Pytorch实战 | P9 YOLOv5-Backbone模块实现天气识别

陈大麦 .

已于 2022-11-28 08:49:16 修改

阅读量522

点赞数

分类专栏：深度学习实践100例文章标签： pytorch 深度学习 python 人工智能

于 2022-11-27 14:40:35 首次发布

本文链接：https://blog.csdn.net/weixin_35820421/article/details/128064222

版权

● 🍨 本文为🔗365天深度学习训练营中的学习记录博客
● 🍦 参考文章：Pytorch实战 | 第P9天：YOLOv5-Backbone模块
● 🍖 原作者：K同学啊|接辅导、项目定制

一、我的环境

● 语言环境：Python3.8
● 编译器：pycharm
● 深度学习环境：Pytorch
● 数据来源：链接: https://pan.baidu.com/s/1SEfd8mvWt7BpzmWOeaIRkQ 提取码: gdie

二、代码实现

1、mian.py

# -*- coding: utf-8 -*-
import copy

import torch.utils.data
from torchvision import datasets, transforms
from model import train1, test1, YOLOv5f_backbone
import torch.nn as nn

# 一、导入和转换数据

img_path = './data/'
# 加载数据
train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406],
                         std=[0.229, 0.224, 0.225])
])
total_data = datasets.ImageFolder(img_path, transform=train_transforms)

# 训练数据和测试数据切分
train_size = int(len(total_data) * 0.8)
test_size = len(total_data) - train_size
train_data, test_data = torch.utils.data.random_split(total_data, [train_size, test_size])
# 按批次处理
batch_size = 4
train_dl = torch.utils.data.DataLoader(train_data, batch_size=batch_size, shuffle=True)
test_dl = torch.utils.data.DataLoader(test_data, batch_size=batch_size, shuffle=True)

# 二、模型网络结构 model.py

# 三、训练函数 model.py train1()和test1()函数
device = 'cuda' if torch.cuda.is_available() else 'cpu'
print('using:{}'.format(device))

model = YOLOv5f_backbone().to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
loss_fn = nn.CrossEntropyLoss()

epochs = 60

train_loss = []
test_loss = []
train_acc = []
test_acc