本文介绍了一个使用卷积神经网络(CNN)进行猫狗图像分类的项目，详细展示了从数据预处理、模型构建到训练和测试的全过程。采用TensorFlow框架，在Linux环境下实现了模型训练，并通过测试验证了模型的有效性。
数据集链接：http://pan.baidu.com/s/1dFd8kmt 密码：psor
运行环境：linux16.04，TensorFlow -GPU版本，GTX960显卡
主要用到四个python文件：
-
input_data.py
input_data.py
import tensorflow as tf
import numpy as np
import os
# you need to change this to your data directory
train_dir = '/home/lei/PycharmProjects/Cats_vs_Dogs/data/train/'
def get_files(file_dir):
'''
Args:
file_dir: file directory
Returns:
list of images and labels
'''
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(float(i)) for i in label_list]
return image_list, label_list
def get_batch(image, label, image_W, image_H, batch_size, capacity):
'''
Args:
image: list type
label: list type
image_W: image width
image_H: image height
batch_size: batch size
capacity: the maximum elements in queue
Returns:
image_batch: 4D tensor [batch_size, width, height, 3], dtype=tf.float32
label_batch: 1D tensor [batch_size], dtype=tf.int32
'''
image = tf.cast(image, tf.string)
label = tf.cast(label, tf.int32)
# make an input queue
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)
######################################
# data argumentation should go to here
######################################
image = tf.image.resize_image_with_crop_or_pad(image, image_W, image_H)
# if you want to test the generated batches of images, you might want to comment the following line.
# 如果想看到正常的图片，请注释掉111行（标准化）和 126行（image_batch = tf.cast(image_batch, tf.float32)）
# 训练时不要注释掉！
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)
# you can also use shuffle_batch
# image_batch, label_batch = tf.train.shuffle_batch([image,label],
# batch_size=BATCH_SIZE,
# num_threads=64,
# capacity=CAPACITY,
# min_after_dequeue=CAPACITY-1)
label_batch = tf.reshape(label_batch, [batch_size])
image_batch = tf.cast(image_batch, tf.float32)
return image_batch, label_batch
如果想要测试一下效果：
To test the generated batches of images
When training the model, DO comment the following codes
import matplotlib.pyplot as plt
BATCH_SIZE = 2
CAPACITY = 256
IMG_W = 208
IMG_H = 208
train_dir = '/home/lei/PycharmProjects/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
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])
# just test one 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)
这部分主要是做图像的预处理，读取，裁剪等。
import tensorflow as tf
def inference(images, batch_size, n_classes):
'''Build the model
Args:
images: image batch, 4D tensor, tf.float32, [batch_size, width, height, channels]
Returns:
output tensor with the computed logits, float, [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= 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, 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 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')
#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
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):
'''Compute loss from logits and labels
Args:
logits: logits tensor, float, [batch_size, n_classes]
labels: label tensor, tf.int32, [batch_size]
Returns:
loss tensor of float type
'''
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_rate):
'''Training ops, the Op returned by this function is what must be passed to
'sess.run()' call to cause the model to train.
Args:
loss: loss tensor, from losses()
Returns:
train_op: The op for trainning
'''
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):
"""Evaluate the quality of the logits at predicting the label.
Args:
logits: Logits tensor, float - [batch_size, NUM_CLASSES].
labels: Labels tensor, int32 - [batch_size], with values in the
range [0, NUM_CLASSES).
Returns:
A scalar int32 tensor with the number of examples (out of batch_size)
that were predicted correctly.
"""
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
model部分，两层卷积，两层全连接。
import os
import numpy as np
import tensorflow as tf
import input_data
import model
N_CLASSES = 2 # 猫和狗
IMG_W = 208 # resize图像，太大的话训练时间久
IMG_H = 208
BATCH_SIZE = 16
CAPACITY = 2000
MAX_STEP = 15000 # 一般大于10K
learning_rate = 0.0001 # 一般小于0.0001
train_dir = '/home/lei/PycharmProjects/Cats_vs_Dogs/data/train/'
logs_train_dir = '/home/lei/PycharmProjects/Cats_vs_Dogs/log/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.trainning(train_loss, learning_rate)
train__acc = model.evaluation(train_logits, train_label_batch)
summary_op = tf.summary.merge_all() # 这个是log汇总记录
# 产生一个会话
sess = tf.Session()
# 产生一个writer来写log文件
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
# 产生一个saver来存储训练好的模型
saver = tf.train.Saver()
# 所有节点初始化
sess.run(tf.global_variables_initializer())
# 队列监控
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
# 执行MAX_STEP步的训练，一步一个batch
for step in np.arange(MAX_STEP):
if coord.should_stop():
break
# 启动以下操作节点，有个疑问，为什么train_logits在这里没有开启？
_, tra_loss, tra_acc = sess.run([train_op, train_loss, train__acc])
# 每隔50步打印一次当前的loss以及acc，同时记录log，写入writer
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)
# 每隔2000步，保存一次训练好的模型
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()
如果想要测试其中单独的一副图片：
test.py
from PIL import Image
import matplotlib.pyplot as plt
import input_data
import model
import os
import numpy as np
import tensorflow as tf
def get_one_image(train):
'''Randomly pick one image from training data
Return: ndarray
'''
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():
'''Test one image against the saved models and parameters
'''
# you need to change the directories to yours.
# train_dir = '/home/kevin/tensorflow/cats_vs_dogs/data/train/'
train_dir = '/home/lei/PycharmProjects/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
image = tf.cast(image_array, tf.float32)
image = tf.image.per_image_standardization(image)
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])
# you need to change the directories to yours.
# logs_train_dir = '/home/kevin/tensorflow/cats_vs_dogs/logs/train/'
logs_train_dir = '/home/lei/PycharmProjects/Cats_vs_Dogs/log/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 possibility %.6f' % prediction[:, 1])
plt.imshow(image_array)
plt.show()
evaluate_one_image()
跑出来效果还不错，测试了几张，准确率还行。
主要参考了：
https://blog.youkuaiyun.com/xingwei_09/article/details/79159591
https://blog.youkuaiyun.com/hjxu2016/article/details/75305123
扫一扫
2728
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
