爬虫技术+卷积神经网络对汽车、飞机、船三分类识别
1.爬取百度片(动态加载),用requests请求库获取URL,re正则里面的compile()方法创建正则表达式对象,findall()方法进行搜索所有图片链接
import re
import sys
import urllib
import requests
def get_onepage_urls(onepageurl):
if not onepageurl:
print('到最后一页, 结束')
return [], ''
try:
html = requests.get(onepageurl)
html.encoding = 'utf-8'
html = html.text
except Exception as e:
print(e)
pic_urls = []
fanye_url = ''
return pic_urls, fanye_url
pic_urls = re.findall('"objURL":"(.*?)",', html, re.S)
fanye_urls = re.findall(re.compile(r'<a href="(.*)" class="n">下一页</a>'), html, flags=0)
fanye_url = 'http://image.baidu.com' + fanye_urls[0] if fanye_urls else ''
return pic_urls, fanye_url
def down_pic(pic_urls):
for i, pic_url in enumerate(pic_urls):
try:
pic = requests.get(pic_url, timeout=15)
string = str(i + 1) + '.jpg'
with open(string, 'wb') as f:
f.write(pic.content)
print('成功下载第%s张图片: %s' % (str(i + 1), str(pic_url)))
except Exception as e:
print('下载第%s张图片时失败: %s' % (str(i + 1), str(pic_url)))
print(e)
continue
if __name__ == '__main__':
keyword = '汽车'
url_init_first = r'http://image.baidu.com/search/flip?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1497491098685_R&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&ctd=1497491098685%5E00_1519X735&word='
url_init = url_init_first + urllib.parse.quote(keyword, safe='/')
all_pic_urls = []
onepage_urls, fanye_url = get_onepage_urls(url_init)
all_pic_urls.extend(onepage_urls)
fanye_count = 0 # 累计翻页数
while 1:
onepage_urls, fanye_url = get_onepage_urls(fanye_url)
fanye_count += 1
if fanye_url == '' and onepage_urls == []:
break
all_pic_urls.extend(onepage_urls)
down_pic(list(set(all_pic_urls)))
2. 更改图片名,便于遍历,用os模块里面的os.path.join()字符串拼接的方式进行命名
import os
path = "D:\\python\\CarsPlanesShips\\training_data\\ships"
filelist = os.listdir(path) #该文件夹下所有的文件(包括文件夹)
count=0
for file in filelist:
print(file)
for file in filelist: #遍历所有文件
Olddir=os.path.join(path,file) #原来的文件路径
if os.path.isdir(Olddir): #如果是文件夹则跳过
continue
filename=os.path.splitext(file)[0] #文件名
filetype=os.path.splitext(file)[1] #文件扩展名
Newdir=os.path.join(path,"ship"+"."+str(count)+filetype) #用字符串函数zfill 以0补全所需位数
os.rename(Olddir,Newdir)#重命名
count+=1
print("ok")
3.验证集和训练集,shuffle()打乱图片,opencv2处理图片,try语句加上去,以防图片格式不对,报错。
dataset.py
import cv2
import os
import glob
from sklearn.utils import shuffle
import numpy as np
def load_train(train_path, image_size, classes):
images = []
labels = []
img_names = []
cls = []
print('Going to read training images')
for fields in classes:
index = classes.index(fields)
print('Now going to read {} files (Index: {})'.format(fields, index))
path = os.path.join(train_path, fields, '*g')
files = glob.glob(path)
for fl in files:
#try:
image = cv2.imread(fl)
print(fl)
image = cv2.resize(image, (image_size, image_size),0,0, cv2.INTER_LINEAR)
image = image.astype(np.float32)
image = np.multiply(image, 1.0 / 255.0)
images.append(image)
label = np.zeros(len(classes))
label[index] = 1.0
labels.append(label)
flbase = os.path.basename(fl)
img_names.append(flbase)
cls.append(fields)
#except:
#pass
images = np.array(images)
labels = np.array(labels)
img_names = np.array(img_names)
cls = np.array(cls)
return images, labels, img_names, cls
class DataSet(object):
def __init__(self, images, labels, img_names, cls):
self._num_examples = images.shape[0]
self._images = images
self._labels = labels
self._img_names = img_names
self._cls = cls
self._epochs_done = 0
self._index_in_epoch = 0
@property
def images(self):
return self._images
@property
def labels(self):
return self._labels
@property
def img_names(self):
return self._img_names
@property
def cls(self):
return self._cls
@property
def num_examples(self):
return self._num_examples
@property
def epochs_done(self):
return self._epochs_done
def next_batch(self, batch_size):
"""Return the next `batch_size` examples from this data set."""
start = self._index_in_epoch
self._index_in_epoch += batch_size
if self._index_in_epoch > self._num_examples:
# After each epoch we update this
self._epochs_done += 1
start = 0
self._index_in_epoch = batch_size
assert batch_size <= self._num_examples
end = self._index_in_epoch
return self._images[start:end], self._labels[start:end], self._img_names[start:end], self._cls[start:end]
def read_train_sets(train_path, image_size, classes, validation_size):
class DataSets(object):
pass
data_sets = DataSets()
images, labels, img_names, cls = load_train(train_path, image_size, classes)
images, labels, img_names, cls = shuffle(images, labels, img_names, cls)
if isinstance(validation_size, float):
validation_size = int(validation_size * images.shape[0])
validation_images = images[:validation_size]
validation_labels = labels[:validation_size]
validation_img_names = img_names[:validation_size]
validation_cls = cls[:validation_size]
train_images = images[validation_size:]
train_labels = labels[validation_size:]
train_img_names = img_names[validation_size:]
train_cls = cls[validation_size:]
data_sets.train = DataSet(train_images, train_labels, train_img_names, train_cls)
data_sets.valid = DataSet(validation_images, validation_labels, validation_img_names, validation_cls)
return data_sets
4.卷积神经网络训练模型 简述:
--数据层:归一化减少图片维度的影响
--卷积计算层:滤波器(filter),根据卷积核设计filter的步长和深度,进行卷积的计算
--激励函数:将卷积层输出结果做非线性映射,它的特点是收敛快,求梯度简单,但较脆弱
--池化层:压缩图片大小,防止过拟合
--全连接层:经过卷积-池化循环得到最终图片影像
train.py
import dataset
import tensorflow as tf
import time
from datetime import timedelta
import math
import random
import numpy as np
# conda install --channel https://conda.anaconda.org/menpo opencv3
#Adding Seed so that random initialization is consistent
from numpy.random import seed
seed(10)
from tensorflow import set_random_seed
set_random_seed(20)
batch_size = 32
#Prepare input data
classes = ['cars','planes','shipes']
num_classes = len(classes)
# 20% of the data will automatically be used for validation
validation_size = 0.2
img_size = 64
num_channels = 3
train_path='training_data'
# We shall load all the training and validation images and labels into memory using openCV and use that during training
data = dataset.read_train_sets(train_path, img_size, classes, validation_size=validation_size)
print("Complete reading input data. Will Now print a snippet of it")
print("Number of files in Training-set:\t\t{}".format(len(data.train.labels)))
print("Number of files in Validation-set:\t{}".format(len(data.valid.labels)))
session = tf.Session()
x = tf.placeholder(tf.float32, shape=[None, img_size,img_size,num_channels], name='x')
## labels
y_true = tf.placeholder(tf.float32, shape=[None, num_classes], name='y_true')
y_true_cls = tf.argmax(y_true, dimension=1)
##Network graph params
filter_size_conv1 = 3
num_filters_conv1 = 32
filter_size_conv2 = 3
num_filters_conv2 = 32
filter_size_conv3 = 3
num_filters_conv3 = 64
fc_layer_size = 1024
def create_weights(shape):
return tf.Variable(tf.truncated_normal(shape, stddev=0.05))
def create_biases(size):
return tf.Variable(tf.constant(0.05, shape=[size]))
def create_convolutional_layer(input,
num_input_channels,
conv_filter_size,
num_filters):
## We shall define the weights that will be trained using create_weights function. 3 3 3 32
weights = create_weights(shape=[conv_filter_size, conv_filter_size, num_input_channels, num_filters])
## We create biases using the create_biases function. These are also trained.
biases = create_biases(num_filters)
## Creating the convolutional layer
layer = tf.nn.conv2d(input=input,
filter=weights,
strides=[1, 1, 1, 1],
padding='SAME')
layer += biases
layer = tf.nn.relu(layer)
## We shall be using max-pooling.
layer = tf.nn.max_pool(value=layer,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME')
## Output of pooling is fed to Relu which is the activation function for us.
#layer = tf.nn.relu(layer)
return layer
def create_flatten_layer(layer):
#We know that the shape of the layer will be [batch_size img_size img_size num_channels]
# But let's get it from the previous layer.
layer_shape = layer.get_shape()
## Number of features will be img_height * img_width* num_channels. But we shall calculate it in place of hard-coding it.
num_features = layer_shape[1:4].num_elements()
## Now, we Flatten the layer so we shall have to reshape to num_features
layer = tf.reshape(layer, [-1, num_features])
return layer
def create_fc_layer(input,
num_inputs,
num_outputs,
use_relu=True):
#Let's define trainable weights and biases.
weights = create_weights(shape=[num_inputs, num_outputs])
biases = create_biases(num_outputs)
# Fully connected layer takes input x and produces wx+b.Since, these are matrices, we use matmul function in Tensorflow
layer = tf.matmul(input, weights) + biases
layer=tf.nn.dropout(layer,keep_prob=0.7)
if use_relu:
layer = tf.nn.relu(layer)
return layer
layer_conv1 = create_convolutional_layer(input=x,
num_input_channels=num_channels,
conv_filter_size=filter_size_conv1,
num_filters=num_filters_conv1)
layer_conv2 = create_convolutional_layer(input=layer_conv1,
num_input_channels=num_filters_conv1,
conv_filter_size=filter_size_conv2,
num_filters=num_filters_conv2)
layer_conv3= create_convolutional_layer(input=layer_conv2,
num_input_channels=num_filters_conv2,
conv_filter_size=filter_size_conv3,
num_filters=num_filters_conv3)
layer_flat = create_flatten_layer(layer_conv3)
layer_fc1 = create_fc_layer(input=layer_flat,
num_inputs=layer_flat.get_shape()[1:4].num_elements(),
num_outputs=fc_layer_size,
use_relu=True)
layer_fc2 = create_fc_layer(input=layer_fc1,
num_inputs=fc_layer_size,
num_outputs=num_classes,
use_relu=False)
y_pred = tf.nn.softmax(layer_fc2,name='y_pred')
y_pred_cls = tf.argmax(y_pred, dimension=1)
session.run(tf.global_variables_initializer())
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=layer_fc2,
labels=y_true)
cost = tf.reduce_mean(cross_entropy)
optimizer = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(cost)
correct_prediction = tf.equal(y_pred_cls, y_true_cls)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
session.run(tf.global_variables_initializer())
def show_progress(epoch, feed_dict_train, feed_dict_validate, val_loss,i):
acc = session.run(accuracy, feed_dict=feed_dict_train)
val_acc = session.run(accuracy, feed_dict=feed_dict_validate)
msg = "Training Epoch {0}--- iterations: {1}--- Training Accuracy: {2:>6.1%}, Validation Accuracy: {3:>6.1%}, Validation Loss: {4:.3f}"
print(msg.format(epoch + 1,i, acc, val_acc, val_loss))
total_iterations = 0
saver = tf.train.Saver()
def train(num_iteration):
global total_iterations
for i in range(total_iterations,
total_iterations + num_iteration):
x_batch, y_true_batch, _, cls_batch = data.train.next_batch(batch_size)
x_valid_batch, y_valid_batch, _, valid_cls_batch = data.valid.next_batch(batch_size)
feed_dict_tr = {x: x_batch,
y_true: y_true_batch}
feed_dict_val = {x: x_valid_batch,
y_true: y_valid_batch}
session.run(optimizer, feed_dict=feed_dict_tr)
if i % int(data.train.num_examples/batch_size) == 0:
val_loss = session.run(cost, feed_dict=feed_dict_val)
epoch = int(i / int(data.train.num_examples/batch_size))
show_progress(epoch, feed_dict_tr, feed_dict_val, val_loss,i)
saver.save(session, './cars-planes-ships-model/car-plane-ship.ckpt',global_step=i)
total_iterations += num_iteration
train(num_iteration=8000)
5.Tensorflow数据流图, 用于模型验证。
计算图(nomograph)用于计算结果,绘画模型(Session)来执行构造好的计算图,同时会话拥有和管理程序运行时的所有资源。当计算完成之后,张量(Tensor)是对运算结果的引用,运算结果多以数组的形式存储,需要通过关闭会 话来帮助系统回收资源,图必须在会话里被启动,会话将图的op分发到诸如 CPU 或 GPU 之类的设备上, 同时提供执行op 的方法。
predict.py
import tensorflow as tf
import numpy as np
import os,glob,cv2
import sys,argparse
image_size=64
num_channels=3
images = []
path = 'test_data\car1.jpg'
image = cv2.imread(path)
# Resizing the image to our desired size and preprocessing wil
#
#
# l be done exactly as done during training
image = cv2.resize(image, (image_size, image_size),0,0, cv2.INTER_LINEAR)
images.append(image)
images = np.array(images, dtype=np.uint8)
images = images.astype('float32')
images = np.multiply(images, 1.0/255.0)
#The input to the network is of shape [None image_size image_size num_channels]. Hence we reshape.
x_batch = images.reshape(1, image_size,image_size,num_channels)
## Let us restore the saved model
sess = tf.Session()
# Step-1: Recreate the network graph. At this step only graph is created.
saver = tf.train.import_meta_graph('./cars-planes-ships-model/car-plane-ship.ckpt-7956.meta')
# Step-2: Now let's load the weights saved using the restore method.
saver.restore(sess, './cars-planes-ships-model/car-plane-ship.ckpt-7956')
# Accessing the default graph which we have restored
graph = tf.get_default_graph()
# Now, let's get hold of the op that we can be processed to get the output.
# In the original network y_pred is the tensor that is the prediction of the network
y_pred = graph.get_tensor_by_name("y_pred:0")
## Let's feed the images to the input placeholders
x= graph.get_tensor_by_name("x:0")
y_true = graph.get_tensor_by_name("y_true:0")
y_test_images = np.zeros((1, 3))
### Creating the feed_dict that is required to be fed to calculate y_pred
feed_dict_testing = {x: x_batch, y_true: y_test_images}
result=sess.run(y_pred, feed_dict=feed_dict_testing)
# result is of this format [probabiliy_of_rose probability_of_sunflower]
# dog [1 0]
res_label = ['car','plane','ship']
print(res_label[result.argmax()])
和猫狗识别相似,不懂得可以找视频理解一下。