Python_2019-01-08_机器学习——Tensorflow一个卷积神经网络分类模型

目录

​

第一步：【网络输入】

第二步：【net网络搭建、loss损失函数、op梯度下降、acc评估模型】

第三步：【保存加载】

第四步：【开始训练】

第五步：【评估验证】

第六步：【训练监测】

 

---

第一步：【网络输入】

data文件夹{0，1，2，3。。。等类}，默认224*224*3的图

命令行：python tfrecords.py -i data

或者做成子程序调用

#coding=utf-8
# author:dongjinhua 
# data:2010107
import os
import getopt
import tensorflow as tf
from PIL import Image
import sys

'''
制作tfrecords数据：
creat_tfrecords(train_dir)

读取tfrecords数据
images, labels = read_and_decode('./train.tfrecords')

batch数据
img_batch, label_batch = tf.train.shuffle_batch([images, labels],
                                                batch_size=batch_size,
                                                capacity=392,
                                                min_after_dequeue=200)
'''
IMG_W = 224
IMG_H = 224
def creat_tfrecords(imgpath):

    cwd = os.getcwd() # 获取当前目录
    classes = os.listdir(cwd + imgpath)

    writer = tf.python_io.TFRecordWriter("train.tfrecords")
    for index, name in enumerate(classes):
        class_path = cwd + imgpath + name + "/"
        print(class_path)
        if os.path.isdir(class_path):
            for img_name in os.listdir(class_path):
                img_path = class_path + img_name
                img = Image.open(img_path)
                img = img.resize((IMG_W, IMG_H))
                img_raw = img.tobytes()              #将图片转化为原生bytes
                example = tf.train.Example(features=tf.train.Features(feature={
                'label': tf.train.Feature(int64_list=tf.train.Int64List(value=[int(name)])),
                'img_raw': tf.train.Feature(bytes_list=tf.train.BytesList(value=[img_raw]))
            }))
                writer.write(example.SerializeToString())  #序列化为字符串
                print(img_name)
    writer.close()

def read_and_decode(filename):
    #根据文件名生成一个队列
    filename_queue = tf.train.string_input_producer([filename])

    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)   #返回文件名和文件
    features = tf.parse_single_example(serialized_example,
                                       features={
                                           'label': tf.FixedLenFeature([], tf.int64),
                                           'img_raw' : tf.FixedLenFeature([], tf.string),
                                       })

    img = tf.decode_raw(features['img_raw'], tf.uint8)
    img = tf.reshape(img, [IMG_W, IMG_H, 3])
    # 转换为float32类型，并做归一化处理
    img = tf.cast(img, tf.float32)# * (1. / 255)
    label = tf.cast(features['label'], tf.int64)
    #print 'images的样子是：', img
    #print 'label的样子是：', label
    #pdb.set_trace()
    return img, label

def  main(argv):
    inputfile = ''    
    try:
        opts, args = getopt.getopt(argv, "hi:o:", ["ifile="])
    except getopt.GetoptError:
        print ('test.py -i <inputfile>')
        sys.exit(2)
    for opt, arg in opts:
        if opt == '-h':
            print ('test.py -i <inputfile>')
            sys.exit()
        elif opt in ("-i", "--ifile"):
            inputfile = arg
            inputfile = './' + inputfile + '\\'
            creat_tfrecords(inputfile)
    if inputfile == '':
        print('please test as "python test.py -i <inputfile>"')


if __name__ == '__main__':
    # 命令行：python tfrecords.py -i data或者将该文档做成没有main的子程序
    main(sys.argv[1:])

'''
if __name__ == '__main__':
  images, labels = read_and_decode('./train.tfrecords')
  img_batch, label_batch = tf.train.shuffle_batch([images, labels],
                                                    batch_size=batch_size,
                                                    capacity=392,
                                                    min_after_dequeue=200)
'''

第二步：【net网络搭建、loss损失函数、op梯度下降、acc评估模型】

#coding=utf-8  
import tensorflow as tf  
# 网络（net）
    # 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
# 损失函数（loss）
# 优化器（梯度下降op）
# 评估（准确率acc）
# 输入images、batch_size、n_classes
def net(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('pool1') 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('pool2') 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('fc1') 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('fc2') 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

第三步：【保存加载】

第四步：【开始训练】

第五步：【评估验证】

第六步：【训练监测】

tensorboard  --logdir=logs

或者直接：http://localhost:6006