第一步：准备数据
12种宠物猫类数据：self.class_indict = ["阿比西尼猫", "豹猫", "伯曼猫", "孟买猫", "英国短毛猫", "埃及猫", "缅因猫", "波斯猫", "布偶猫", "克拉特猫", "泰国暹罗猫", "加拿大无毛猫"]
，总共有2160张图片，每个文件夹单独放一种数据
第二步：搭建模型
本文选择一个ConvNext网络，其原理介绍如下：
ConvNext (Convolutional Network Net Generation), 即下一代卷积神经网络, 是近些年来 CV 领域的一个重要发展. ConvNext 由 Facebook AI Research 提出, 仅仅通过卷积结构就达到了与 Transformer 结构相媲美的 ImageNet Top-1 准确率, 这在近年来以 Transformer 为主导的视觉问题解决趋势中显得尤为突出.
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 argparse
import torch
import torch.optim as optim
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
from my_dataset import MyDataSet
from model import convnext_tiny as create_model
from utils import read_split_data, create_lr_scheduler, get_params_groups, train_one_epoch, evaluate
def main(args):
device = torch.device(args.device if torch.cuda.is_available() else "cpu")
print(f"using {device} device.")
if os.path.exists("./weights") is False:
os.makedirs("./weights")
tb_writer = SummaryWriter()
train_images_path, train_images_label, val_images_path, val_images_label = read_split_data(args.data_path)
img_size = 224
data_transform = {
"train": transforms.Compose([transforms.RandomResizedCrop(img_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
"val": transforms.Compose([transforms.Resize(int(img_size * 1.143)),
transforms.CenterCrop(img_size),
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)
model = create_model(num_classes=args.num_classes).to(device)
if args.weights != "":
assert os.path.exists(args.weights), "weights file: '{}' not exist.".format(args.weights)
weights_dict = torch.load(args.weights, map_location=device)["model"]
# 删除有关分类类别的权重
for k in list(weights_dict.keys()):
if "head" in k:
del weights_dict[k]
print(model.load_state_dict(weights_dict, strict=False))
if args.freeze_layers:
for name, para in model.named_parameters():
# 除head外，其他权重全部冻结
if "head" not in name:
para.requires_grad_(False)
else:
print("training {}".format(name))
# pg = [p for p in model.parameters() if p.requires_grad]
pg = get_params_groups(model, weight_decay=args.wd)
optimizer = optim.AdamW(pg, lr=args.lr, weight_decay=args.wd)
lr_scheduler = create_lr_scheduler(optimizer, len(train_loader), args.epochs,
warmup=True, warmup_epochs=1)
best_acc = 0.
for epoch in range(args.epochs):
# train
train_loss, train_acc = train_one_epoch(model=model,
optimizer=optimizer,
data_loader=train_loader,
device=device,
epoch=epoch,
lr_scheduler=lr_scheduler)
# validate
val_loss, val_acc = evaluate(model=model,
data_loader=val_loader,
device=device,
epoch=epoch)
tags = ["train_loss", "train_acc", "val_loss", "val_acc", "learning_rate"]
tb_writer.add_scalar(tags[0], train_loss, epoch)
tb_writer.add_scalar(tags[1], train_acc, epoch)
tb_writer.add_scalar(tags[2], val_loss, epoch)
tb_writer.add_scalar(tags[3], val_acc, epoch)
tb_writer.add_scalar(tags[4], optimizer.param_groups[0]["lr"], epoch)
if best_acc < val_acc:
torch.save(model.state_dict(), "./weights/best_model.pth")
best_acc = val_acc
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--num_classes', type=int, default=12)
parser.add_argument('--epochs', type=int, default=100)
parser.add_argument('--batch-size', type=int, default=4)
parser.add_argument('--lr', type=float, default=5e-4)
parser.add_argument('--wd', type=float, default=5e-2)
# 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\cat_data_sets_models\cat_12_train")
# 预训练权重路径，如果不想载入就设置为空字符
# 链接: https://pan.baidu.com/s/1aNqQW4n_RrUlWUBNlaJRHA 密码: i83t
parser.add_argument('--weights', type=str, default='./convnext_tiny_1k_224_ema.pth',
help='initial weights path')
# 是否冻结head以外所有权重
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
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
代码的下载路径（新窗口打开链接）：基于Pytorch框架的深度学习ConvNext神经网络宠物猫识别分类系统源码
有问题可以私信或者留言，有问必答