基于Pytorch框架的深度学习RegNet神经网络二十五种宝石识别分类系统源码

第一步：准备数据

25种宝石数据，总共800张：

{ "0": "Alexandrite","1": "Almandine","2": "Benitoite","3": "Beryl Golden","4": "Carnelian", "5": "Cats Eye","6": "Danburite", "7": "Diamond","8": "Emerald","9": "Fluorite","10": "Garnet Red","11": "Hessonite","12": "Iolite","13": "Jade","14": "Kunzite","15": "Labradorite","16": "Malachite","17": "Onyx Black","18": "Pearl","19": "Quartz Beer","20": "Rhodochrosite","21": "Sapphire Blue","22": "Tanzanite","23": "Variscite","24": "Zircon"}

第二步：搭建模型

本文选择一个RegNet网络，其原理介绍如下：

该论文提出了一个新的网络设计范式，并不是专注于设计单个网络实例，而是设计了一个网络设计空间network design space。整个过程类似于经典的手工网络设计，但被提升到了设计空间的水平。使用本文的方法，作者探索了网络设计的结构方面，并得到了一个由简单、规则的网络构成了低维设计空间并称之为RegNet。RegNet设计空间提供了各个范围flop下简单、快速的网络。在类似的训练设置和flops下，RegNet的效果超过了EfficientNet同时在GPU上快了5倍

第三步：训练代码

1）损失函数为：交叉熵损失函数

2）训练代码：

import os
import math
import argparseimport torch
import torch.optim as optim
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
import torch.optim.lr_scheduler as lr_schedulerfrom model import create_regnet
from my_dataset import MyDataSet
from utils import read_split_data, train_one_epoch, evaluatedef main(args):device = torch.device(args.device if torch.cuda.is_available() else "cpu")print(args)print('Start Tensorboard with "tensorboard --logdir=runs", view at http://localhost:6006/')tb_writer = SummaryWriter()if os.path.exists("./weights") is False:os.makedirs("./weights")train_images_path, train_images_label, val_images_path, val_images_label = read_split_data(args.data_path)data_transform = {"train": transforms.Compose([transforms.RandomResizedCrop(224),transforms.RandomHorizontalFlip(),transforms.ToTensor(),transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),"val": transforms.Compose([transforms.Resize(256),transforms.CenterCrop(224),transforms.ToTensor(),transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])}# 实例化训练数据集train_dataset = MyDataSet(images_path=train_images_path,images_class=train_images_label,transform=data_transform["train"])# 实例化验证数据集val_dataset = MyDataSet(images_path=val_images_path,images_class=val_images_label,transform=data_transform["val"])batch_size = args.batch_sizenw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8])  # number of workersprint('Using {} dataloader workers every process'.format(nw))train_loader = torch.utils.data.DataLoader(train_dataset,batch_size=batch_size,shuffle=True,pin_memory=True,num_workers=nw,collate_fn=train_dataset.collate_fn)val_loader = torch.utils.data.DataLoader(val_dataset,batch_size=batch_size,shuffle=False,pin_memory=True,num_workers=nw,collate_fn=val_dataset.collate_fn)# 如果存在预训练权重则载入model = create_regnet(model_name=args.model_name,num_classes=args.num_classes).to(device)# print(model)if args.weights != "":if os.path.exists(args.weights):weights_dict = torch.load(args.weights, map_location=device)load_weights_dict = {k: v for k, v in weights_dict.items()if model.state_dict()[k].numel() == v.numel()}print(model.load_state_dict(load_weights_dict, strict=False))else:raise FileNotFoundError("not found weights file: {}".format(args.weights))# 是否冻结权重if args.freeze_layers:for name, para in model.named_parameters():# 除最后的全连接层外，其他权重全部冻结if "head" not in name:para.requires_grad_(False)else:print("train {}".format(name))pg = [p for p in model.parameters() if p.requires_grad]optimizer = optim.SGD(pg, lr=args.lr, momentum=0.9, weight_decay=5E-5)# Scheduler https://arxiv.org/pdf/1812.01187.pdflf = lambda x: ((1 + math.cos(x * math.pi / args.epochs)) / 2) * (1 - args.lrf) + args.lrf  # cosinescheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)for epoch in range(args.epochs):# trainmean_loss = train_one_epoch(model=model,optimizer=optimizer,data_loader=train_loader,device=device,epoch=epoch)scheduler.step()# validateacc = evaluate(model=model,data_loader=val_loader,device=device)print("[epoch {}] accuracy: {}".format(epoch, round(acc, 3)))tags = ["loss", "accuracy", "learning_rate"]tb_writer.add_scalar(tags[0], mean_loss, epoch)tb_writer.add_scalar(tags[1], acc, epoch)tb_writer.add_scalar(tags[2], optimizer.param_groups[0]["lr"], epoch)torch.save(model.state_dict(), "./weights/model-{}.pth".format(epoch))if __name__ == '__main__':parser = argparse.ArgumentParser()parser.add_argument('--num_classes', type=int, default=25)parser.add_argument('--epochs', type=int, default=100)parser.add_argument('--batch-size', type=int, default=4)parser.add_argument('--lr', type=float, default=0.001)parser.add_argument('--lrf', type=float, default=0.01)# 数据集所在根目录# https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgzparser.add_argument('--data-path', type=str,default=r"G:\demo\data\gemstone\archive_train")parser.add_argument('--model-name', default='RegNetY_400MF', help='create model name')# 预训练权重下载地址# 链接: https://pan.baidu.com/s/1XTo3walj9ai7ZhWz7jh-YA  密码: 8lmuparser.add_argument('--weights', type=str, default='regnety_400mf.pth',help='initial weights path')parser.add_argument('--freeze-layers', type=bool, default=False)parser.add_argument('--device', default='cuda:0', help='device id (i.e. 0 or 0,1 or cpu)')opt = parser.parse_args()main(opt)

第四步：统计正确率