第一步:准备数据
5种鸟类行为数据:self.class_indict =
["bowing_status", "grooming", "headdown", "vigilance_status", "walking"]
,总共有23790张图片,每个文件夹单独放一种数据
第二步:搭建模型
简介:
DenseNet(Dense Convolutional Network)稠密卷积网络
CVPR2017的优秀文章
从feature入手,通过对feature的极致利用达到更好的效果和更少的参数。
优点:
减轻了vanishing-gradient(梯度消失)
加强了feature的传递
更有效地利用了feature
一定程度上较少了参数数量
在深度学习网络中,随着网络深度的加深,梯度消失问题会愈加明显,解决方法是创建浅层与深层之间的短路径。在DenseNet中,在保证网络中层与层之间最大程度的信息传输的前提下,直接将所有层连接起来。
在传统卷积神经网络中,如果你有L层,那么就会有L个连接,但是在DenseNet中,会有(L+1)/2个连接。简单来说,就是每一层的输入来自前面所有层的输出。如下图是dense block的结构图,x是数据,H是网络层。
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:
python
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 densenet121, load_state_dict
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 "cd", 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 = densenet121(num_classes=args.num_classes).to(device)
if args.weights != "":
if os.path.exists(args.weights):
load_state_dict(model, args.weights)
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 "classifier" not in name:
para.requires_grad_(False)
pg = [p for p in model.parameters() if p.requires_grad]
optimizer = optim.SGD(pg, lr=args.lr, momentum=0.9, weight_decay=1E-4, nesterov=True)
# 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=5)
parser.add_argument('--epochs', type=int, default=100)
parser.add_argument('--batch-size', type=int, default=16)
parser.add_argument('--lr', type=float, default=0.001)
parser.add_argument('--lrf', type=float, default=0.1)
# 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"E:\20240717\data")
# densenet121 官方权重下载地址
# https://download.pytorch.org/models/densenet121-a639ec97.pth
parser.add_argument('--weights', type=str, default='densenet121.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
第五步:搭建GUI界面
视频演示地址: 基于Pytorch框架的深度学习densenet121神经网络鸟类行为识别分类系统源码_哔哩哔哩_bilibili
第六步:整个工程的内容
有训练代码和训练好的模型以及训练过程,提供数据,提供GUI界面代码
代码见:基于Pytorch框架的深度学习densenet121神经网络鸟类行为识别分类系统源码
有问题可以私信或者留言,有问必答