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()