''
    Args:
        file_dir: file directory
    Returns:
        list of images and labels
    '''
    cats = []
    label_cats = []
    dogs = []
    label_dogs = []
    for file in os.listdir(file_dir):
        name = file.split('.')
        if name[0]=='cat':
            cats.append(file_dir + file)
            label_cats.append(0)
        else:
            dogs.append(file_dir + file)
            label_dogs.append(1)
    print('There are %d cats\nThere are %d dogs' %(len(cats), len(dogs)))
    
    image_list = np.hstack((cats, dogs))
    label_list = np.hstack((label_cats, label_dogs))
    
    temp = np.array([image_list, label_list])
    temp = temp.transpose()
    np.random.shuffle(temp)
    
    image_list = list(temp[:, 0])
    label_list = list(temp[:, 1])
    label_list = [int(i) for i in label_list]
    
    
    return image_list, label_list


#%%

def int64_feature(value):
  """Wrapper for inserting int64 features into Example proto."""
  if not isinstance(value, list):
    value = [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 convert_to_tfrecord(images, labels, save_dir, name):
    '''convert all images and labels to one tfrecord file.
    Args:
        images: list of image directories, string type
        labels: list of labels, int type
        save_dir: the directory to save tfrecord file, e.g.: '/home/folder1/'
        name: the name of tfrecord file, string type, e.g.: 'train'
    Return:
        no return
    Note:
        converting needs some time, be patient...
    '''
    
    filename =      (save_dir + name + '.tfrecords')
    n_samples = len(labels)
    
    if np.shape(images)[0] != n_samples:
        raise ValueError('Images size %d does not match label size %d.' %(images.shape[0], n_samples))
    
    
    
    # wait some time here, transforming need some time based on the size of your data.
    writer = tf.python_io.TFRecordWriter(filename)
    print('\nTransform start......')
    for i in np.arange(0, n_samples):
        try:
            image = cv2.imread(images[i])  
            image = cv2.resize(image, (208, 208))  
            b,g,r = cv2.split(image)  
            rgb_image = cv2.merge([r,g,b])  # this is suitable  
#            image = rgb_image.astype(np.float32) 
#            image = io.imread(images[i]) # type(image) must be array!  #这边是两种读取图像的方法
#            image = transform.resize(image, (208, 208))
#            image = np.asarray(image)
            image_raw =  rgb_image.tostring()
            label = int(labels[i])
            example = tf.train.Example(features=tf.train.Features(feature={
                            'label':int64_feature(label),
                            'image_raw': bytes_feature(image_raw)}))
            writer.write(example.SerializeToString())
        except IOError as e:
            print('Could not read:', images[i])
            print('error: %s' %e)
            print('Skip it!\n')
    writer.close()
    print('Transform done!')
    

#%%

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([tfrecords_file])
    
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)
    img_features = tf.parse_single_example(
                                        serialized_example,
                                        features={
                                               'label': tf.FixedLenFeature([], tf.int64),
                                               'image_raw': tf.FixedLenFeature([], tf.string),
                                               })
    image = tf.decode_raw(img_features['image_raw'], tf.uint8)
    
    ##########################################################
    # you can put data augmentation here, I didn't use it
    ##########################################################
    # all the images of notMNIST are 28*28, you need to change the image size if you use other dataset.
    
    image = tf.reshape(image, [208, 208,3])
    label = tf.cast(img_features['label'], tf.float32)    
    image = tf.image.per_image_standardization(image)
    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])

上述代码中 def get_file(file_dir)

返回的是文件中保存图片的路径和对应的label

制作数据需要用writer = tf.python_io.TFRecordWriter(SAVE_PATH)

之后就需要将图片和标签转换成二进制文件保存到records文件中，这时候需要

 image_raw =  rgb_image.tostring()

函数来转换图片格式，注意，opencv和pIL读取进来的图片通道是不一样的，在转换的时候也要注意下，label只需要int一下转换格式就可以了

制作好tfrecords文件之后，该怎么解码这里面的二进制文件呢？这里面讲解的很全面http://www.2cto.com/kf/201611/561584.html

http://wiki.jikexueyuan.com/project/tensorflow-zh/how_tos/reading_data.html

tf提供解码函数

首先需要利用tf.train.string_input_producer()这个函数建立一个队列，利用tf.RecoderReader()和tf.parse_single_example()来将example协议内存块解析为张量

filename_queue = tf.train.string_input_producer([tfrecords_file])

 reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)
    img_features = tf.parse_single_example(
                                        serialized_example,
                                        features={
                                               'label': tf.FixedLenFeature([], tf.int64),
                                               'image_raw': tf.FixedLenFeature([], tf.string),
                                               })
    image = tf.decode_raw(img_features['image_raw'], tf.uint8)

tf.decode_raw()是将bytes转化成一个数字向量表示，下面就是训练了

建立一个model.py文件，模型和视频中的模型是一样的，

#%%
import tensorflow as tf

#%%
def inference(images, batch_size, n_classes):
    '''Build the model
    Args:
        images: image batch, 4D tensor, tf.float32, [batch_size, width, height, channels]
    Returns:
        output tensor with the computed logits, float, [batch_size, n_classes]
    '''
    #conv1, shape = [kernel size, kernel size, channels, kernel numbers]
    
    with tf.variable_scope('conv1') as scope:
        weights = tf.get_variable('weights', 
                                  shape = [3,3,3, 16],
                                  dtype = tf.float32, 
                                  initializer=tf.truncated_normal_initializer(stddev=0.1,dtype=tf.float32))
        biases = tf.get_variable('biases', 
                                 shape=[16],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
        conv = tf.nn.conv2d(images, weights, strides=[1,1,1,1], padding='SAME')
        pre_activation = tf.nn.bias_add(conv, biases)
        conv1 = tf.nn.relu(pre_activation, name= scope.name)
    
    #pool1 and norm1   
    with tf.variable_scope('pooling1_lrn') as scope:
        pool1 = tf.nn.max_pool(conv1, ksize=[1,3,3,1],strides=[1,2,2,1],
                               padding='SAME', name='pooling1')
        norm1 = tf.nn.lrn(pool1, depth_radius=4, bias=1.0, alpha=0.001/9.0,
                          beta=0.75,name='norm1')
    
    #conv2
    with tf.variable_scope('conv2') as scope:
        weights = tf.get_variable('weights',
                                  shape=[3,3,16,16],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.1,dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[16], 
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
        conv = tf.nn.conv2d(norm1, weights, strides=[1,1,1,1],padding='SAME')
        pre_activation = tf.nn.bias_add(conv, biases)
        conv2 = tf.nn.relu(pre_activation, name='conv2')
    
    
    #pool2 and norm2
    with tf.variable_scope('pooling2_lrn') as scope:
        norm2 = tf.nn.lrn(conv2, depth_radius=4, bias=1.0, alpha=0.001/9.0,
                          beta=0.75,name='norm2')
        pool2 = tf.nn.max_pool(norm2, ksize=[1,3,3,1], strides=[1,1,1,1],
                               padding='SAME',name='pooling2')
    
    
    #local3
    with tf.variable_scope('local3') as scope:
        reshape = tf.reshape(pool2, shape=[batch_size, -1])
        dim = reshape.get_shape()[1].value
        weights = tf.get_variable('weights',
                                  shape=[dim,128],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.005,dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[128],
                                 dtype=tf.float32, 
                                 initializer=tf.constant_initializer(0.1))
        local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)    
    
    #local4
    with tf.variable_scope('local4') as scope:
        weights = tf.get_variable('weights',
                                  shape=[128,128],
                                  dtype=tf.float32, 
                                  initializer=tf.truncated_normal_initializer(stddev=0.005,dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[128],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
        local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name='local4')
     
        
    # softmax
    with tf.variable_scope('softmax_linear') as scope:
        weights = tf.get_variable('softmax_linear',
                                  shape=[128, n_classes],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.005,dtype=tf.float32))
        biases = tf.get_variable('biases', 
                                 shape=[n_classes],
                                 dtype=tf.float32, 
                                 initializer=tf.constant_initializer(0.1))
        softmax_linear = tf.add(tf.matmul(local4, weights), biases, name='softmax_linear')
    
    return softmax_linear

#%%
def losses(logits, labels):
    '''Compute loss from logits and labels
    Args:
        logits: logits tensor, float, [batch_size, n_classes]
        labels: label tensor, tf.int32, [batch_size]
        
    Returns:
        loss tensor of float type
    '''
    with tf.variable_scope('loss') as scope:
        cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits\
                        (logits=logits, labels=labels, name='xentropy_per_example')
        loss = tf.reduce_mean(cross_entropy, name='loss')
        tf.summary.scalar(scope.name+'/loss', loss)
    return loss

#%%
def trainning(loss, learning_rate):
    '''Training ops, the Op returned by this function is what must be passed to 
        'sess.run()' call to cause the model to train.
        
    Args:
        loss: loss tensor, from losses()
        
    Returns:
        train_op: The op for trainning
    '''
    with tf.name_scope('optimizer'):
        optimizer = tf.train.AdamOptimizer(learning_rate= learning_rate)
        global_step = tf.Variable(0, name='global_step', trainable=False)
        train_op = optimizer.minimize(loss, global_step= global_step)
    return train_op

#%%
def evaluation(logits, labels):
  """Evaluate the quality of the logits at predicting the label.
  Args:
    logits: Logits tensor, float - [batch_size, NUM_CLASSES].
    labels: Labels tensor, int32 - [batch_size], with values in the
      range [0, NUM_CLASSES).
  Returns:
    A scalar int32 tensor with the number of examples (out of batch_size)
    that were predicted correctly.
  """
  with tf.variable_scope('accuracy') as scope:
      correct = tf.nn.in_top_k(logits, labels, 1)
      correct = tf.cast(correct, tf.float16)
      accuracy = tf.reduce_mean(correct)
      tf.summary.scalar(scope.name+'/accuracy', accuracy)
  return accuracy

#%%

然后调用建立一个train_records.py函数，调用tfrecords数据，来训练

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Wed Jul 26 18:17:37 2017

@author: hjxu
"""
#%%

import os
import numpy as np
import tensorflow as tf
#import input_data
import model
import create_records as cr
#%%

N_CLASSES = 2
IMG_W = 208  # resize the image, if the input image is too large, training will be very slow.
IMG_H = 208
BATCH_SIZE = 16
CAPACITY = 2000
MAX_STEP = 10000 # with current parameters, it is suggested to use MAX_STEP>10k
learning_rate = 0.0001 # with current parameters, it is suggested to use learning rate<0.0001


#%%
def run_training1():
    
    # you need to change the directories to yours.
#    train_dir = '/home/hjxu/PycharmProjects/01_cats_vs_dogs/data/train/'
    logs_train_dir = '/home/hjxu/PycharmProjects/01_cats_vs_dogs/logs/recordstrain/'
#    
#    train, train_label = input_data.get_files(train_dir)
    tfrecords_file = '/home/hjxu/PycharmProjects/01_cats_vs_dogs/tfrecords/test.tfrecords'
    train_batch, train_label_batch = cr.read_and_decode(tfrecords_file, batch_size=BATCH_SIZE)
    train_batch = tf.cast(train_batch,dtype=tf.float32)
    train_label_batch = tf.cast(train_label_batch,dtype=tf.int64)
    
    train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES)
    train_loss = model.losses(train_logits, train_label_batch)        
    train_op = model.trainning(train_loss, learning_rate)
    train__acc = model.evaluation(train_logits, train_label_batch)
       
    summary_op = tf.summary.merge_all()
    sess = tf.Session()
    train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
    saver = tf.train.Saver()
    
    sess.run(tf.global_variables_initializer())
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(sess=sess, coord=coord)
    
    try:
        for step in np.arange(MAX_STEP):
            if coord.should_stop():
                    break
            _, tra_loss, tra_acc = sess.run([train_op, train_loss, train__acc])
               
            if step % 50 == 0:
                print('Step %d, train loss = %.2f, train accuracy = %.2f%%' %(step, tra_loss, tra_acc*100.0))
                summary_str = sess.run(summary_op)
                train_writer.add_summary(summary_str, step)
            
            if step % 2000 == 0 or (step + 1) == MAX_STEP:
                checkpoint_path = os.path.join(logs_train_dir, 'model.ckpt')
                saver.save(sess, checkpoint_path, global_step=step)
                
    except tf.errors.OutOfRangeError:
        print('Done training -- epoch limit reached')
    finally:
        coord.request_stop()
        
    coord.join(threads)
    sess.close()
    
run_training1()
#%% Evaluate one image
# when training, comment the following codes.


#from PIL import Image
#import matplotlib.pyplot as plt
#
#def get_one_image(train):
#    '''Randomly pick one image from training data
#    Return: ndarray
#    '''
#    n = len(train)
#    ind = np.random.randint(0, n)
#    img_dir = train[ind]
#
#    image = Image.open(img_dir)
#    plt.imshow(image)
#    image = image.resize([208, 208])
#    image = np.array(image)
#    return image
#
#def evaluate_one_image():
#    '''Test one image against the saved models and parameters
#    '''
#    
#    # you need to change the directories to yours.
#    train_dir = '/home/kevin/tensorflow/cats_vs_dogs/data/train/'
#    train, train_label = input_data.get_files(train_dir)
#    image_array = get_one_image(train)
#    
#    with tf.Graph().as_default():
#        BATCH_SIZE = 1
#        N_CLASSES = 2
#        
#        image = tf.cast(image_array, tf.float32)
#        image = tf.image.per_image_standardization(image)
#        image = tf.reshape(image, [1, 208, 208, 3])
#        logit = model.inference(image, BATCH_SIZE, N_CLASSES)
#        
#        logit = tf.nn.softmax(logit)
#        
#        x = tf.placeholder(tf.float32, shape=[208, 208, 3])
#        
#        # you need to change the directories to yours.
#        logs_train_dir = '/home/kevin/tensorflow/cats_vs_dogs/logs/train/' 
#                       
#        saver = tf.train.Saver()
#        
#        with tf.Session() as sess:
#            
#            print("Reading checkpoints...")
#            ckpt = tf.train.get_checkpoint_state(logs_train_dir)
#            if ckpt and ckpt.model_checkpoint_path:
#                global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
#                saver.restore(sess, ckpt.model_checkpoint_path)
#                print('Loading success, global_step is %s' % global_step)
#            else:
#                print('No checkpoint file found')
#            
#            prediction = sess.run(logit, feed_dict={x: image_array})
#            max_index = np.argmax(prediction)
#            if max_index==0:
#                print('This is a cat with possibility %.6f' %prediction[:, 0])
#            else:
#                print('This is a dog with possibility %.6f' %prediction[:, 1])


#%%

然后建立一个evaluate_one_image.py文件

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Mon Jul 24 05:33:09 2017

@author: hjxu
"""

#%% Evaluate one image
# when training, comment the following codes.
import model
import numpy as np
from PIL import Image
import tensorflow as tf
import matplotlib.pyplot as plt
import input_data

def get_one_image(train):
    '''Randomly pick one image from training data
    Return: ndarray
    '''
    n = len(train)
    ind = np.random.randint(0, n)
    img_dir = train[ind]

    image = Image.open(img_dir)
    plt.imshow(image)
    image = image.resize([208, 208])
    image = np.array(image)
    return image


def get_one_img(img_dir):
    image = Image.open(img_dir)
    plt.imshow(image)
    image = image.resize([208, 208])
    image = np.array(image)
    return image
    
def evaluate_one_image():
    '''Test one image against the saved models and parameters
    '''
    
    # you need to change the directories to yours.
#    img_dir = '/home/hjxu/PycharmProjects/01_cats_vs_dogs/222.jpg'
#    image_array = get_one_img(img_dir)
    train_dir = '/home/hjxu/PycharmProjects/01_cats_vs_dogs/data/train/'
    train, train_label = input_data.get_files(train_dir)
    image_array = get_one_image(train)

    
    with tf.Graph().as_default():
        BATCH_SIZE = 1
        N_CLASSES = 2
        
        image = tf.cast(image_array, tf.float32)
        image = tf.image.per_image_standardization(image)
        image = tf.reshape(image, [1, 208, 208, 3])
        logit = model.inference(image, BATCH_SIZE, N_CLASSES)
        
        logit = tf.nn.softmax(logit)
        
        x = tf.placeholder(tf.float32, shape=[208, 208, 3])
        
        # you need to change the directories to yours.
        logs_train_dir = '/home/hjxu/PycharmProjects/01_cats_vs_dogs/logs/recordstrain/' 
                       
        saver = tf.train.Saver()
        
        with tf.Session() as sess:
            
            print("Reading checkpoints...")
            ckpt = tf.train.get_checkpoint_state(logs_train_dir)
            if ckpt and ckpt.model_checkpoint_path:
                global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
                saver.restore(sess, ckpt.model_checkpoint_path)
                print('Loading success, global_step is %s' % global_step)
            else:
                print('No checkpoint file found')
            
            prediction = sess.run(logit, feed_dict={x: image_array})
            max_index = np.argmax(prediction)
            if max_index==0:
                print('This is a cat with possibility %.6f' %prediction[:, 0])
            else:
                print('This is a dog with possibility %.6f' %prediction[:, 1])