猫狗大战Tensorflow1.4.0（2）

最近课程project要识别猫和狗，做一个自动投食机。目前思考方案是先在ubuntu虚拟机上训练好模型，然后放到树莓派上跑视觉识别，并发指令给ardiuno完成相应动作。无奈ubuntu虚拟机实在跑不动Tensorflow，于是只好放在mac上跑。这里讲一下mac从0开始跑猫狗识别。

首先mac是自带python2.7的，但是python2.7马上就不支持维护了，于是首先要装python3，安装python3方法也有很多，可以看考官方文档：

https://tensorflow.juejin.im/install/install_mac.html#toc-18

brew是一个非常好管理mac文档的东西，但是brew提供的python是最新版的3.7，对于tensorflow的兼容并不友好，于是推荐可以到python的官网下载python3.4/3.5/3.6。

https://www.python.org/downloads/

安装好python3.5就可以开始安装tensorflow了。下面这篇教程写的非常好：

https://zhuanlan.zhihu.com/p/28362186

但是按照默认的来安装的话是安装最新版的tensorflow2.0了，因此跟网上贴出的许多基于tensorflow1.x的代码兼容性不高，作为tensorflow小白果断选择了安装老版本的tensorflow。

只要把下面这句：

pip3 install --upgrade tensorflow

换成：

pip3 install https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-1.4.0-py3-none-any.whl

就是安装tensorflow1.4.0了，要装其他版本的tensorflow把对应版本换一下就行。

下面开始贴代码，该代码在网上广为流传，在python3.5.2和tensorflow1.4.0亲测可用。新建4个py文件，input_data.py，model.py，training.py 和test.py，分别用来读入处理图片，建立卷积层，训练模型和测试训练好的模型。

input_data.py:

#coding=utf-8
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
import numpy as np

def get_files(file_dir):
	cats = []
	label_cats = []
	dogs = []
	label_dogs = []
	for file in os.listdir(file_dir):
		name = file.split(sep='.')
		if 'cat' in name[0]:
			cats.append(file_dir + file)
			label_cats.append(0)
		else:
			if 'dog' in name[0]:
				dogs.append(file_dir + file)
				label_dogs.append(1)
		image_list = np.hstack((cats,dogs))
		label_list = np.hstack((label_cats,label_dogs))
			# print('There are %d cats\nThere are %d dogs' %(len(cats), len(dogs)))
			# 多个种类分别的时候需要把多个种类放在一起，打乱顺序,这里不需要
     
	# 把标签和图片都放倒一个 temp 中 然后打乱顺序，然后取出来
	temp = np.array([image_list,label_list])
	temp = temp.transpose()
	# 打乱顺序
	np.random.shuffle(temp)

	# 取出第一个元素作为 image 第二个元素作为 label
	image_list = list(temp[:,0])
	label_list = list(temp[:,1])
	label_list = [int(i) for i in label_list]  
	return image_list,label_list

# 测试 get_files
#imgs , label = get_files("/Users/cenjun/Desktop/Sensor/train")
#for i in imgs:
#  print("img:",i)
#
#for i in label:
#  print('label:',i)
#测试 get_files end


# image_W ,image_H 指定图片大小，batch_size 每批读取的个数 ，capacity队列中 最多容纳元素的个数
def get_batch(image,label,image_W,image_H,batch_size,capacity):
	# 转换数据为 ts 能识别的格式
	image = tf.cast(image,tf.string)
	label = tf.cast(label, tf.int32)

	# 将image 和 label 放倒队列里 
	input_queue = tf.train.slice_input_producer([image,label])
	label = input_queue[1]
	# 读取图片的全部信息
	image_contents = tf.read_file(input_queue[0])
	# 把图片解码，channels ＝3 为彩色图片, r，g ，b  黑白图片为 1 ，也可以理解为图片的厚度
	image = tf.image.decode_jpeg(image_contents,channels =3)
	# 将图片以图片中心进行裁剪或者扩充为 指定的image_W，image_H
	image = tf.image.resize_image_with_crop_or_pad(image, image_W, image_H)
	# 对数据进行标准化,标准化，就是减去它的均值，除以他的方差
	image = tf.image.per_image_standardization(image)

	# 生成批次  num_threads 有多少个线程根据电脑配置设置  capacity 队列中 最多容纳图片的个数  tf.train.shuffle_batch 打乱顺序，
	image_batch, label_batch = tf.train.batch([image, label],batch_size = batch_size, num_threads = 64, capacity = capacity)
	
    # 重新定义下 label_batch 的形状
	label_batch = tf.reshape(label_batch , [batch_size])
	# 转化图片
	image_batch = tf.cast(image_batch,tf.float32)
	return  image_batch, label_batch

# TEST
#import matplotlib
#matplotlib.use('TkAgg')
#import matplotlib.pyplot as plt
#
#BATCH_SIZE = 2
#CAPACITY = 256
#IMG_W = 208
#IMG_H = 208
#
#train_dir = "/Users/cenjun/Desktop/Sensor/train/"
#image_list, label_list = get_files(train_dir)
#image_batch, label_batch = get_batch(image_list, label_list, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
#
#with tf.Session() as sess:
#    i = 0
#    coord = tf.train.Coordinator()
#    threads = tf.train.start_queue_runners(coord=coord)
#    try:
#        while not coord.should_stop() and i < 1:
#            img, label = sess.run([image_batch, label_batch])
#
#            for j in np.arange(BATCH_SIZE):
#                print("label: %d" % label[j])
#                plt.imshow(img[j, :, :, :])
#                plt.show()
#            i += 1
#    except tf.errors.OutOfRangeError:
#        print("done!")
#    finally:
#        coord.request_stop()
#    coord.join(threads)
  

这里一定要注意一个大坑！图片的文件夹路径最后必须要加/，也就是像我这样"/Users/cenjun/Desktop/Sensor/train/"，如果是"/Users/cenjun/Desktop/Sensor/train"就不行！在下面一个形成batch的test时候会报错！但是在ubuntu中就没有这个坑，搞了好久这个bug。

model.py:

#coding=utf-8  
import tensorflow as tf  

def inference(images, batch_size, n_classes):  
  
    with tf.variable_scope('conv1') as scope: 
     # 卷积盒的为 3*3 的卷积盒，图片厚度是3，输出是16个featuremap
        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)  
  
    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')  
  
    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')  
  
    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):  
    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):  
    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):  
    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

training.py:

#coding=utf-8  
import os 
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import numpy as np  
import tensorflow as tf  
import input_data     
import model  

  
N_CLASSES = 2  # 2个输出神经元，［1，0］ 或者 ［0，1］猫和狗的概率
IMG_W = 208  # 重新定义图片的大小，图片如果过大则训练比较慢  
IMG_H = 208  
BATCH_SIZE = 8  #每批数据的大小
CAPACITY = 16  
MAX_STEP = 15000 # 训练的步数，应当 >= 10000
learning_rate = 0.0001 # 学习率，建议刚开始的 learning_rate <= 0.0001
  

def run_training():  
      
    # 数据集
    train_dir = '/Users/cenjun/Desktop/Sensor/train/'   #My dir--20170727-csq  
    #logs_train_dir 存放训练模型的过程的数据，在tensorboard 中查看 
    logs_train_dir = '/Users/cenjun/Desktop/Sensor/res/'  

    # 获取图片和标签集
    train, train_label = input_data.get_files(train_dir)  
    # 生成批次
    train_batch, train_label_batch = input_data.get_batch(train,  
                                                          train_label,  
                                                          IMG_W,  
                                                          IMG_H,  
                                                          BATCH_SIZE,   
                                                          CAPACITY)
    # 进入模型
    train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES) 
    # 获取 loss 
    train_loss = model.losses(train_logits, train_label_batch)
    # 训练 
    train_op = model.trainning(train_loss, learning_rate)
    # 获取准确率 
    train__acc = model.evaluation(train_logits, train_label_batch)  
    # 合并 summary
    summary_op = tf.summary.merge_all()  
    sess = tf.Session()
    # 保存summary
    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:  
                # 每隔2000步保存一下模型，模型保存在 checkpoint_path 中
                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()  

# train
run_training()

然后打开终端开始跑就可以了，跑的过程中如下：

接下来就是漫长的等待时间了。
算完之后运行test.py:

#coding=utf-8  
import tensorflow as tf 
from PIL import Image
import matplotlib
matplotlib.use('TkAgg')
import matplotlib.pyplot as plt
import input_data 
import numpy as np
import model
import os 
 
#从指定目录中选取一张图片 
def get_one_image(train): 
    files = os.listdir(train)
    n = len(files)
    ind = np.random.randint(0,n)
    img_dir = os.path.join(train,files[ind])  
    image = Image.open(img_dir)  
    plt.imshow(image)
    plt.show()
    image = image.resize([208, 208])  
    image = np.array(image)
    return image  
 
 
def evaluate_one_image():  
    #存放的是我从百度下载的猫狗图片路径
    train = '/Users/cenjun/Desktop/Sensor/train/' 
    image_array = get_one_image(train)  
 
    with tf.Graph().as_default():  
        BATCH_SIZE = 1  # 因为只读取一副图片 所以batch 设置为1
        N_CLASSES = 2  # 2个输出神经元，［1，0］ 或者 ［0，1］猫和狗的概率
        # 转化图片格式
        image = tf.cast(image_array, tf.float32)  
        # 图片标准化
        image = tf.image.per_image_standardization(image)
        # 图片原来是三维的 [208, 208, 3] 重新定义图片形状 改为一个4D  四维的 tensor
        image = tf.reshape(image, [1, 208, 208, 3])  
        logit = model.inference(image, BATCH_SIZE, N_CLASSES)  
        # 因为 inference 的返回没有用激活函数，所以在这里对结果用softmax 激活
        logit = tf.nn.softmax(logit)  
 
        # 用最原始的输入数据的方式向模型输入数据 placeholder
        x = tf.placeholder(tf.float32, shape=[208, 208, 3])  
 
        # 我门存放模型的路径
        logs_train_dir = '/Users/cenjun/Desktop/Sensor/res/'   
        # 定义saver 
        saver = tf.train.Saver()  
 
        with tf.Session() as sess:  
 
            print("从指定的路径中加载模型。。。。")
            # 将模型加载到sess 中 
            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('模型加载成功, 训练的步数为 %s' % global_step)  
            else:  
                print('模型加载失败，，，文件没有找到')  
            # 将图片输入到模型计算
            prediction = sess.run(logit, feed_dict={x: image_array})
            # 获取输出结果中最大概率的索引
            max_index = np.argmax(prediction)  
            if max_index==0:  
                print('猫的概率 %.6f' %prediction[:, 0])  
            else:  
                print('狗的概率 %.6f' %prediction[:, 1]) 
# 测试
evaluate_one_image()

这样会在train文件夹下面随意选一张图片进行识别，并给出猫和狗的概率。