(一)数据
负责实现读取数据,生成批次(batch)
import tensorflow as tf
import numpy as np
import os
os模块包含操作系统相关的功能,
可以处理文件和目录这些我们日常手动需要做的操作。因为我们需要获取test目录下的文件,所以要导入os模块。
数据构成,在训练数据中,There are 12500 cat,There are 12500 dogs,共25000张
获取文件路径和标签
def get_files(file_dir):
# file_dir: 文件夹路径 ‘D:/Python/neural network/Cats_vs_Dogs/data/train’
# 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)
#注意需要通视频的代码区别开,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/neural network/Cats_vs_Dogs/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)
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
# 视频方法,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
import matplotlib.pyplot as plt
BATCH_SIZE = 2
CAPACITY = 256
IMG_W = 208
IMG_H = 208
train_dir = ‘D:/Python/neural network/Cats_vs_Dogs/data/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 #测试一部分
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
#这两个函数监控队列的状态
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
#分批次显示
except tf.errors.OutOfRangeError:
print("done!")
finally:
coord.request_stop()
coord.join(threads)
(二)模型
from future import print_function
import tensorflow as tf
模型是仿照TensorFlow的官方例程cifar-10的网络结构来写的。就是两个卷积层(每个卷积层后加一个池化层)
两个全连接层,最后一个softmax输出分类结果。
定义各层的参数
整个卷积过程就是卷积》池化》正则化》卷积》池化》正则化》全连接》全连接》softmax
def inference(images, batch_size, n_classes):
# conv1, shape = [kernel_size, kernel_size, channels, kernel_numbers]
with tf.variable_scope(“conv1”) as scope:
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=”conv1”)
# pool1 && norm1
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')
# conv2
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 && norm2
with tf.variable_scope("pooling2_lrn") as scope:
pool2 = tf.nn.max_pool(conv2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
padding="SAME", name="pooling2")
norm2 = tf.nn.lrn(pool2, depth_radius=4, bias=1.0, alpha=0.001/9.0,
beta=0.75, name='norm2')
整个卷积过程就是卷积》池化》正则化》卷积》池化》正则化》全连接》全连接
# full-connect1
with tf.variable_scope("fc1") as scope:
reshape = tf.reshape(norm2, 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))
fc1 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name="fc1")
# full_connect2
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))
fc2 = tf.nn.relu(tf.matmul(fc1, weights) + biases, name="fc2")
# softmax
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.add(tf.matmul(fc2, weights), biases, name="softmax_linear")
return softmax_linear
#这里没有用激活函数,因为loss调用的时候默认有激活函数
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) #用于显示
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
(三)训练#负责实现模型的训练以及评估
import os
import numpy as np
import tensorflow as tf
import input_data
import model #导入另外两个文件
N_CLASSES = 2 #二分类,cat or dog
IMG_W = 208
IMG_H =208
BATCH_SIZE = 16
CAPACITY = 2000
MAX_STEP = 15000 #with current parameter,it is suggested to use MAX_STEP>10k
learning_rate = 0.0001 #with current parameters,it is suggested to use leaning rate<0.0001
训练过程以及结果的保存
def run_training():
# with tf.Graph().as_default:
train_dir = ‘D:/Python/neural network/Cats_vs_Dogs/data/train’
logs_train_dir = ‘D:/Python/neural network/Cats_vs_Dogs/logs/train/’
#新建一个训练的参数以及模型的结构存放地址
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)
train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES)
train_loss = model.losses(train_logits, train_label_batch)
train_op = model.training(train_loss, learning_rate)
train_acc = model.evaluation(train_logits, train_label_batch)
summary_op = tf.summary.merge_all() # 所有的summary弄到一块
sess = tf.Session()
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)
# 开始训练
try:
for step in np.arange(MAX_STEP): # 定义一个循环,迭代次数
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:
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()
%%Evaluate one image
from PIL import Image
import matplotlib.pyplot as plt
获得一张图片去预测
def get_one_image(train):
n = len(train)
ind = np.random.randint(0, n) #随机获取一张
img_dir = train[ind]
image = Image.open(img_dir)
plt.imshow(image)
image = np.array(image)
return image
def evaluate_one_image():
train_dir = ‘D:/Python/neural network/Cats_vs_Dogs/data/train’
train, train_label = input_data.get_files(train_dir)
image_array = get_one_image(train)
with tf.Graph().as_default():
BATCH_SIZE = 1
N_CLASSES = 2 # 2分类
image = tf.cast(image_array, tf.float32)
image = tf.reshape(image, [1, 208, 208, 3]) # 转化为4D
logit = model.inference(image, BATCH_SIZE, N_CLASSES)
#inferrence没有激活函数,所以后面添加一个
logit = tf.nn.softmax(logit)
x = tf.palceholder(tf.float32, shape=[208, 208, 3])
logs_train_dir = 'D:/Python/neural network/Cats_vs_Dogs/logs/train/'
saver = tf.train.Saver()
with tf.Session() as sess:
print("Reading checkpoints...")
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('Loading success,global_step is %s' % global_step)
else:
print("No checkpoint file found")
prediction = sess.run(logit, feed_dict={X: image_array})
max_index = np.argmax(prediction)
if max_index == 0:
print('This is a cat with possiblity%.6f' % prediction[:, 0])
else:
print('This is a dog with possiblity%.6f' % prediction[:, 1]