基于Tensorflow2.x的ResNet-50的病虫害分类（有界面）

import osclass BatchRename():def __init__(self):self.path = "B:/BaiduNetdiskDownload/class/testing_data/Leaf-ulcer" #图片的路径def rename(self):filelist = os.listdir(self.path) filelist.sort()total_num = len(filelist)i = 0for item in filelist:item = item.lower() if item.endswith('.png'):src = os.path.join(self.path, item)s = str(i)s = s.zfill(2)  #Python zfill() 方法返回指定长度的字符串，原字符串右对齐，前面填充0dst = os.path.join(os.path.abspath(self.path), s + '.png')'''概述：os.rename() 方法用于重命名文件或目录，从 src 到 dst,如果dst是一个存在的目录, 将抛出OSError语法：rename()方法语法格式如下：os.rename(src, dst)参数：src  要修改的目录名dst  修改后的目录名返回值：该方法没有返回值'''try:os.rename(src, dst)print ('converting %s to %s ...' % (src, dst))i = i + 1except Exception as e:print(e)print('rename dir fail\r\n')print ('total %d to rename & converted %d jpgs' % (total_num, i))if __name__ == '__main__':demo = BatchRename()demo.rename()

import os
import random
from shutil import copy2def data_set_split(initial_data_folder, target_data_folder, train_scale=0.8, val_scale=0.2, test_scale=0.0):'''读取源数据文件夹，生成划分好的文件夹，分为trian、val、test三个文件夹进行:param initial_data_folder: 源文件夹 E:/biye/gogogo/note_book/torch_note/data/utils_test/data_split/initial_data:param target_data_folder: 目标文件夹 E:/biye/gogogo/note_book/torch_note/data/utils_test/data_split/target_data:param train_scale: 训练集比例:param val_scale: 验证集比例:param test_scale: 测试集比例:return:'''print("开始数据集划分")class_names = os.listdir(initial_data_folder)#用于返回initial_data_folder文件夹包含的图片文件的名字的列表# 在目标目录下创建文件夹split_names = ['train', 'val', 'test']for split_name in split_names:split_path = os.path.join(target_data_folder, split_name)if os.path.isdir(split_path):  #os.path.isdir()函数判断某一路径是否为目录  passelse:os.mkdir(split_path)   #os.mkdir()函数创建目录（创建一级目录）,其参数path 为要创建目录的路径    拓展：使用os.rmdir()函数删除目录。# 然后在split_path的目录下创建类别文件夹，生成Fruit-anthrax等五个文件夹for class_name in class_names:class_split_path = os.path.join(split_path, class_name)if os.path.isdir(class_split_path):passelse:os.mkdir(class_split_path)# 按照比例划分数据集，并进行数据图片的复制# 首先进行分类遍历for class_name in class_names:current_class_data_path = os.path.join(initial_data_folder, class_name)current_all_data = os.listdir(current_class_data_path)#用于返回current_class_data_path文件夹包含的图片文件的名字的列表current_data_length = len(current_all_data)current_data_index_list = list(range(current_data_length))random.shuffle(current_data_index_list)train_folder = os.path.join(os.path.join(target_data_folder, 'train'), class_name)val_folder = os.path.join(os.path.join(target_data_folder, 'val'), class_name)test_folder = os.path.join(os.path.join(target_data_folder, 'test'), class_name)train_stop_flag = current_data_length * train_scaleval_stop_flag = current_data_length * (train_scale + val_scale)current_idx = 0train_num = 0val_num = 0test_num = 0for i in current_data_index_list:initial_img_path = os.path.join(current_class_data_path, current_all_data[i])if current_idx <= train_stop_flag:copy2(initial_img_path, train_folder)train_num = train_num + 1elif (current_idx > train_stop_flag) and (current_idx <= val_stop_flag):copy2(initial_img_path, val_folder)val_num = val_num + 1else:copy2(initial_img_path, test_folder)test_num = test_num + 1current_idx = current_idx + 1print("*********************************{}*************************************".format(class_name))print("{}类按照{}：{}：{}的比例划分完成，一共{}张图片".format(class_name, train_scale, val_scale, test_scale, current_data_length))print("训练集{}：{}张".format(train_folder, train_num))print("验证集{}：{}张".format(val_folder, val_num))print("测试集{}：{}张".format(test_folder, test_num))if __name__ == '__main__':initial_data_folder = "training_data"   # 原始数据集路径target_data_folder = "split_data"  # 目标存放的路径data_set_split(initial_data_folder, target_data_folder)

import tensorflow as tf
import matplotlib.pyplot as plt
from time import *
from keras.models import Model
from keras.layers import Input, Dense, Dropout, BatchNormalization, Conv2D, MaxPooling2D, AveragePooling2D, concatenate, \Activation, ZeroPadding2D
from keras.layers import add, Flatten
from keras.metrics import top_k_categorical_accuracy
from keras.preprocessing.image import ImageDataGenerator
from keras.models import load_model
import os# 数据集加载函数，指明数据集的位置并统一处理为imgheight*imgwidth的大小，同时设置batch
def data_load(data_dir, test_data_dir, img_height, img_width, batch_size):# 加载训练集#tf.keras.preprocessing.image_dataset_from_directory从目录中的图像文件生成一个 tf.data.Datasettrain_ds = tf.keras.preprocessing.image_dataset_from_directory(data_dir,  # 数据所在目录。如果标签是“inferred”（默认），则它应该包含子目录，每个目录包含一个类的图像。否则，将忽略目录结构。 #省略labels: “inferred”（标签从目录结构生成），或者是整数标签的列表/元组，其大小与目录中找到的图像文件的数量相同。标签应根据图像文件路径的字母顺序排序（通过Python中的os.walk(directory)获得）。label_mode='categorical',# 'int'：表示标签被编码成整数（例如：sparse_categorical_crossentropy loss）。‘categorical’指标签被编码为分类向量（例如：categorical_crossentropy loss）。‘binary’意味着标签（只能有2个）被编码为值为0或1的float32标量（例如：binary_crossentropy）。None（无标签）。  seed=123,  #用于shuffle和转换的可选随机种子image_size=(img_height, img_width),  #数据批次的大小。默认值：32batch_size=batch_size)   #数据批次的大小。默认值：32# 加载验证集val_ds = tf.keras.preprocessing.image_dataset_from_directory(test_data_dir,label_mode='categorical',seed=123,image_size=(img_height, img_width),batch_size=batch_size)class_names = train_ds.class_names# 返回处理之后的训练集、验证集和类名return train_ds, val_ds, class_names
#拓展：
#如果label_mode 是 int, labels是形状为（batch_size, ）的int32张量
#如果label_mode 是 binary, labels是形状为（batch_size, 1）的1和0的float32张量。
#如果label_mode 是 categorial, labels是形状为（batch_size, num_classes）的float32张量，表示类索引的one-hot编码。
def Conv2d_BN(x, nb_filter, kernel_size, strides=(1, 1), padding='same', name=None):if name is not None:bn_name = name + '_bn'conv_name = name + '_conv'else:bn_name = Noneconv_name = Nonex = Conv2D(nb_filter, kernel_size, padding=padding, strides=strides, activation='relu', name=conv_name)(x)x = BatchNormalization(axis=3, name=bn_name)(x)return xdef identity_Block(inpt, nb_filter, kernel_size, strides=(1, 1), with_conv_shortcut=False):x = Conv2d_BN(inpt, nb_filter=nb_filter, kernel_size=kernel_size, strides=strides, padding='same')x = Conv2d_BN(x, nb_filter=nb_filter, kernel_size=kernel_size, padding='same')if with_conv_shortcut:shortcut = Conv2d_BN(inpt, nb_filter=nb_filter, strides=strides, kernel_size=kernel_size)x = add([x, shortcut])return xelse:x = add([x, inpt])return xdef bottleneck_Block(inpt,nb_filters,strides=(1,1),with_conv_shortcut=False):k1,k2,k3=nb_filtersx = Conv2d_BN(inpt, nb_filter=k1, kernel_size=1, strides=strides, padding='same')x = Conv2d_BN(x, nb_filter=k2, kernel_size=3, padding='same')x = Conv2d_BN(x, nb_filter=k3, kernel_size=1, padding='same')if with_conv_shortcut:shortcut = Conv2d_BN(inpt, nb_filter=k3, strides=strides, kernel_size=1)x = add([x, shortcut])return xelse:x = add([x, inpt])return xdef resnet_50(IMG_SHAPE=(224, 224, 3), class_num=5):inpt =Input(shape=IMG_SHAPE)x = ZeroPadding2D((3, 3))(inpt)x = Conv2d_BN(x, nb_filter=64, kernel_size=(7, 7), strides=(2, 2), padding='valid')x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='same')(x)#conv2_xx = bottleneck_Block(x, nb_filters=[64,64,256],strides=(1,1),with_conv_shortcut=True)x = bottleneck_Block(x, nb_filters=[64,64,256])x = bottleneck_Block(x, nb_filters=[64,64,256])#conv3_xx = bottleneck_Block(x, nb_filters=[128, 128, 512],strides=(2,2),with_conv_shortcut=True)x = bottleneck_Block(x, nb_filters=[128, 128, 512])x = bottleneck_Block(x, nb_filters=[128, 128, 512])x = bottleneck_Block(x, nb_filters=[128, 128, 512])#conv4_xx = bottleneck_Block(x, nb_filters=[256, 256, 1024],strides=(2,2),with_conv_shortcut=True)x = bottleneck_Block(x, nb_filters=[256, 256, 1024])x = bottleneck_Block(x, nb_filters=[256, 256, 1024])x = bottleneck_Block(x, nb_filters=[256, 256, 1024])x = bottleneck_Block(x, nb_filters=[256, 256, 1024])x = bottleneck_Block(x, nb_filters=[256, 256, 1024])#conv5_xx = bottleneck_Block(x, nb_filters=[512, 512, 2048], strides=(2, 2), with_conv_shortcut=True)x = bottleneck_Block(x, nb_filters=[512, 512, 2048])x = bottleneck_Block(x, nb_filters=[512, 512, 2048])x = AveragePooling2D(pool_size=(7, 7))(x)x = Flatten()(x)x = Dense(class_num, activation='softmax')(x)model = Model(inputs=inpt, outputs=x)# 输出模型信息model.summary()# 指明模型的训练参数，优化器为sgd优化器，损失函数为交叉熵损失函数model.compile(optimizer='sgd', loss='categorical_crossentropy', metrics=['accuracy'])# 返回模型return modeldef acc_top2(y_true, y_pred):return top_k_categorical_accuracy(y_true, y_pred, k=2)# 展示训练过程的曲线
def show_loss_acc(history):# 从history中提取模型训练集和验证集准确率信息和误差信息acc = history.history['accuracy']val_acc = history.history['val_accuracy']loss = history.history['loss']val_loss = history.history['val_loss']# 按照上下结构将图画输出plt.figure(figsize=(8, 8))plt.subplot(2, 1, 1)plt.plot(acc, label='Training Accuracy')plt.plot(val_acc, label='Validation Accuracy')plt.legend(loc='lower right')plt.ylabel('Accuracy')plt.ylim([min(plt.ylim()), 1])plt.title('Training and Validation Accuracy')plt.subplot(2, 1, 2)plt.plot(loss, label='Training Loss')plt.plot(val_loss, label='Validation Loss')plt.legend(loc='upper right')plt.ylabel('Cross Entropy')plt.title('Training and Validation Loss')plt.xlabel('epoch')plt.savefig('results/results_resnet.png', dpi=100)plt.show()
def train(epochs):# 开始训练，记录开始时间print("开始训练，记录开始时间。。。")begin_time = time()batch_size=16print("加载数据集中。。。")# todo 加载数据集， 修改为你的数据集的路径train_ds, val_ds, class_names = data_load("split_data/train","split_data/val", 224, 224, batch_size)print(class_names)print("加载模型中。。。")# 加载模型model = resnet_50(class_num=len(class_names))# 指明训练的轮数epoch，开始训练print("指明训练的轮数epoch，开始训练中。。。")history = model.fit(train_ds, validation_data=val_ds, epochs=epochs)# todo 保存模型， 修改为你要保存的模型的名称model.save("results/resnet_orange.h5")print("记录结束时间中。。。")# 记录结束时间end_time = time()run_time = end_time - begin_timeprint('该循环程序运行时间：', run_time, "s")  # 该循环程序运行时间： 1.4201874732# 绘制模型训练过程图show_loss_acc(history)if __name__ == '__main__':train(epochs=30)

import tensorflow as tf
from PyQt5.QtGui import *
from PyQt5.QtCore import *
from PyQt5.QtWidgets import *
import sys
import cv2
from PIL import Image
import numpy as np
import shutilclass MainWindow(QTabWidget):# 初始化def __init__(self):super().__init__()self.setWindowIcon(QIcon('images/logo.png'))self.setWindowTitle('大田柑橘病虫害识别系统')  # todo 修改系统名称# 模型初始化self.model = tf.keras.models.load_model("results/mobilenet_orange.h5")  # todo 修改模型名称:cnn_orange.h5、mobilenet_orange.h5、resnet_orange.h5self.to_predict_name = "images/background.jpg"  # todo 修改初始图片，这个图片要放在images目录下self.class_names = ['Fruit-anthrax', 'Fruit-ulcer', 'Leaf-anthrax','Leaf-ulcer', 'leaf_thyroid']  # todo 修改类名，这个数组在模型训练的开始会输出self.resize(900, 700)self.initUI()# 界面初始化，设置界面布局def initUI(self):main_widget = QWidget()main_layout = QHBoxLayout()font = QFont('楷体', 18)# 主页面，设置组件并在组件放在布局上left_widget = QWidget()left_layout = QVBoxLayout()img_title = QLabel("样本")img_title.setFont(font)img_title.setAlignment(Qt.AlignCenter)self.img_label = QLabel()img_init = cv2.imread(self.to_predict_name)h, w, c = img_init.shapescale = 400 / himg_show = cv2.resize(img_init, (0, 0), fx=scale, fy=scale)cv2.imwrite("images/show.png", img_show)img_init = cv2.resize(img_init, (224, 224))cv2.imwrite('images/target.png', img_init)self.img_label.setPixmap(QPixmap("images/show.png"))left_layout.addWidget(img_title)left_layout.addWidget(self.img_label, 1, Qt.AlignCenter)left_widget.setLayout(left_layout)right_widget = QWidget()right_layout = QVBoxLayout()btn_change = QPushButton(" 上传图片 ")btn_change.clicked.connect(self.change_img)btn_change.setFont(font)btn_predict = QPushButton(" 开始识别 ")btn_predict.setFont(font)btn_predict.clicked.connect(self.predict_img)label_result = QLabel(' 柑橘病虫害名称 ')self.result = QLabel("等待识别")label_result.setFont(QFont('楷体', 16))self.result.setFont(QFont('楷体', 24))right_layout.addStretch()right_layout.addWidget(label_result, 0, Qt.AlignCenter)right_layout.addStretch()right_layout.addWidget(self.result, 0, Qt.AlignCenter)right_layout.addStretch()right_layout.addStretch()right_layout.addWidget(btn_change)right_layout.addWidget(btn_predict)right_layout.addStretch()right_widget.setLayout(right_layout)main_layout.addWidget(left_widget)main_layout.addWidget(right_widget)main_widget.setLayout(main_layout)# 关于页面，设置组件并把组件放在布局上about_widget = QWidget()about_layout = QVBoxLayout()about_title = QLabel('欢迎使用柑橘病虫害识别系统')  # todo 修改欢迎词语about_title.setFont(QFont('楷体', 18))about_title.setAlignment(Qt.AlignCenter)about_img = QLabel()about_img.setPixmap(QPixmap('images/bj.jpg'))about_img.setAlignment(Qt.AlignCenter)label_super = QLabel("作者：宋扬")  # todo 更换作者信息label_super.setFont(QFont('楷体', 15))# label_super.setOpenExternalLinks(True)label_super.setAlignment(Qt.AlignRight)about_layout.addWidget(about_title)about_layout.addStretch()about_layout.addWidget(about_img)about_layout.addStretch()about_layout.addWidget(label_super)about_widget.setLayout(about_layout)# 添加注释self.addTab(main_widget, '主页')self.addTab(about_widget, '关于')self.setTabIcon(0, QIcon('images/主页面.png'))self.setTabIcon(1, QIcon('images/关于.png'))# 上传并显示图片def change_img(self):openfile_name = QFileDialog.getOpenFileName(self, 'chose files', '','Image files(*.jpg *.png *jpeg)')  # 打开文件选择框选择文件img_name = openfile_name[0]  # 获取图片名称if img_name == '':passelse:target_image_name = "images/tmp_up." + img_name.split(".")[-1]  # 将图片移动到当前目录shutil.copy(img_name, target_image_name)self.to_predict_name = target_image_nameimg_init = cv2.imread(self.to_predict_name)  # 打开图片h, w, c = img_init.shapescale = 400 / himg_show = cv2.resize(img_init, (0, 0), fx=scale, fy=scale)  # 将图片的大小统一调整到400的高，方便界面显示cv2.imwrite("images/show.png", img_show)img_init = cv2.resize(img_init, (224, 224))  # 将图片大小调整到224*224用于模型推理cv2.imwrite('images/target.png', img_init)self.img_label.setPixmap(QPixmap("images/show.png"))self.result.setText("等待识别")# 预测图片def predict_img(self):img = Image.open('images/target.png')  # 读取图片img = np.asarray(img)  # 将图片转化为numpy的数组outputs = self.model.predict(img.reshape(1, 224, 224, 3))  # 将图片输入模型得到结果result_index = int(np.argmax(outputs))result = self.class_names[result_index]  # 获得对应的水果名称self.result.setText(result)  # 在界面上做显示# 界面关闭事件，询问用户是否关闭def closeEvent(self, event):reply = QMessageBox.question(self,'退出',"是否要退出程序？",QMessageBox.Yes | QMessageBox.No,QMessageBox.No)if reply == QMessageBox.Yes:self.close()event.accept()else:event.ignore()if __name__ == "__main__":app = QApplication(sys.argv)x = MainWindow()x.show()sys.exit(app.exec_())