Tensorflow化骨绵掌第5式-LeNet、AlexNet、VGG16、VGG19打造自己的图像识别模型（3）
1、数据制备
本文使用的数据集依然是前两期学习使用的flowers17数据集，所以具体请看前面的数据集介绍。现在我们进行数据集的转换格式成tfrecord格式的数据集。
To_tfrecord.py
#coding=utf-8
import os
import tensorflow as tf
from PIL import Image
import sys
def creat_tf(imgpath):
cwd = os.getcwd()
classes = os.listdir(cwd + imgpath)
writer = tf.python_io.TFRecordWriter("train.tfrecords")
for index, name in enumerate(classes):
class_path = cwd + imgpath + name + "/"
print class_path
if os.path.isdir(class_path):
for img_name in os.listdir(class_path):
img_path = class_path + img_name
img = Image.open(img_path)
img = img.resize((224, 224))
img_raw = img.tobytes() #将图片转化为原生bytes
example = tf.train.Example(features=tf.train.Features(feature={
'label': tf.train.Feature(int64_list=tf.train.Int64List(value=[int(name)])),
'img_raw': tf.train.Feature(bytes_list=tf.train.BytesList(value=[img_raw]))
}))
writer.write(example.SerializeToString()) #序列化为字符串
print(img_name)
writer.close()
def read_example():
#简单的读取例子：
for serialized_example in tf.python_io.tf_record_iterator("train.tfrecords"):
example = tf.train.Example()
example.ParseFromString(serialized_example)
#image = example.features.feature['img_raw'].bytes_list.value
label = example.features.feature['label'].int64_list.value
# 可以做一些预处理之类的
print label
if __name__ == '__main__':
imgpath = './17flowers/'
creat_tf(imgpath)
#read_example()2、VGG16网络简介
VGG 是视觉领域竞赛 ILSVRC 在 2014 年的获胜模型，以 7.3% 的错误率在 ImageNet 数据集上大幅刷新了前一年 11.7% 的世界纪录。VGG16 基本上继承了 AlexNet 深的思想，并且发扬光大，做到了更深。AlexNet 只用到了 8 层网络，而 VGG 的两个版本分别是 16 层网络版和 19 层网络版。在接下来的迁移学习实践中，我们会采用稍微简单的一些的 VGG16，他和 VGG19 有几乎完全一样的准确度，但是运算起来更快一些。
VGG16的网络结构参数如图所示：
VGG-16模型更加复杂一些，一般情况下，其CONV layer和POOL layer设置如下：
CONV = 3x3 filters, s = 1, same
MAX-POOL = 2x2, s = 2VGG-16结构如下所示：
VGG-16的参数多达1亿3千万。
3、VGG16网络的构建
在进行构建网络之前，需要下载vgg16.npy文件。
下载地址：
链接：https://pan.baidu.com/s/1yQAS8CegNf4TcdyTiPdumQ
提取码：7ch5
下面是对VGG16网络进行构建，具体代码如下所示：
vgg16.py
#coding=utf-8
import tensorflow as tf
import numpy as np
data_dict = np.load('./vgg16.npy', encoding='latin1').item()
def print_layer(t):
print(t.op.name, ' ', t.get_shape().as_list(), '\n')
def conv(x, d_out, name, fineturn=False, xavier=False):
d_in = x.get_shape()[-1].value
with tf.name_scope(name) as scope:
# Fine-tuning
if fineturn:
'''
kernel = tf.Variable(tf.constant(data_dict[name][0]), name="weights")
bias = tf.Variable(tf.constant(data_dict[name][1]), name="bias")
'''
kernel = tf.constant(data_dict[name][0], name="weights")
bias = tf.constant(data_dict[name][1], name="bias")
print("fineturn")
elif not xavier:
kernel = tf.Variable(tf.truncated_normal([3, 3, d_in, d_out], stddev=0.1), name='weights')
bias = tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[d_out]),
trainable=True,
name='bias')
print("truncated_normal")
else:
kernel = tf.get_variable(scope+'weights', shape=[3, 3, d_in, d_out],
dtype=tf.float32,
initializer=tf.contrib.layers.xavier_initializer_conv2d())
bias = tf.Variable(tf.constant(0.0, dtype=tf.float32, shape=[d_out]),
trainable=True,
name='bias')
print("xavier")
conv = tf.nn.conv2d(x, kernel,[1, 1, 1, 1], padding='SAME')
activation = tf.nn.relu(conv + bias, name=scope)
print_layer(activation)
return activation
def maxpool(x, name):
activation = tf.nn.max_pool(x, [1, 2, 2, 1], [1, 2, 2, 1], padding='VALID', name=name)
print_layer(activation)
return activation
def fc(x, n_out, name, fineturn=False, xavier=False):
n_in = x.get_shape()[-1].value
with tf.name_scope(name) as scope:
if fineturn:
'''
weight = tf.Variable(tf.constant(data_dict[name][0]), name="weights")
bias = tf.Variable(tf.constant(data_dict[name][1]), name="bias")
'''
weight = tf.constant(data_dict[name][0], name="weights")
bias = tf.constant(data_dict[name][1], name="bias")
print("fineturn")
elif not xavier:
weight = tf.Variable(tf.truncated_normal([n_in, n_out], stddev=0.01), name='weights')
bias = tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[n_out]),
trainable=True,
name='bias')
print("truncated_normal")
else:
weight = tf.get_variable(scope+'weights', shape=[n_in, n_out],
dtype=tf.float32,
initializer=tf.contrib.layers.xavier_initializer_conv2d())
bias = tf.Variable(tf.constant(0.1, dtype=tf.float32, shape=[n_out]),
trainable=True,
name='bias')
print("xavier")
# 全连接层可以使用relu_layer函数比较方便，不用像卷积层使用relu函数
activation = tf.nn.relu_layer(x, weight, bias, name=name)
print_layer(activation)
return activation
def VGG16(images, _dropout, n_cls):
conv1_1 = conv(images, 64, 'conv1_1', fineturn=True)
conv1_2 = conv(conv1_1, 64, 'conv1_2', fineturn=True)
pool1 = maxpool(conv1_2, 'pool1')
conv2_1 = conv(pool1, 128, 'conv2_1', fineturn=True)
conv2_2 = conv(conv2_1, 128, 'conv2_2', fineturn=True)
pool2 = maxpool(conv2_2, 'pool2')
conv3_1 = conv(pool2, 256, 'conv3_1', fineturn=True)
conv3_2 = conv(conv3_1, 256, 'conv3_2', fineturn=True)
conv3_3 = conv(conv3_2, 256, 'conv3_3', fineturn=True)
pool3 = maxpool(conv3_3, 'pool3')
conv4_1 = conv(pool3, 512, 'conv4_1', fineturn=True)
conv4_2 = conv(conv4_1, 512, 'conv4_2', fineturn=True)
conv4_3 = conv(conv4_2, 512, 'conv4_3', fineturn=True)
pool4 = maxpool(conv4_3, 'pool4')
conv5_1 = conv(pool4, 512, 'conv5_1', fineturn=True)
conv5_2 = conv(conv5_1, 512, 'conv5_2', fineturn=True)
conv5_3 = conv(conv5_2, 512, 'conv5_3', fineturn=True)
pool5 = maxpool(conv5_3, 'pool5')
'''
因为训练自己的数据，全连接层最好不要使用预训练参数
'''
flatten = tf.reshape(pool5, [-1, 7*7*512])
fc6 = fc(flatten, 4096, 'fc6', xavier=True)
dropout1 = tf.nn.dropout(fc6, _dropout)
fc7 = fc(dropout1, 4096, 'fc7', xavier=True)
dropout2 = tf.nn.dropout(fc7, _dropout)
fc8 = fc(dropout2, n_cls, 'fc8', xavier=True)
return fc84、开始构建VGG16的训练模型
前面构建的是基础的VGG16网络代码，接下来进行构建训练代码的编写。
当电脑显卡配置不高时只能将batch调低参数。
train.py
#coding=utf-8
import tensorflow as tf
import numpy as np
import pdb
from datetime import datetime
from VGG16 import *
batch_size = 64
lr = 0.0001
n_cls = 17
max_steps = 10000
def read_and_decode(filename):
#根据文件名生成一个队列
filename_queue = tf.train.string_input_producer([filename])
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue) #返回文件名和文件
features = tf.parse_single_example(serialized_example,
features={
'label': tf.FixedLenFeature([], tf.int64),
'img_raw' : tf.FixedLenFeature([], tf.string),
})
img = tf.decode_raw(features['img_raw'], tf.uint8)
img = tf.reshape(img, [224, 224, 3])
# 转换为float32类型，并做归一化处理
img = tf.cast(img, tf.float32)# * (1. / 255)
label = tf.cast(features['label'], tf.int64)
#print 'images的样子是：', img
#print 'label的样子是：', label
#pdb.set_trace()
return img, label
def train():
x = tf.placeholder(dtype=tf.float32, shape=[None, 224, 224, 3], name='input')
y = tf.placeholder(dtype=tf.float32, shape=[None, n_cls], name='label')
keep_prob = tf.placeholder(tf.float32)
output = VGG16(x, keep_prob, n_cls)
#probs = tf.nn.softmax(output)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=output, labels=y))
#train_step = tf.train.AdamOptimizer(learning_rate=0.1).minimize(loss)
train_step = tf.train.GradientDescentOptimizer(learning_rate=lr).minimize(loss)
accuracy = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(output,1), tf.argmax(y, 1)), tf.float32))
images, labels = read_and_decode('./train.tfrecords')
img_batch, label_batch = tf.train.shuffle_batch([images, labels],
batch_size=batch_size,
capacity=392,
min_after_dequeue=200)
label_batch = tf.one_hot(label_batch, n_cls, 1, 0)
init = tf.global_variables_initializer()
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(init)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
for i in range(max_steps):
batch_x, batch_y = sess.run([img_batch, label_batch])
# print batch_x, batch_x.shape
# print batch_y
# pdb.set_trace()
_, loss_val = sess.run([train_step, loss], feed_dict={x:batch_x, y:batch_y, keep_prob:0.8})
if i%10 == 0:
train_arr = accuracy.eval（feed_dict={x:batch_x, y: batch_y, keep_prob: 1.0})
print("%s: Step [%d] Loss : %f, training accuracy : %g" % (datetime.now(), i, loss_val, train_arr))
if (i + 1) == max_steps:
#checkpoint_path = os.path.join(FLAGS.train_dir, './model/model.ckpt')
saver.save(sess, './model/model.ckpt', global_step=i)
coord.request_stop()
coord.join(threads)
#saver.save(sess, 'model/model.ckpt')
if __name__ == '__main__':
train()5、模型进行测试
test.py
#coding=utf-8
import tensorflow as tf
import numpy as np
import pdb
from datetime import datetime
from VGG16 import *
import cv2
import os
def test(path):
x = tf.placeholder(dtype=tf.float32, shape=[None, 224, 224, 3], name='input')
keep_prob = tf.placeholder(tf.float32)
output = VGG16(x, keep_prob, 17)
score = tf.nn.softmax(output)
f_cls = tf.argmax(score, 1)
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess, './model/model.ckpt-9999')
for i in os.listdir(path):
imgpath = os.path.join(path, i)
im = cv2.imread(imgpath)
im = cv2.resize(im, (224 , 224))# * (1. / 255)
im = np.expand_dims(im, axis=0)
#pred = sess.run(f_cls, feed_dict={x:im, keep_prob:1.0})
pred, _score = sess.run([f_cls, score], feed_dict={x:im, keep_prob:1.0})
prob = round(np.max(_score), 4)
#print "{} flowers class is: {}".format(i, pred)
print("{} flowers class is: {}, score: {}".format(i, int(pred), prob))
sess.close()
if __name__ == '__main__':
path = './test'
test(path)测试结果如下所示：（此处只显示前1100次的训练结果）
6、遇到的问题
训练的时候loss有不收敛的情况，可以适当的调整学习率。
kee_prob设置为0.5的时候，虽然loss下降到很低，但是测试的效果很差，因为这个纠结了好久。后来改为0.8感觉还可以，可能是因为数据集太少的原因。
本期学习作业：
（1）了解什么是迁移学习
（2）使用VGG19进行花卉识别
（3）修改参数，继续提升网络分类准确率
本期学习到此结束，欢迎大家进行关注、批评指正。
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
