1.数据
再kaggle里下载猫狗的图片数据,各12500张作为训练集,下载另外12500张作为训练集。这是一个二分类问题,可以让猫的标签为0,狗的标签为1。
2.步骤
(1).生成图片和图片对应标签的lists。
(2).用lists列表生成tensorflow queue队列。
(3).使用一种tensorflow中的读取器读取队列。
(4).使用一种tensorflow中的解码器根据数据不同格式对数据解码。
(5).把数据生成相关的批次。
(6).把这些数据送进计算图中进行计算。
(7).训练
3.Epoch和Batch和Iteration/step
Epoch:一个epoch指把所有数据执行一次。一个Epoch包含n个Iteration/step
Batch:每一个批次里的图片张数
比如有5000张图片,batch_size为10,则需要训练500个step训练完一次,训练完一次就叫一个epoch。
4.input_data.py 用于读取数据,生成批次。
import tensorflow as tf
import numpy as np
import os
img_width=208
img_height=208
train_dir='D:/software/mycodes/python3/524/image/train/train/'
def get_files(file_dir):
cats=[]
label_cats=[]
dogs=[]
label_dogs=[]
for file in os.listdir(file_dir):
name=file.split(sep='.')
if name[0]=='cat':
cats.append(file_dir+file)
label_cats.append(0)
else:
dogs.append(file_dir+file)
label_dogs.append(1)
print('There are %d cats\nThere are %d dogs'%(len(cats),len(dogs)))
image_list=np.hstack((cats,dogs))
label_list=np.hstack((label_cats,label_dogs))
temp=np.array([image_list,label_list])
temp=temp.transpose()
np.random.shuffle(temp)
image_list=list(temp[:,0])
label_list=list(temp[:,1])
label_list=[int(i) for i in label_list]
return image_list,label_list
image_list,label_list=get_files(train_dir)
def get_batch(image,label,image_W,image_H,batch_size,capacity):
image=tf.cast(image,tf.string)
label=tf.cast(label,tf.int32)
input_queue=tf.train.slice_input_producer([image,label])
label=input_queue[1]
image_contents=tf.read_file(input_queue[0])
image=tf.image.decode_jpeg(image_contents,channels=3)
image=tf.image.resize_image_with_crop_or_pad(image, image_W,image_H)
image=tf.image.per_image_standardization(image)
image_batch,label_batch=tf.train.batch([image,label],batch_size=batch_size,num_threads=64,capacity=capacity)
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:/software/mycodes/python3/524/image/train/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
coord=tf.train.Coordinator()
threads=tf.train.start_queue_runners(coord=coord)
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
except tf.errors.OutOfRangeError:
print('done!')
finally:
coord.request_stop()
coord.join(threads)
6.model.py 网络模型文件
import tensorflow as tf
def inference(images,batch_size,n_classes):
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=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')
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)
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')
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 training(loss,learning_rate):
with tf.name_scope('optimizer'):
optimizer=tf.train.AdadeltaOptimizer(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
7.training.py 训练文件
import os
import numpy as np
import tensorflow as tf
import input_data
import model
N_CLASSES=2
IMG_W=208
IMG_H=208
BATCH_SIZE=16
CAPACITY=2000
MAX_STEP=15000
learing_rate=0.0001
def run_training():
train_dir='D:/software/mycodes/python3/524/image/train/train/'
logs_train_dir='D:/software/mycodes/python3/524/logs/train/'
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,learing_rate)
train_acc=model.evaluation(train_logits,train_label_batch)
summary_op=tf.summary.merge_all()
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)
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))
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 traing -- epoch limit reached')
finally:
coord.request_stop()
coord.join(threads)
sess.close()
run_training()
8.测试文件:
from PIL import Image
import matplotlib.pyplot as plt
import numpy as np
import input_data
import tensorflow as tf
import model
def get_one_image(train):
n=len(train)
ind=np.random.randint(0,n)
img_dir=train[ind]
image=Image.open(img_dir)
plt.imshow(image)
image=image.resize([208,208])
image=np.array(image)
return image
def evaluate_one_image():
train_dir='D:/software/mycodes/python3/524/image/train/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
image=tf.cast(image_array,tf.float32)
image=tf.reshape(image,[1,208,208,3])
logit=model.inference(image,BATCH_SIZE,N_CLASSES)
logit=tf.nn.softmax(logit)
x=tf.placeholder(tf.float32,shape=[208,208,3])
logs_train_dir='D:/software/mycodes/python3/524/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 possibility %.6f"%prediction[:,0])
else:
print("this is a dog with posiibility %.6f"%prediction[:,1])
evaluate_one_image()
evaluate_one_image()
evaluate_one_image()