作者 | 苏溪镇的水
出品 | AI科技大本营(ID:rgznai100)
在人工智能的发展越来越火热的今天,其中智能应用也在伴随着我们的生活,其中最具有代表性的便是图像识别,并且其中的应用比比皆是,如车站的人脸识别系统,交通的智能监控车牌号系统等等。而卷积神经网络作为图像识别的首选算法,对于图像的特征提取具有很好的效果,而TensorFlow作为Google的开源框架具有很好的结构化特征,而本篇文章将利用卷积神经网络算法对图像识别进行应用,开发出颜值评分器的功能。
首先我们准备训练的数据集文件保存在images文件夹下,其中的数据集如下:
其中需要训练的数据集的标签保存在Excel中,为All_Ratings.xlsx,即标签就为图像的颜值评分,其中的数据如下:
接着我们新建一个python文件为_input_data.py,即用来读取数据集以达到训练的目的。这里和卷积神经网络无关,故我仅仅大概说明一下并加以附上代码,其中要导入的模块代码:
代码语言:javascript复制import numpy as np
import tensorflow as tf
import os
import cv2
import matplotlib.pyplot as plt
import os
from PIL import Image
import pandas as pd
然后定义一个函数用来获取文件夹下的图片,并定义四个数组分别为meis,chous,chous_label,meis_label这几个数组分别保存着美人的图片名及路径,丑人的图片名及路径,丑人的标签设为0保存到chous_label这个数组中,美人的标签设为1保存在meis_label。代码如下:
代码语言:javascript复制def get_files(file_dir):
chous = []
meis = []
chous_label = []
meis_label = []
img_dirs = os.listdir(file_dir)#读取文件名下所有!目录名(列表形式)
labpath = "F:/python练习/test1/All_Ratings.xlsx"
date = pd.read_excel(labpath)
filenames = date['Filename']
label = date['Rating']
for i in range(filenames.shape[0]):
if int(label[i])>3:
meis_label.append(1)
meis.append(file_dir filenames[i])
else:
chous_label.append(0)
chous.append(file_dir filenames[i])
img_list = np.hstack((chous, meis))#列表(字符串形式)
label_list = np.hstack((chous_label, meis_label))#列表(整数形式)
return img_list, label_list
接着再定义一个函数用来获取图片的长和宽,一次训练的个数等等。具体代码如下:
代码语言:javascript复制def get_batch(image, label, image_w, image_h, batch_size, capacity):#capacity: 队列中 最多容纳图片的个数
input_queue = tf.train.slice_input_producer([image, label])#tf.train.slice_input_producer是一个tensor生成器,作用是
# 按照设定,每次从一个tensor列表中按顺序或者随机抽取出一个tensor放入文件名队列。
label = input_queue[1]
img_contents = tf.read_file(input_queue[0])#一维
image = tf.image.decode_jpeg(img_contents, channels=3)#解码成三维矩阵
image = tf.image.resize_image_with_crop_or_pad(image, image_w, image_h)
image = tf.cast(image, tf.float32)
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
image_batch, label_batch = tf.train.batch([image, label], batch_size=batch_size, num_threads=64, capacity=capacity)
return image_batch, label_batch
接着下面是卷积神经网络的算法部分,我们需要建立一个文件名为model.py的文件,用来保存算法结构参数,首先导入TensorFlow框架,代码为:
代码语言:javascript复制import tensorflow as tf
首先简单说明下这篇文章所用的卷积神经网络的原理和结构:其中第一层为输入层,即可以读取图像的各点像素值保存在矩阵中,接着为卷积一层我把它命名为“conv1”,即为第一个卷积层,即利用我定义的卷积核来乘上原来输入层的矩阵,而所谓的卷积核也就是一个矩阵,而其中相乘包括步长等等这里不详细说明。
接着接上一个池化层命名为“pooling1_lrn”,其主要目的是降采样,即将其中图像的像素矩阵变小。接着再接上卷积二层,命名为“conv2”,每一层的输入层为上一层的输出值,再接上池化二层“pooling2_lrn”,同样目的降采样,接着接上全连接层中的两个隐藏层名为“local3”,和“local4”,最后输出层接的是softmax激活函数,为二分类的激活函数,主要原因是我需要的结果是美和丑两种结果,详细代码见下:
代码语言:javascript复制import tensorflow as tf
#卷积神经网络提取特征
def inference(image, batch_size, n_classes):
#第一个卷积层
with tf.variable_scope("conv1") as scope:#课本108,variable_scope控制get_variable是获取(reuse=True)还是创建变量
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(image, 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)
#池化层,降采样
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")#局部响应归一化??????
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=scope.name)
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=[1,2,2,1], padding="SAME", name="pooling2")
#全连接层
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)
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二分类
with tf.variable_scope("softmax_linear") as scope:
weights = tf.get_variable("weights", 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.nn.relu(tf.matmul(local4, weights) biases,name="softmax_linear")
return softmax_linear
def loss(logits, labels):#输出结果和标准答案
with tf.variable_scope("loss") as scope:
cross_entropy= tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=labels, name="entropy_per_example")
loss = tf.reduce_mean(cross_entropy)
tf.summary.scalar(scope.name "/loss",loss)#对标量数据汇总和记录使用tf.summary.scalar
return loss
def training(loss, learning_rate):
with tf.name_scope("optimizer"):
global_step = tf.Variable(0, name="global_step", trainable=False)#定义训练的轮数,为不可训练的参数
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op= optimizer.minimize(loss, global_step=global_step)
#上两行等价于train_op = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss,global_step=global_step)
return train_op
def evalution(logits, labels):
with tf.variable_scope("accuracy") as scope:
correct = tf.nn.in_top_k(logits, labels, 1)#下面
correct = tf.cast(correct, tf.float16)
accuracy = tf.reduce_mean(correct)
tf.summary.scalar(scope.name "/accuracy", accuracy)#用来显示标量信息
return accuracy
"""
top_1_op取样本的最大预测概率的索引与实际标签对比,top_2_op取样本的最大和仅次最大的两个预测概率与实际标签对比,
如果实际标签在其中则为True,否则为False。
"""
其中定义的几个函数是为了训练使用而定义的,loss函数计算每次训练的损失值,training函数用来加载训练,包括损失值和学习率,evalution用来评估每次训练的精准度。
接着开始模型的训练,新建一个python文件名为“training.py”,其中设定常量:
代码语言:javascript复制N_CLASSES = 2
IMG_W = 350
IMG_H = 350
BATCH_SIZE = 32
CAPACITY = 256
STEP =500 #训练步数应当大于10000
LEARNING_RATE = 0.0001
分别表示结果输出为二分类(美和丑),图片的长和宽,每次训练的图片数目,训练容量,训练次数,学习率;接着将前面建立的python文件中的函数直接拿来使用,首先依旧是导入库以及前面建立的两个python文件:
代码语言:javascript复制import tensorflow as tf
import numpy as np
import os
import _input_data
import model
接着定义训练数据所保存的路径,模型保存的路径,其中应注意模型保存的路径中不能出现中文,否则报错;接着使用函数训练。详细代码如下:
代码语言:javascript复制x = tf.placeholder(tf.float32, shape=[None,129792])
y_ = tf.placeholder(tf.float32, shape=[None, 5])
def run_training():
train_dir = "F:/python练习/test1/Images/"
log_train_dir = "F:/train_savenet/"
train,train_labels = _input_data.get_files(train_dir)
train_batch, train_label_batch = _input_data.get_batch(train, train_labels, IMG_W,IMG_H,BATCH_SIZE,CAPACITY)
train_logits= model.inference(train_batch, BATCH_SIZE, N_CLASSES)
train_loss= model.loss(train_logits, train_label_batch)
train_op = model.training(train_loss, LEARNING_RATE)
train_acc = model.evalution(train_logits, train_label_batch)
summary_op = tf.summary.merge_all()#merge_all 可以将所有summary全部保存到磁盘,以便tensorboard显示。
# 一般这一句就可显示训练时的各种信息。
sess = tf.Session()
train_writer =tf.summary.FileWriter(log_train_dir, sess.graph)#指定一个文件用来保存图
saver = tf.train.Saver()
sess.run(tf.global_variables_initializer())
# Coordinator 和 start_queue_runners 监控 queue 的状态,不停的入队出队
coord = tf.train.Coordinator()#https://blog.csdn.net/weixin_42052460/article/details/80714539
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
for step in np.arange(STEP):
if coord.should_stop():
break
_, tra_loss, tra_acc = sess.run([train_op, train_loss, train_acc])
if step % 4 == 0 or (step 1) == STEP:
# 每隔2步保存一下模型,模型保存在 checkpoint_path 中
checkpoint_path = os.path.join(log_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_training()
训练过程如图:
训练完毕后,会形成一些训练出来模型文件,可以直接拿来使用,这时候建立一个python文件名为“predict.py”用来使用模型,这部分不是重点,给出代码和结果即可:
代码语言:javascript复制# -*- coding: utf-8 -*-
import tensorflow as tf
from PIL import Image
import numpy as np
import os
import model
import matplotlib.pyplot as plt
import _input_data
from matplotlib import pyplot
from matplotlib.font_manager import FontProperties
def get_one_img(test):#从指定目录中选取一张图片
file = os.listdir(test)#os.listdir()返回指定目录下的所有文件和目录名。
n = len(file)
ind = np.random.randint(0, n)
img_dir = os.path.join(test, file[ind])#判断是否存在文件或目录name
global image1
image1= Image.open(img_dir)
#plt.imshow(image)
#plt.show()
image = image1.resize([350, 350])
image = np.array(image)
return image
def evaluate_one_img():
test = "F:/python练习/test1/Images/"
test_array = get_one_img(test)
with tf.Graph().as_default():#https://www.cnblogs.com/studylyn/p/9105818.html
BATCH_SIZE = 1
N_CLASSES = 2
image = tf.cast(test_array, tf.float32)
image = tf.image.per_image_standardization(image)
image = tf.reshape(image,[1,350,350,3])
logit = model.inference(image, BATCH_SIZE, N_CLASSES)
logit = tf.nn.softmax(logit)
x =tf.placeholder(tf.float32, shape =[350,350,3])
log_test_dir = 'F:/train_savenet/'
saver = tf.train.Saver()
global title
with tf.Session() as sess:
print("从指定路径中加载模型。。。")
#将模型加载到sess中
ckpt = tf.train.get_checkpoint_state(log_test_dir)
if ckpt and ckpt.model_checkpoint_path:#https://blog.csdn.net/u011500062/article/details/51728830/
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 " 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: test_array})
max_index = tf.argmax(prediction) # 将图片输入到模型计算
if float(prediction[:, 0])>0.5:
print('丑的概率 %.6f' %prediction[:, 0])
print("丑")
title=u'丑' str(prediction[:, 0]*100)
else:
print('美的概率 %.6f' %prediction[:, 1])
print("美")
title=u'美' str(prediction[:, 1]*100)
# 测试
evaluate_one_img()
imgplot = plt.imshow(image1)
myfont = FontProperties(fname=r"c:windowsfontssimsun.ttc", size=15)
plt.title(title,fontproperties=myfont)
plt.show()
最终拿一个图片来实验的结果如下: