一.开源神经网络(AlexNet)
1.获取数据集
split_data.py
import osfrom shutil import copy, rmtreeimport randomdef mk_file(file_path: str):if os.path.exists(file_path):# 如果文件夹存在，则先删除原文件夹在重新创建rmtree(file_path)os.makedirs(file_path)def main():# 保证随机可复现random.seed(0)# 将数据集中10%的数据划分到验证集中split_rate = 0.1# 指向你解压后的flower_photos文件夹cwd = os.getcwd()data_root = os.path.join(cwd, "flower_data")origin_flower_path = os.path.join(data_root, "flower_photos")assert os.path.exists(origin_flower_path)flower_class = [cla for cla in os.listdir(origin_flower_path)if os.path.isdir(os.path.join(origin_flower_path, cla))]# 建立保存训练集的文件夹train_root = os.path.join(data_root, "train")mk_file(train_root)for cla in flower_class:# 建立每个类别对应的文件夹mk_file(os.path.join(train_root, cla))# 建立保存验证集的文件夹val_root = os.path.join(data_root, "val")mk_file(val_root)for cla in flower_class:# 建立每个类别对应的文件夹mk_file(os.path.join(val_root, cla))for cla in flower_class:cla_path = os.path.join(origin_flower_path, cla)images = os.listdir(cla_path)num = len(images)# 随机采样验证集的索引eval_index = random.sample(images, k=int(num*split_rate))for index, image in enumerate(images):if image in eval_index:# 将分配至验证集中的文件复制到相应目录image_path = os.path.join(cla_path, image)new_path = os.path.join(val_root, cla)copy(image_path, new_path)else:# 将分配至训练集中的文件复制到相应目录image_path = os.path.join(cla_path, image)new_path = os.path.join(train_root, cla)copy(image_path, new_path)print("\r[{}] processing [{}/{}]".format(cla, index+1, num), end="") # processing barprint()print("processing done!")if __name__ == '__main__':main()
2.神经网络模型
import torch.nn as nnimport torchclass AlexNet(nn.Module):def __init__(self, num_classes=1000, init_weights=False):super(AlexNet, self).__init__()# 用nn.Sequential()将网络打包成一个模块，精简代码self.features = nn.Sequential( # 卷积层提取图像特征nn.Conv2d(3, 48, kernel_size=11, stride=4, padding=2), # input[3, 224, 224] output[48, 55, 55]nn.ReLU(inplace=True), # 直接修改覆盖原值，节省运算内存nn.MaxPool2d(kernel_size=3, stride=2), # output[48, 27, 27]nn.Conv2d(48, 128, kernel_size=5, padding=2), # output[128, 27, 27]nn.ReLU(inplace=True),nn.MaxPool2d(kernel_size=3, stride=2), # output[128, 13, 13]nn.Conv2d(128, 192, kernel_size=3, padding=1), # output[192, 13, 13]nn.ReLU(inplace=True),nn.Conv2d(192, 192, kernel_size=3, padding=1), # output[192, 13, 13]nn.ReLU(inplace=True),nn.Conv2d(192, 128, kernel_size=3, padding=1), # output[128, 13, 13]nn.ReLU(inplace=True),nn.MaxPool2d(kernel_size=3, stride=2), # output[128, 6, 6])self.classifier = nn.Sequential( # 全连接层对图像分类nn.Dropout(p=0.5), # Dropout 随机失活神经元，默认比例为0.5nn.Linear(128 * 6 * 6, 2048),nn.ReLU(inplace=True),nn.Dropout(p=0.5),nn.Linear(2048, 2048),nn.ReLU(inplace=True),nn.Linear(2048, num_classes),)if init_weights:self._initialize_weights()# 前向传播过程def forward(self, x):x = self.features(x)x = torch.flatten(x, start_dim=1) # 展平后再传入全连接层x = self.classifier(x)return x# 网络权重初始化，实际上 pytorch 在构建网络时会自动初始化权重def _initialize_weights(self):for m in self.modules():if isinstance(m, nn.Conv2d): # 若是卷积层nn.init.kaiming_normal_(m.weight, mode='fan_out', # 用（何）kaiming_normal_法初始化权重nonlinearity='relu')if m.bias is not None:nn.init.constant_(m.bias, 0) # 初始化偏重为0elif isinstance(m, nn.Linear): # 若是全连接层nn.init.normal_(m.weight, 0, 0.01) # 正态分布初始化nn.init.constant_(m.bias, 0) # 初始化偏重为0
3.训练神经网络
# 导入包import torchimport torch.nn as nnfrom torchvision import transforms, datasets, utilsimport matplotlib.pyplot as pltimport numpy as npimport torch.optim as optimfrom model import AlexNetimport osimport jsonimport time# 使用GPU训练device = torch.device("cuda" if torch.cuda.is_available() else "cpu")with open(os.path.join("train.log"), "a") as log:log.write(str(device)+"\n")#数据预处理data_transform = {"train": transforms.Compose([transforms.RandomResizedCrop(224), # 随机裁剪，再缩放成 224×224transforms.RandomHorizontalFlip(p=0.5), # 水平方向随机翻转，概率为 0.5, 即一半的概率翻转, 一半的概率不翻转transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]),"val": transforms.Compose([transforms.Resize((224, 224)), # cannot 224, must (224, 224)transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])}#导入、加载 训练集# 导入训练集#train_set = torchvision.datasets.CIFAR10(root='./data', # 数据集存放目录# train=True, # 表示是数据集中的训练集# download=True, # 第一次运行时为True，下载数据集，下载完成后改为False# transform=transform) # 预处理过程# 加载训练集#train_loader = torch.utils.data.DataLoader(train_set, # 导入的训练集# batch_size=50, # 每批训练的样本数# shuffle=False, # 是否打乱训练集# num_workers=0) # num_workers在windows下设置为0# 获取图像数据集的路径data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path 返回上上层目录image_path = data_root + "/jqsj/data_set/flower_data/" # flower data_set path# 导入训练集并进行预处理train_dataset = datasets.ImageFolder(root=image_path + "/train",transform=data_transform["train"])train_num = len(train_dataset)# 按batch_size分批次加载训练集train_loader = torch.utils.data.DataLoader(train_dataset, # 导入的训练集batch_size=32, # 每批训练的样本数shuffle=True, # 是否打乱训练集num_workers=0) # 使用线程数，在windows下设置为0#导入、加载 验证集# 导入验证集并进行预处理validate_dataset = datasets.ImageFolder(root=image_path + "/val",transform=data_transform["val"])val_num = len(validate_dataset)# 加载验证集validate_loader = torch.utils.data.DataLoader(validate_dataset, # 导入的验证集batch_size=32,shuffle=True,num_workers=0)# 存储 索引：标签 的字典# 字典，类别：索引 {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}flower_list = train_dataset.class_to_idx# 将 flower_list 中的 key 和 val 调换位置cla_dict = dict((val, key) for key, val in flower_list.items())# 将 cla_dict 写入 json 文件中json_str = json.dumps(cla_dict, indent=4)with open('class_indices.json', 'w') as json_file:json_file.write(json_str)#训练过程net = AlexNet(num_classes=5, init_weights=True) # 实例化网络（输出类型为5，初始化权重）net.to(device) # 分配网络到指定的设备（GPU/CPU）训练loss_function = nn.CrossEntropyLoss() # 交叉熵损失optimizer = optim.Adam(net.parameters(), lr=0.0002) # 优化器（训练参数，学习率）save_path = './AlexNet.pth'best_acc = 0.0for epoch in range(150):########################################## train ###############################################net.train() # 训练过程中开启 Dropoutrunning_loss = 0.0 # 每个 epoch 都会对 running_loss 清零time_start = time.perf_counter() # 对训练一个 epoch 计时for step, data in enumerate(train_loader, start=0): # 遍历训练集，step从0开始计算images, labels = data # 获取训练集的图像和标签optimizer.zero_grad() # 清除历史梯度outputs = net(images.to(device)) # 正向传播loss = loss_function(outputs, labels.to(device)) # 计算损失loss.backward() # 反向传播optimizer.step() # 优化器更新参数running_loss += loss.item()# 打印训练进度（使训练过程可视化）rate = (step + 1) / len(train_loader) # 当前进度 = 当前step / 训练一轮epoch所需总stepa = "*" * int(rate * 50)b = "." * int((1 - rate) * 50)with open(os.path.join("train.log"), "a") as log:log.write(str("\rtrain loss: {:^3.0f}%[{}->{}]{:.3f}".format(int(rate * 100), a, b, loss))+"\n")print("\rtrain loss: {:^3.0f}%[{}->{}]{:.3f}".format(int(rate * 100), a, b, loss), end="")print()with open(os.path.join("train.log"), "a") as log:log.write(str('%f s' % (time.perf_counter()-time_start))+"\n")print('%f s' % (time.perf_counter()-time_start))########################################### validate ###########################################net.eval() # 验证过程中关闭 Dropoutacc = 0.0with torch.no_grad():for val_data in validate_loader:val_images, val_labels = val_dataoutputs = net(val_images.to(device))predict_y = torch.max(outputs, dim=1)[1] # 以output中值最大位置对应的索引（标签）作为预测输出acc += (predict_y == val_labels.to(device)).sum().item()val_accurate = acc / val_num# 保存准确率最高的那次网络参数if val_accurate > best_acc:best_acc = val_accuratetorch.save(net.state_dict(), save_path)with open(os.path.join("train.log"), "a") as log:log.write(str('[epoch %d] train_loss: %.3f test_accuracy: %.3f \n' %(epoch + 1, running_loss / step, val_accurate))+"\n")print('[epoch %d] train_loss: %.3f test_accuracy: %.3f \n' %(epoch + 1, running_loss / step, val_accurate))with open(os.path.join("train.log"), "a") as log:log.write(str('Finished Training')+"\n")print('Finished Training')
4.对模型进行预测
import torchfrom model import AlexNetfrom PIL import Imagefrom torchvision import transformsimport matplotlib.pyplot as pltimport json# 预处理data_transform = transforms.Compose([transforms.Resize((224, 224)),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])# load imageimg = Image.open("pgy2.jpg")#plt.imshow(img)# [N, C, H, W]img = data_transform(img)# expand batch dimensionimg = torch.unsqueeze(img, dim=0)# read class_indicttry:json_file = open('./class_indices.json', 'r')class_indict = json.load(json_file)except Exception as e:print(e)exit(-1)# create modelmodel = AlexNet(num_classes=5)# load model weightsmodel_weight_path = "./AlexNet.pth"#, map_location='cpu'model.load_state_dict(torch.load(model_weight_path, map_location='cpu'))# 关闭 Dropoutmodel.eval()with torch.no_grad():# predict classoutput = torch.squeeze(model(img)) # 将输出压缩，即压缩掉 batch 这个维度predict = torch.softmax(output, dim=0)predict_cla = torch.argmax(predict).numpy()print(class_indict[str(predict_cla)], predict[predict_cla].item())plt.show()
二、花卉识别系统搭建（flask）
1.构建页面：
<html lang="en"><head><meta charset="UTF-8"><title>李运辰-花卉识别系统v1.0</title><link rel="stylesheet" type="text/css" href="../static/css/bootstrap.min.css"><link rel="stylesheet" type="text/css" href="../static/css/fileinput.css"><script src="../static/js/jquery-2.1.4.min.js"></script><script src="../static/js/bootstrap.min.js"></script><script src="../static/js/fileinput.js"></script><script src="../static/js/locales/zh.js"></script></head><body><h1 align="center">李运辰-花卉识别系统v1.0</h1><div align="center"><form action="" enctype='multipart/form-data' method='POST'><input type="file" name="file" class="file" data-show-preview="false" style="margin-top:20px;"/><br><input type="submit" value="上传" class="btn btn-primary button-new " style="margin-top:15px;"/></form></div></body></html>
2.调用神经网络模型
# coding:utf-8from flask import Flask, render_template, request, redirect, url_for, make_response, jsonifyfrom werkzeug.utils import secure_filenameimport osimport time####################模型所需库包import torchfrom model import AlexNetfrom PIL import Imagefrom torchvision import transformsimport matplotlib.pyplot as pltimport json# read class_indicttry:json_file = open('./class_indices.json', 'r')class_indict = json.load(json_file)except Exception as e:print(e)exit(-1)# create modelmodel = AlexNet(num_classes=5)# load model weightsmodel_weight_path = "./AlexNet.pth"#, map_location='cpu'model.load_state_dict(torch.load(model_weight_path, map_location='cpu'))# 关闭 Dropoutmodel.eval()###################from datetime import timedelta# 设置允许的文件格式ALLOWED_EXTENSIONS = set(['png', 'jpg', 'JPG', 'PNG', 'bmp'])def allowed_file(filename):return '.' in filename and filename.rsplit('.', 1)[1] in ALLOWED_EXTENSIONSapp = Flask(__name__)# 设置静态文件缓存过期时间app.send_file_max_age_default = timedelta(seconds=1)#图片装换操作def tran(img_path):# 预处理data_transform = transforms.Compose([transforms.Resize((224, 224)),transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])# load imageimg = Image.open("pgy2.jpg")#plt.imshow(img)# [N, C, H, W]img = data_transform(img)# expand batch dimensionimg = torch.unsqueeze(img, dim=0)return imgdef upload():path=""if request.method == 'POST':f = request.files['file']if not (f and allowed_file(f.filename)):return jsonify({"error": 1001, "msg": "请检查上传的图片类型，仅限于png、PNG、jpg、JPG、bmp"})basepath = os.path.dirname(__file__) # 当前文件所在路径path = secure_filename(f.filename)upload_path = os.path.join(basepath, 'static/images', secure_filename(f.filename)) # 注意：没有的文件夹一定要先创建，不然会提示没有该路径# upload_path = os.path.join(basepath, 'static/images','test.jpg') #注意：没有的文件夹一定要先创建，不然会提示没有该路径print(path)img = tran('static/images'+path)###########################预测图片with torch.no_grad():# predict classoutput = torch.squeeze(model(img)) # 将输出压缩，即压缩掉 batch 这个维度predict = torch.softmax(output, dim=0)predict_cla = torch.argmax(predict).numpy()res = class_indict[str(predict_cla)]pred = predict[predict_cla].item()#print(class_indict[str(predict_cla)], predict[predict_cla].item())res_chinese = ""if res=="daisy":res_chinese="雏菊"if res=="dandelion":res_chinese="蒲公英"if res=="roses":res_chinese="玫瑰"if res=="sunflower":res_chinese="向日葵"if res=="tulips":res_chinese="郁金香"#print('result:', class_indict[str(predict_class)], 'accuracy:', prediction[predict_class])##########################f.save(upload_path)pred = pred*100return render_template('upload_ok.html', path=path, res_chinese=res_chinese,pred = pred, val1=time.time())return render_template('upload.html')if __name__ == '__main__':# app.debug = Trueapp.run(host='127.0.0.1', port=80,debug = True)
3.系统识别结果
<html lang="en"><head><meta charset="UTF-8"><title>李运辰-花卉识别系统v1.0</title><link rel="stylesheet" type="text/css" href="../static/css/bootstrap.min.css"><link rel="stylesheet" type="text/css" href="../static/css/fileinput.css"><script src="../static/js/jquery-2.1.4.min.js"></script><script src="../static/js/bootstrap.min.js"></script><script src="../static/js/fileinput.js"></script><script src="../static/js/locales/zh.js"></script></head><body><h1 align="center">李运辰-花卉识别系统v1.0</h1><div align="center"><form action="" enctype='multipart/form-data' method='POST'><input type="file" name="file" class="file" data-show-preview="false" style="margin-top:20px;"/><br><input type="submit" value="上传" class="button-new btn btn-primary" style="margin-top:15px;"/></form><p style="size:15px;color:blue;">识别结果:{{res_chinese}}</p></br><p style="size:15px;color:red;">准确率:{{pred}}%</p><img src="{{ './static/images/'+path }}" width="400" height="400" alt=""/></div></body></html>
4.启动系统：
python main.py
http://127.0.0.1/upload
三、总结
【完整源码获取方式】
【加群获取学习资料QQ群：901381280】
欢迎关注公众号：方便及时阅读最新文章
回复【开源源码】免费获取更多开源项目源码；
本文分享自微信公众号 - Python爬虫数据分析挖掘（zyzx3344）。
如有侵权，请联系 support@oschina.cn 删除。
本文参与“OSC源创计划”，欢迎正在阅读的你也加入，一起分享。
来源：oschina
链接：https://my.oschina.net/u/4638454/blog/4815036