刚刚开始接触TensorFlow,在网上找到一个老师的视频教学,关于利用简单的网络结构实现二分类,也就是猫狗大战的例子。于是对着视屏,自己做了如下的记录。如果有什么地方错误,欢迎大神指点!!!
1.准备数据集。https://www.kaggle.com/c/dogs-vs-cats 在Kaggle的官网上可以下载,如果想直接要数据的童鞋,可以私信我,我发给你,也是可以的。
2.程序结构如图:
3.下面就是关键代码:
input_data.py:
import tensorflow as tf
import numpy as np
import os
img_width=208
img_height=208
#train_dir='G:/PycharmProjects/untitled2/data/train/'
def get_files(file_dir):
cats=[]
label_cats=[]
dogs=[]
label_dogs=[]
for file in os.listdir(file_dir):
name=file.split(sep='.')#文件是cat.1.jpg形式
if name[0]=='cat':
cats.append(file_dir+file)
label_cats.append(0)
else:
dogs.append(file_dir+file)
label_dogs.append(1)
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)#打乱顺序
image_list=list(temp[:,0])
label_list=list(temp[:,1])
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=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) #解码jpg图片
image=tf.image.resize_image_with_crop_or_pad(image,image_w,image_h) #图片过大 从中间裁剪
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)
# image_batch,label_batch=tf.train.shuffle_batch([image,label],batch_size=batch_size,num_threads=64,capacity=capacity,min_after_dequeue=capacity-1)#由于前面打乱顺序,这个地方不需要打乱顺序
label_batch=tf.reshape(label_batch,[batch_size])
return image_batch,label_batch
#test
import matplotlib.pyplot as plt
BATCH_SIZE=2
CAPACITY=256
IMG_W=208
IMG_H=208
train_dir='G:/PycharmProjects/untitled2/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
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)
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, [1, 1, 1, 1], padding='SAME')
pre_activation = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(pre_activation, name=scope.name)
# pool1 and 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(pool1,4,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, [1, 1, 1, 1], padding='SAME')
pre_activation = tf.nn.bias_add(conv, biases)
conv2 = tf.nn.relu(pre_activation, name='conv2')
# norm2
with tf.variable_scope('pooling2_lrn') as scope:
norm2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,name='norm2')
# pool2
pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1],strides=[1, 1, 1, 1], padding='SAME', name='pooling2')
# local3
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)
# local4
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, i.e. softmax(WX + b)
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 loss(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_reate):
with tf.variable_scope('optimizer') as scope:
optimizer=tf.train.AdamOptimizer(learning_rate=learning_reate)#优化算法
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
import os
import numpy as np
import tensorflow as tf
import module
import input_data
N_CLASSES=2
IMG_W=150
IMG_H=150
BATCH_SIZE=16
CAPACITY=2000
MAX_STEP=15000
learning_rate=0.0001
def run_training():
train_dir='G:/PycharmProjects/untitled2/data/train/'
logs_train_dir='G:/PycharmProjects/untitled2/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=module.inference(train_batch,BATCH_SIZE,N_CLASSES)
train_loss=module.loss(train_logits,train_label_batch)
train_op=module.trainning(train_loss,learning_rate)
train_acc=module.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()
# with tf.Session() as sess:
# sess.run(tf.initialize_all_variables())
# 定义保存路径
# save_path = saver.save(sess, "G:/PycharmProjects/untitled2/savemodel/save_test.ckpt")
# print("Save to path: ", save_path)
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:#每50显示
#tra_loss=float(tra_loss)
#tra_acc=float(tra_acc)
print ('step %d,train loss=%.2f,train accuracy =%.2f%%'% (step,tra_loss,train_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('epoch limit reached')
finally:
coord.request_stop()
coord.join(threads)
sess.close()
#test
#run_training()