数据集
cat图片12500张,dog图片12500张,数据集格式如下:
效果
input_data.py
import os
import tensorflow as tf
from PIL import Image
import matplotlib.pyplot as plt
import numpy as np
import cv2
def get_files(file_dir):
# file_dir: 文件夹路径
# return: 乱序后的图片和标签
cats = []
label_cats = []
dogs = []
label_dogs = []
# 载入数据路径并写入标签值
for file in os.listdir(file_dir):
name = file.split(sep='.')
# name的形式为['dog', '9981', 'jpg']
# os.listdir将名字转换为列表表达
if name[0] == 'cat':
cats.append(file_dir + file)
# 注意文件路径和名字之间要加分隔符,不然后面查找图片会提示找不到图片
# 或者在后面传路径的时候末尾加两// 'D:/Python/… /data/train//'
label_cats.append(0)
else:
dogs.append(file_dir + file)
label_dogs.append(1)
# 猫为0,狗为1
print("There are %d cats\nThere are %d dogs" % (len(cats), len(dogs)))
# 打乱文件顺序
image_list = np.hstack((cats, dogs))
label_list = np.hstack((label_cats, label_dogs))
# np.hstack()方法将猫和狗图片和标签整合到一起,标签也整合到一起
temp = np.array([image_list, label_list])
# 这里的数组出来的是2行10列,第一行是image_list的数据,第二行是label_list的数据
temp = temp.transpose() # 转置
# 将其转换为10行2列,第一列是image_list的数据,第二列是label_list的数据
np.random.shuffle(temp)
# 对应的打乱顺序
image_list = list(temp[:, 0]) # 取所有行的第0列数据
label_list = list(temp[:, 1]) # 取所有行的第1列数据,并转换为int
label_list = [int(i) for i in label_list]
return image_list, label_list
# 生成相同大小的批次
def get_batch(image, label, image_W, image_H, batch_size, capacity):
# image, label: 要生成batch的图像和标签list
# image_W, image_H: 图片的宽高
# batch_size: 每个batch有多少张图片
# capacity: 队列容量
# return: 图像和标签的batch
# 将原来的python.list类型转换成tf能够识别的格式
image = tf.cast(image, tf.string)#强制类型转换
label = tf.cast(label, tf.int32)
# 生成队列。我们使用slice_input_producer()来建立一个队列,将image和label放入一个list中当做参数传给该函数
input_queue = tf.train.slice_input_producer([image, label])
image_contents = tf.read_file(input_queue[0])
# 按队列读数据和标签
label = input_queue[1]
image = tf.image.decode_jpeg(image_contents, channels=3)
# 要按照图片格式进行解码。本例程中训练数据是jpg格式的,所以使用decode_jpeg()解码器,
# 如果是其他格式,就要用其他geshi具体可以从官方API中查询。
# 注意decode出来的数据类型是uint8,之后模型卷积层里面conv2d()要求输入数据为float32类型
# 统一图片大小
# 通过裁剪统一,包括裁剪和扩充
# image = tf.image.resize_image_with_crop_or_pad(image, image_W, image_H)
# 我的方法,通过缩小图片,采用NEAREST_NEIGHBOR插值方法
image = tf.image.resize_images(image, [image_H, image_W], method=tf.image.ResizeMethod.NEAREST_NEIGHBOR,
align_corners=False)
image = tf.cast(image, tf.float32)
# 因为没有标准化,所以需要转换类型
# image = tf.image.per_image_standardization(image) # 标准化数据
image_batch, label_batch = tf.train.batch([image, label],
batch_size=batch_size,
num_threads=64, # 线程
capacity=capacity)
# image_batch是一个4D的tensor,[batch, width, height, channels],
# label_batch是一个1D的tensor,[batch]。
# 这行多余?
label_batch = tf.reshape(label_batch, [batch_size])
return image_batch, label_batch
model.py
#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):
# 一个简单的卷积神经网络,卷积+池化层x2,全连接层x2,最后一个softmax层做分类。
# 卷积层1
# 16个3x3的卷积核(3通道),padding=’SAME’,表示padding后卷积的图与原图尺寸一致,激活函数relu()
with tf.variable_scope('conv1') as scope:
#tf.tuncated_normal从截断的正态分布中输出随机值,
# 生成的值服从具有指定平均值和标准偏差的状态分布,如果生成的值大于平均值两个标准偏差的值,则丢弃
#stddev正太分布的标准差
weights = tf.Variable(tf.truncated_normal(shape=[3, 3, 3, 16], stddev=0.1, dtype=tf.float32),
name='weights', dtype=tf.float32)
#tf.constant初始化常量
biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[16]),
name='biases', dtype=tf.float32)
#nn.conv2d,第一个参数为input,指需要做卷积的输入图像,第二个参数,卷积核,第三个参数步长,
# 第四个设置为SAME表示可以停留在图像边上
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)
# 池化层1
# 3x3最大池化,步长strides为2,池化后执行lrn()操作,局部响应归一化,对训练有利。
with tf.variable_scope('pooling1_lrn') as scope:
#第一个参数,需要池化的输入
#第二个参数池化窗口的大小
#第三个参数步长
#第四个参数同上
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')
# 卷积层2
# 16个3x3的卷积核(16通道),padding=’SAME’,表示padding后卷积的图与原图尺寸一致,激活函数relu()
with tf.variable_scope('conv2') as scope:
weights = tf.Variable(tf.truncated_normal(shape=[3, 3, 16, 16], stddev=0.1, dtype=tf.float32),
name='weights', dtype=tf.float32)
biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[16]),
name='biases', dtype=tf.float32)
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')
# 池化层2
# 3x3最大池化,步长strides为2,池化后执行lrn()操作,
# 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')
# 全连接层3
# 128个神经元,将之前pool层的输出reshape成一行,激活函数relu()
with tf.variable_scope('local3') as scope:
reshape = tf.reshape(pool2, shape=[batch_size, -1])
dim = reshape.get_shape()[1].value
weights = tf.Variable(tf.truncated_normal(shape=[dim, 128], stddev=0.005, dtype=tf.float32),
name='weights', dtype=tf.float32)
biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[128]),
name='biases', dtype=tf.float32)
local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)
# 全连接层4
# 128个神经元,激活函数relu()
with tf.variable_scope('local4') as scope:
weights = tf.Variable(tf.truncated_normal(shape=[128, 128], stddev=0.005, dtype=tf.float32),
name='weights', dtype=tf.float32)
biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[128]),
name='biases', dtype=tf.float32)
local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name='local4')
# dropout层
# with tf.variable_scope('dropout') as scope:
# drop_out = tf.nn.dropout(local4, 0.8)
# Softmax回归层
# 将前面的FC层输出,做一个线性回归,计算出每一类的得分,在这里是2类,所以这个层输出的是两个得分。
with tf.variable_scope('softmax_linear') as scope:
weights = tf.Variable(tf.truncated_normal(shape=[128, n_classes], stddev=0.005, dtype=tf.float32),
name='softmax_linear', dtype=tf.float32)
biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[n_classes]),
name='biases', dtype=tf.float32)
softmax_linear = tf.add(tf.matmul(local4, weights), biases, name='softmax_linear')
return softmax_linear
# -----------------------------------------------------------------------------
# loss计算
# 传入参数:logits,网络计算输出值。labels,真实值,在这里是0或者1
# 返回参数:loss,损失值
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
# --------------------------------------------------------------------------
# loss损失值优化
# 输入参数:loss。learning_rate,学习速率。
# 返回参数:train_op,训练op,这个参数要输入sess.run中让模型去训练。
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
# -----------------------------------------------------------------------
# 评价/准确率计算
# 输入参数:logits,网络计算值。labels,标签,也就是真实值,在这里是0或者1。
# 返回参数:accuracy,当前step的平均准确率,也就是在这些batch中多少张图片被正确分类了。
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
import os
import numpy as np
import tensorflow as tf
import input_data
import model
import time
N_CLASSES = 2
IMG_W = 208
IMG_H = 208
BATCH_SIZE = 16
CAPACITY = 2000 #队列中元素个数
MAX_STEP = 8000
learning_rate = 0.0001 #小于0.001
print("I'm OK")
train_dir = 'D:\\workspace4\\tensorflow\\train\\' # 训练图片文件夹
logs_train_dir = 'D:\\workspace4\\tensorflow\\save1\\' # 保存训练结果文件夹
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(train,
train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
#训练操作定义
sess = tf.Session()
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)
#train_label_batch = tf.one_hot(train_label_batch,2,1,0)
#测试操作定义
summary_op = tf.summary.merge_all()
#产生一个writer来写log文件
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)#加入队列,很重要
tra_loss = .0
tra_acc = .0
# val_loss = .0
# val_acc = .0
try:
start = time.clock()#计算每一个step所花的时间
for step in np.arange(MAX_STEP):
if coord.should_stop():
break
_,tra_loss_,tra_acc_ = sess.run([train_op,train_loss,train_acc])
# val_loss_, val_acc_ = sess.run([test_loss, test_acc])
#下面这一段为我为了打印神经网络最后一层变化写的,可以不要
'''
train,label = sess.run([train_logits,train_label_batch])
#print(train)
L = []
for i in train:
max_ = np.argmax(i)
L.append(max_)
print(L)
print(label)
'''
tra_loss = tra_loss+tra_loss_
tra_acc = tra_acc+tra_acc_
# val_loss = val_loss+val_loss_
# val_acc = val_acc+val_acc_
if (step+1) % 50 == 0 and step!=0:
end = time.clock()
print('Step %d, train loss = %.2f, train accuracy = %.2f%%' % (step+1, tra_loss/50, tra_acc * 100.0/50))
#print('Step %d, val loss = %.2f, val accuracy = %.2f%%' % (step, val_loss/50,val_acc*100.0/50))
print(str(end-start))
tra_loss = .0
tra_acc = .0
summary_str = sess.run(summary_op)
train_writer.add_summary(summary_str, step)
start = time.clock()
# 每隔2000步,保存一次训练好的模型
if step%2000==0 or step == MAX_STEP-1:
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()
evaluateCatOrDog.py
#coding=utf-8
import tensorflow as tf
from PIL import Image
import matplotlib.pyplot as plt
import input_data
import numpy as np
import model
import os
#从训练集中选取一张图片
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():
train = 'D:\\workspace4\\tensorflow\\test1\\'
# 获取图片路径集和标签集
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 = 'D:\\workspace4\\tensorflow\\save1\\'
# 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()