加载vgg16数据,复现神经网络
#!/usr/bin/python
#coding:utf-8
import inspect
import os
import numpy as np
import tensorflow as tf
import time
import matplotlib.pyplot as plt
VGG_MEAN = [103.939, 116.779, 123.68] # 图像的平均像素值
class Vgg16():
def __init__(self, vgg16_path=None):
if vgg16_path is None:
vgg16_path = os.path.join(os.getcwd(), "vgg16.npy") # os函数拼接路径
self.data_dict = np.load(vgg16_path, encoding='latin1').item() # 读取vgg_16数据文件
def forward(self, images):
print("build model started")
start_time = time.time()
rgb_scaled = images * 255.0
# 将r,g,b转换为b,g,r并减去一个平均值
red, green, blue = tf.split(rgb_scaled,3,3)
bgr = tf.concat([
blue - VGG_MEAN[0],
green - VGG_MEAN[1],
red - VGG_MEAN[2]],3)
# 第一层 两层卷积,一层最大池化
self.conv1_1 = self.conv_layer(bgr, "conv1_1")
self.conv1_2 = self.conv_layer(self.conv1_1, "conv1_2")
self.pool1 = self.max_pool_2x2(self.conv1_2, "pool1")
# 第二层 和第一层相同
self.conv2_1 = self.conv_layer(self.pool1, "conv2_1")
self.conv2_2 = self.conv_layer(self.conv2_1, "conv2_2")
self.pool2 = self.max_pool_2x2(self.conv2_2, "pool2")
# 第三层
self.conv3_1 = self.conv_layer(self.pool2, "conv3_1")
self.conv3_2 = self.conv_layer(self.conv3_1, "conv3_2")
self.conv3_3 = self.conv_layer(self.conv3_2, "conv3_3")
self.pool3 = self.max_pool_2x2(self.conv3_3, "pool3")
# 第四层
self.conv4_1 = self.conv_layer(self.pool3, "conv4_1")
self.conv4_2 = self.conv_layer(self.conv4_1, "conv4_2")
self.conv4_3 = self.conv_layer(self.conv4_2, "conv4_3")
self.pool4 = self.max_pool_2x2(self.conv4_3, "pool4")
# 第五层
self.conv5_1 = self.conv_layer(self.pool4, "conv5_1")
self.conv5_2 = self.conv_layer(self.conv5_1, "conv5_2")
self.conv5_3 = self.conv_layer(self.conv5_2, "conv5_3")
self.pool5 = self.max_pool_2x2(self.conv5_3, "pool5")
# 全连接层
self.fc6 = self.fc_layer(self.pool5, "fc6")
self.relu6 = tf.nn.relu(self.fc6)
# 全连接层
self.fc7 = self.fc_layer(self.relu6, "fc7")
self.relu7 = tf.nn.relu(self.fc7)
# 最后经过一个全连接层,输出
self.fc8 = self.fc_layer(self.relu7, "fc8")
self.prob = tf.nn.softmax(self.fc8, name="prob")
end_time = time.time()
# 测一下时间
print(("time consuming: %f" % (end_time-start_time)))
self.data_dict = None
def conv_layer(self, x, name):
with tf.variable_scope(name):
# 获取卷积核
w = self.get_conv_filter(name)
# 进行卷积操作
conv = tf.nn.conv2d(x, w, [1, 1, 1, 1], padding='SAME')
# 获得偏置层
conv_biases = self.get_bias(name)
# 偏置层并加激活函数
result = tf.nn.relu(tf.nn.bias_add(conv, conv_biases))
return result
def get_conv_filter(self, name):
# 根据名字检索到对应的卷积核
return tf.constant(self.data_dict[name][0], name="filter")
def get_bias(self, name):
# 根据名字检索到对应的偏置
return tf.constant(self.data_dict[name][1], name="biases")
def max_pool_2x2(self, x, name):
# 进行2x2最大池化操作
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', name=name)
def fc_layer(self, x, name):
with tf.variable_scope(name):
# 获取张量的形状
shape = x.get_shape().as_list()
dim = 1
for i in shape[1:]:
dim *= i
# 将张量变为一维化
x = tf.reshape(x, [-1, dim])
# 获取全连接w参数
w = self.get_fc_weight(name)
# 获取全连接偏置参数
b = self.get_bias(name)
# 计算全连接
result = tf.nn.bias_add(tf.matmul(x, w), b)
return result
def get_fc_weight(self, name):
# 获取对应全连接层参数
return tf.constant(self.data_dict[name][0], name="weights")
图片裁剪函数,传入输入函数
#!/usr/bin/python
#coding:utf-8
from skimage import io, transform
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
from pylab import mpl
# mpl.rcParams['font.sans-serif']=['SimHei'] # 正常显示中文标签
# mpl.rcParams['axes.unicode_minus']=False # 正常显示正负号
def load_image(path):
fig = plt.figure("Centre and Resize")
# 读取图片
img = io.imread(path)
# 处理图片 归一化
img = img / 255.0
ax0 = fig.add_subplot(131)
ax0.set_xlabel(u'Original Picture')
# 显示图片
ax0.imshow(img)
# 裁剪边缘/边缘处理
short_edge = min(img.shape[:2])
y = (img.shape[0] - short_edge) // 2
x = (img.shape[1] - short_edge) // 2
crop_img = img[y:y+short_edge, x:x+short_edge]
ax1 = fig.add_subplot(132)
ax1.set_xlabel(u"Centre Picture")
ax1.imshow(crop_img)
# 重新修改图片尺寸
re_img = transform.resize(crop_img, (224, 224))
ax2 = fig.add_subplot(133)
ax2.set_xlabel(u"Resize Picture")
ax2.imshow(re_img)
img_ready = re_img.reshape((1, 224, 224, 3))
return img_ready
def percent(value):
return '%.2f%%' % (value * 100)
应用函数(主函数),输入图片,并做预测
#coding:utf-8
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
import vgg16
import utils
from Nclasses import labels
# img_path = input('Input the path and image name:')
img_path = "D:\\python学习\\复现神经网络\\pic\\c.jpg"
img_ready = utils.load_image(img_path)
fig=plt.figure(u"Top-5 预测结果")
with tf.Session() as sess:
images = tf.placeholder(tf.float32, [1, 224, 224, 3]) # 输入占位
vgg = vgg16.Vgg16() # 加载vgg16网络对象c
vgg.forward(images) # 传入vgg网络参数
probability = sess.run(vgg.prob, feed_dict={images:img_ready}) # 用sess运行
top5 = np.argsort(probability[0])[-1:-6:-1] # 读取概率值最大前五个数
print("top5:",top5)
values = []
bar_label = []
# 分别输出5个预测的概率的直方图
for n, i in enumerate(top5):
print("n:",n)
print("i:",i)
values.append(probability[0][i])
bar_label.append(labels[i])
print(i, ":", labels[i], "----", utils.percent(probability[0][i]) )
ax = fig.add_subplot(111)
ax.bar(range(len(values)), values, tick_label=bar_label, width=0.5, fc='g')
ax.set_ylabel(u'probabilityit')
ax.set_title(u'Top-5')
for a,b in zip(range(len(values)), values):
ax.text(a, b+0.0005, utils.percent(b), ha='center', va = 'bottom', fontsize=7)
plt.show()