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

news2024/11/18 2:37:04

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 argparse

import torch
import torch.optim as optim
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
import torch.optim.lr_scheduler as lr_scheduler

from model import create_regnet
from my_dataset import MyDataSet
from utils import read_split_data, train_one_epoch, evaluate


def 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_size
    nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8])  # number of workers
    print('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.pdf
    lf = lambda x: ((1 + math.cos(x * math.pi / args.epochs)) / 2) * (1 - args.lrf) + args.lrf  # cosine
    scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)

    for epoch in range(args.epochs):
        # train
        mean_loss = train_one_epoch(model=model,
                                    optimizer=optimizer,
                                    data_loader=train_loader,
                                    device=device,
                                    epoch=epoch)

        scheduler.step()

        # validate
        acc = 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.tgz
    parser.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: 8lmu
    parser.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