tensorflow的简单应用，图片分类

图片分类

一.配置环境
我们用的环境是win10+anaconda+pycharm
1.安装anaconda
2.安装完成后，创建适用于tensorflow的虚环境，在anaconda prompt中输入以下命令

  	添加映像
 - conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
 - conda config --set show_channel_urls yes
	创建虚环境（tensorflow不支持Python3.7,我们这里使用python3.5，将该环境命名为fi
 - conda create -n fi python=3.5
	启动虚环境
 - activate fi
	安装tensorflow
 - pip install --upgrade --ignore-installed tensorflow

3.测似是否安装成功

 - 在anaconda prompt中的fi虚环境里启动python（输入python）
 - 测试代码如下
 - import tensorflow as tf
 - hello = tf.constant('Hello, TensorFlow!')
 - sess = tf.Session()
 - print(sess.run(hello))

4.部署pycharm

• pycharm的安装过程不再详述，首先new project-pure python,创建一个python项目
• File-settings-project,将之前设置的虚环境地址配置到pycharm中

pycharm配置完成
二.项目：
项目要求是分析图片是否经过了颜色修改
数据集来自imagenet
input_data.py

#我们的图片文件夹中是原图片和经过颜色修改过后的图片混在一起，文件名可以区分，我们先把图片分别择出来，添加标签
import tensorflow as tf
import os
import numpy as np


def get_files(file_dir):
    fakes = []
    label_fakes = []
    trues = []
    label_trues = []
    for file in os.listdir(file_dir):
        name = file.split(sep='.')
        if 'rich' in name[0]:
            fakes.append(file_dir + file)
            label_fakes.append(0)
        else:
            trues.append(file_dir + file)
            label_trues.append(1)
        image_list = np.hstack((fakes, trues))
        label_list = np.hstack((label_fakes, label_trues))
    # 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('D://Source//math_model//train_path//add//')
#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

model.py

#模型构建
# coding=utf-8
import tensorflow as tf


# 结构
# conv1   卷积层 1
# pooling1_lrn  池化层 1
# conv2  卷积层 2
# pooling2_lrn 池化层 2
# local3 全连接层 1
# local4 全连接层 2
# softmax 全连接层 3
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

train.py

import os
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 = 32  # 每批数据的大小
CAPACITY = 256
MAX_STEP = 20000  # 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 = 'D://Source//math_model//train_path//add//'  # 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 = 'D://Source//math_model//models//'

    # 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()

以上训练后设置的是每2000步保存一次模型，保存模型的文件夹最好在项目文件夹中
evaluate.py

# coding=utf-8
import tensorflow as tf
from PIL import Image
import numpy as np
import model
import os

#加载模型判断图片真假
def evaluate_one_image(image_array,dir):

    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] 假和真的概率
        # 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 = 'D://Source//math_model//models//'
        # 定义saver
        saver = tf.train.Saver()

        with tf.Session() as sess:

             #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)
            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)
            #print(str(dir)+str(prediction))
            if max_index == 0:
                print(str(dir)+'假的概率 %.6f' % prediction[:, 0])
            else:
                print(str(dir)+'真的概率 %.6f' % prediction[:, 1])
            # 测试


train = 'D://Source//math_model//train_path//test//'
files = os.listdir(train)
n = len(files)
for x in range(0,n):
    img_dir = os.path.join(train, files[x])
    image = Image.open(img_dir).convert("RGB")
    image = image.resize([208, 208])
    image = np.array(image)
    evaluate_one_image(image,img_dir)

完成！

参考博客
https://blog.youkuaiyun.com/u012052268/article/details/74202439?tdsourcetag=s_pcqq_aiomsg
https://blog.youkuaiyun.com/u012373815/article/details/78768727