tensorflow-keras框架搭建GoogLeNet分类网络(附带注释)

模块1：resize数据集

import os
import cv2def resize_img(DATADIR, data_k, img_size):w = img_size[0]h = img_size[1]'''设置目标像素大小，此处设为300'''path = os.path.join(DATADIR, data_k)#按顺序拼接多个路径# 返回path路径下所有文件的名字img_list = os.listdir(path)for i in img_list:if i.endswith('.jpg'):# 调用cv2.imread读入图片，读入格式为IMREAD_COLORimg_array = cv2.imread((path + '/' + i), cv2.IMREAD_COLOR)# 调用cv2.resize函数resize图片new_array = cv2.resize(img_array, (w, h), interpolation=cv2.INTER_CUBIC)img_name = str(i)'''生成图片存储的目标文件夹'''save_path = path + '_new/'if os.path.exists(save_path):print(i)'''调用cv.2的imwrite函数保存图片'''save_img = save_path + img_namecv2.imwrite(save_img, new_array)else:os.mkdir(save_path)save_img = save_path + img_namecv2.imwrite(save_img, new_array)if __name__ == '__main__':# 设置图片路径DATADIR = "F:/Github/cat_dataset/cat_12_test"data_k = '  '# 需要修改的新的尺寸img_size = [224, 224]resize_img(DATADIR, data_k, img_size)

模块2：利用.txt文件分类整体数据集

import numpy as np
import os
import shutil
filename = 'train_list.txt' # txt文件和当前脚本在同一目录下，所以不用写具体路径
pos = []
Efield = []
with open(filename, 'r') as file_to_read:while True:lines = file_to_read.readline() # 整行读取数据if not lines:breakp_tmp, E_tmp = [i for i in lines.split()] # 将整行数据分割处理，如果分割符是空格，括号里就不用传入参数，如果是逗号， 则传入‘，'字符。if not os.path.exists(E_tmp):#判断指定文件是否存在，结果是bool值os.makedirs(E_tmp)#创建文件夹shutil.move(p_tmp,E_tmp)

模块3：模型

from tensorflow.keras import layers, models, Model, Sequentialdef GoogLeNet(im_height=224, im_width=224, class_num=12, aux_logits=False):# tensorflow中的tensor通道排序是NHWCinput_image = layers.Input(shape=(im_height, im_width, 3), dtype="float32")# (None, 224, 224, 3)x = layers.Conv2D(64, kernel_size=7, strides=2, padding="SAME", activation="relu", name="conv2d_1")(input_image)# (None, 112, 112, 64)x = layers.MaxPool2D(pool_size=3, strides=2, padding="SAME", name="maxpool_1")(x)# (None, 56, 56, 64)x = layers.Conv2D(64, kernel_size=1, activation="relu", name="conv2d_2")(x)# (None, 56, 56, 64)x = layers.Conv2D(192, kernel_size=3, padding="SAME", activation="relu", name="conv2d_3")(x)# (None, 56, 56, 192)x = layers.MaxPool2D(pool_size=3, strides=2, padding="SAME", name="maxpool_2")(x)# (None, 28, 28, 192)x = Inception(64, 96, 128, 16, 32, 32, name="inception_3a")(x)# (None, 28, 28, 256)x = Inception(128, 128, 192, 32, 96, 64, name="inception_3b")(x)# (None, 28, 28, 480)x = layers.MaxPool2D(pool_size=3, strides=2, padding="SAME", name="maxpool_3")(x)# (None, 14, 14, 480)x = Inception(192, 96, 208, 16, 48, 64, name="inception_4a")(x)if aux_logits:#如果为true就创建辅助分类器aux1 = InceptionAux(class_num, name="aux_1")(x)# (None, 14, 14, 512)x = Inception(160, 112, 224, 24, 64, 64, name="inception_4b")(x)# (None, 14, 14, 512)x = Inception(128, 128, 256, 24, 64, 64, name="inception_4c")(x)# (None, 14, 14, 512)x = Inception(112, 144, 288, 32, 64, 64, name="inception_4d")(x)if aux_logits:aux2 = InceptionAux(class_num, name="aux_2")(x)# (None, 14, 14, 528)x = Inception(256, 160, 320, 32, 128, 128, name="inception_4e")(x)# (None, 14, 14, 532)x = layers.MaxPool2D(pool_size=3, strides=2, padding="SAME", name="maxpool_4")(x)# (None, 7, 7, 832)x = Inception(256, 160, 320, 32, 128, 128, name="inception_5a")(x)# (None, 7, 7, 832)x = Inception(384, 192, 384, 48, 128, 128, name="inception_5b")(x)# (None, 7, 7, 1024)x = layers.AvgPool2D(pool_size=7, strides=1, name="avgpool_1")(x)# (None, 1, 1, 1024)x = layers.Flatten(name="output_flatten")(x)# (None, 1024)x = layers.Dropout(rate=0.4, name="output_dropout")(x)x = layers.Dense(class_num, name="output_dense")(x)# (None, class_num)aux3 = layers.Softmax(name="aux_3")(x)if aux_logits:model = models.Model(inputs=input_image, outputs=[aux1, aux2, aux3])#第一个和第二个是辅助分类器 第三个是主输出else:model = models.Model(inputs=input_image, outputs=aux3)return modelclass Inception(layers.Layer):def __init__(self, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj, **kwargs):#**kwargs传入我们的层名称super(Inception, self).__init__(**kwargs)self.branch1 = layers.Conv2D(ch1x1, kernel_size=1, activation="relu")#有两个卷积层 用sequential类讲二者合并   步距是=1 就没有写 保证可以在深度上进行拼接self.branch2 = Sequential([layers.Conv2D(ch3x3red, kernel_size=1, activation="relu"),layers.Conv2D(ch3x3, kernel_size=3, padding="SAME", activation="relu")])      # output_size= input_sizeself.branch3 = Sequential([layers.Conv2D(ch5x5red, kernel_size=1, activation="relu"),layers.Conv2D(ch5x5, kernel_size=5, padding="SAME", activation="relu")])      # output_size= input_sizeself.branch4 = Sequential([layers.MaxPool2D(pool_size=3, strides=1, padding="SAME"),  # caution: default strides==pool_sizelayers.Conv2D(pool_proj, kernel_size=1, activation="relu")])                  # output_size= input_sizedef call(self, inputs, **kwargs):branch1 = self.branch1(inputs)branch2 = self.branch2(inputs)branch3 = self.branch3(inputs)branch4 = self.branch4(inputs)outputs = layers.concatenate([branch1, branch2, branch3, branch4])#将四个分支的输出在深度上进行拼接return outputs#定义辅助分类器结构
class InceptionAux(layers.Layer):def __init__(self, num_classes, **kwargs):#方便定义层名称super(InceptionAux, self).__init__(**kwargs)self.averagePool = layers.AvgPool2D(pool_size=5, strides=3)self.conv = layers.Conv2D(128, kernel_size=1, activation="relu")self.fc1 = layers.Dense(1024, activation="relu")self.fc2 = layers.Dense(num_classes)self.softmax = layers.Softmax()#将输出值转化为概率分布def call(self, inputs, **kwargs):# aux1: N x 512 x 14 x 14, aux2: N x 528 x 14 x 14  N是batchx = self.averagePool(inputs)# aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4x = self.conv(x)# N x 128 x 4 x 4x = layers.Flatten()(x)x = layers.Dropout(rate=0.5)(x)# N x 2048x = self.fc1(x)x = layers.Dropout(rate=0.5)(x)# N x 1024x = self.fc2(x)# N x num_classesx = self.softmax(x)return x

模块4：训练

from tensorflow.keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
from model import GoogLeNet
import tensorflow as tf
import json
import osdata_root = os.path.abspath(os.path.join(os.getcwd(), "../.."))  # get data root path
image_path = data_root + "/cat_dataset/"  # flower data set path
train_dir = image_path + "train"
validation_dir = image_path + "val"# create direction for saving weights
if not os.path.exists("save_weights"):os.makedirs("save_weights")im_height = 224
im_width = 224
batch_size = 20
epochs = 50def pre_function(img):# img = im.open('test.jpg')# img = np.array(img).astype(np.float32)img = img / 255.img = (img - 0.5) * 2.0#标准化处理return img# data generator with data augmentation
#ImageDataGenerator会自动生成一个标签 与所需的三个标签是不匹配的 因此不能用fit方法 使用底层api
train_image_generator = ImageDataGenerator(preprocessing_function=pre_function,horizontal_flip=True)
validation_image_generator = ImageDataGenerator(preprocessing_function=pre_function)train_data_gen = train_image_generator.flow_from_directory(directory=train_dir,batch_size=batch_size,shuffle=True,target_size=(im_height, im_width),class_mode='categorical')
total_train = train_data_gen.n# get class dict
class_indices = train_data_gen.class_indices# transform value and key of dict
inverse_dict = dict((val, key) for key, val in class_indices.items())
# write dict into json file
json_str = json.dumps(inverse_dict, indent=4)
with open('class_indices.json', 'w') as json_file:json_file.write(json_str)val_data_gen = train_image_generator.flow_from_directory(directory=validation_dir,batch_size=batch_size,shuffle=True,target_size=(im_height, im_width),class_mode='categorical')
total_val = val_data_gen.nmodel = GoogLeNet(im_height=im_height, im_width=im_width, class_num=12, aux_logits=True)
# model.build((batch_size, 224, 224, 3))  # when using subclass model
model.summary()# using keras low level api for training
loss_object = tf.keras.losses.CategoricalCrossentropy(from_logits=False)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.0003)train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.CategoricalAccuracy(name='train_accuracy')test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.CategoricalAccuracy(name='test_accuracy')@tf.function
def train_step(images, labels):with tf.GradientTape() as tape:aux1, aux2, output = model(images, training=True)#将一批图像数据输入到模型中 得到三个输出loss1 = loss_object(labels, aux1)#计算损失loss2 = loss_object(labels, aux2)loss3 = loss_object(labels, output)loss = loss1*0.3 + loss2*0.3 + loss3#根据googlenet原论文 将分损失加到总损失中gradients = tape.gradient(loss, model.trainable_variables)#反向传播optimizer.apply_gradients(zip(gradients, model.trainable_variables))#更新每个节点的参数train_loss(loss)train_accuracy(labels, output)@tf.function
def test_step(images, labels):_, _, output = model(images, training=False)#验证的时候就不需要辅助分类器1和2t_loss = loss_object(labels, output)test_loss(t_loss)test_accuracy(labels, output)best_test_loss = float('inf')
for epoch in range(1, epochs+1):train_loss.reset_states()        # clear history infotrain_accuracy.reset_states()    # clear history infotest_loss.reset_states()         # clear history infotest_accuracy.reset_states()     # clear history infofor step in range(total_train // batch_size):images, labels = next(train_data_gen)train_step(images, labels)for step in range(total_val // batch_size):test_images, test_labels = next(val_data_gen)test_step(test_images, test_labels)template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'print(template.format(epoch,train_loss.result(),train_accuracy.result() * 100,test_loss.result(),test_accuracy.result() * 100))if test_loss.result() < best_test_loss:best_test_loss = test_loss.result()model.save_weights("./save_weights/myGoogLeNet.h5")

模块5：预测

from model import GoogLeNet
from PIL import Image, ImageFont, ImageDraw
import numpy as np
import json
import matplotlib.pyplot as pltim_height = 224
im_width = 224# load image
img = Image.open("../1.jpg")
# resize image to 224x224
img = img.resize((im_width, im_height))# scaling pixel value and normalize
img = ((np.array(img) / 255.) - 0.5) / 0.5# Add the image to a batch where it's the only member.
img = (np.expand_dims(img, 0))# read class_indict
try:json_file = open('./class_indices.json', 'r')class_indict = json.load(json_file)
except Exception as e:print(e)exit(-1)model = GoogLeNet(class_num=12, aux_logits=False)
model.summary()
model.load_weights("./save_weights/myGoogLenet.h5", by_name=True)  # h5 format
#model.load_weights("./save_weights/myGoogLeNet.ckpt")  # ckpt format
result = model.predict(img)
predict_class = np.argmax(result)img0 = Image.open("../1.jpg")
ttf = ImageFont.load_default()
draw = ImageDraw.Draw(img0) #新建画布绘画对象
draw.text((10,10),str(class_indict[str(predict_class)]),font=ttf, fill=(155,215,155))
img0.show()

tensorflow-keras框架搭建GoogLeNet分类网络(附带注释)相关推荐

Keras之TCN：基于keras框架利用时间卷积网络TCN算法对上海最高气温实现回归预测(把时间序列数据集转化为有监督学习数据集)案例
Keras之TCN:基于keras框架利用时间卷积网络TCN算法对上海最高气温实现回归预测(把时间序列数据集转化为有监督学习数据集)案例目录利用时间卷积网络TCN算法对上海最高气温实现回归预测(把 ...
Win10系统Anaconda+TensorFlow+Keras 环境搭建教程
红色石头的个人网站:redstonewill.com 前天我在公众号推荐了<Python Deep Learning>这本书.该书是由 Keras 作者写的,所以全书基本围绕着 Keras ...
【Keras】Win10系统 + Anaconda+TensorFlow+Keras 环境搭建教程
1. 安装 Anaconda 打开 Anaconda 的官方下载地址:https://www.anaconda.com/download/ 选择 Python 对应的version 下载.下载完成后直 ...
基于Docker的TensorFlow机器学习框架搭建和实例源码解读
http://blog.csdn.net/dream_an/article/details/55520205
keras 多输入多输出网络
keras中的多输入多输出网络多输入多输出网络搭建的官网介绍: http://keras-cn.readthedocs.io/en/latest/getting_started/functional ...
(TF)Anaconda安装Tensorflow+Keras+Jupyter Notebook 老电脑（CPU不支持AVX指令集）
(TF)Anaconda安装Tensorflow+Keras+Jupyter Notebook 老电脑(CPU不支持AVX指令集) 目录     - 1.安装anaconda最新版本     - 2. ...
华硕飞行堡垒 linux安装cuda8+cuDnn6+tensorflow+keras 教程
得不说坑好多-- 在这里先说在前面最好的组合是cuda8 cudnn6 不要问我为什么--都是泪!!! cuda9 tensorflow前段时间说是兼容了,但是不好按,会报错 cudnn我按官网上面 ...
android开发ssh框架搭建,基于SSH框架的Android系统的研究
摘要: 本文设计开发了一个基于SSH框架的酒店Android手机查询系统.该系统采用面向对象的设计思想进行分析与设计,利用Eclipse,MyEclipse,Android SDK,Tomcat和My ...
Keras封装实现经典深度网络框架 VGG-16, ZF-Net,Alex-Net,LeNet,Google-Net,ResNet, DenseNet-50
文章目录 1.Keras封装实现 LeNet网络-5(1998) 2.Keras封装实现 Alex-Net网络-8(2012) 3.Keras封装实现 ZF-Net网络-8(2013) 4.Keras ...

tensorflow-keras框架搭建GoogLeNet分类网络(附带注释)

模块1：resize数据集

模块2：利用.txt文件分类整体数据集

模块3：模型

模块4：训练

模块5：预测

tensorflow-keras框架搭建GoogLeNet分类网络(附带注释)相关推荐

最新文章

热门文章