LAB 3 First pair lab

m0_48094987 m0_48094987 墨衍会员 · AI 创作全网分发 墨衍智能分发 通过墨衍一键同步至各平台 可同步平台 CSDN微信公众号微博知乎掘金百家号博客园抖音小红书 你的文章也可以这样分发 墨衍会员 ¥399起/年,写一次发全网 我也要 + 加入社区
The Link Your Class https://bbs.csdn.net/forums/MUEE308FZ
The Link of Requirement of This Assignment https://bbs.csdn.net/topics/600914861
The Aim of This AssignmentRealize Bobing software prototype
MU STU ID and FZU STU ID19105002 & 831901310
MU STU ID and FZU STU ID19104987 & 831901324
Personal Software Process StageEstimated Time (minutes)Actual Time (minutes)
Planning3030
Estimate2020
Development--
Analysis3035
Design Spec3030
Design Review6075
Coding Standard2020
Design4020
Coding--
Code Review--
Test1010
Reporting6060
Test Report4040
Size Measurement1520
Postmortem&Process Improvement5060
Total405420

Prototype Exhibition
https://modao.cc/app/4d13cecdba630fb377a6a6b3af743f6575353f76#screen=sku5cbpdq1ep5uu

Requirements analysis: NABCD model
NABCD is composed of the first letters of five words Need, Approach, Benfit, Competitors, Delivery, which respectively refers to demand, practice, benefit, competition and promotion. Through these five parts, the characteristics of the project can be clearly and concisedly summarized.

1. Need
Mid-autumn Festival is a traditional festival in China, and people in China are always willing to hold various activities to celebrate the great customs and recall their ancestors. Due to the outbreak of COVID-19 pandemic, mass part and the gathering of large-scale crowd are not allowed in this special period, and people have to take other measures to celebrate the festival.
Bobing, a very famous activity, which is popular in Fujian province for over hundreds of years, also have to stop due to its large-scale crowd-gathering, which could may cause the fast spread of COVID-19. Without this offline activity, the atmosphere of Mid-autumn festival is greatly reduced and the loss of communications in families during the festival is also a great loss for modern people.

2. Approach
The program is designed on ink knives, and you can play it directly on the website.
The program can also run on the smart phone.

img

I also introduce the story of Bobing, the rules are included.

img

3. Benefit
It response national policy for epidemic control.
Easy to operate, even the elders can get this started easily.
The interactive page is clean. People can quickly now what to do and how to operate.
(High EQ:Clean Low EQ:poor)

img

4. Competitors
Many same kinds of programs have already existed, and some of them have beautiful animations and more thorough. But in all, I think the program we designed is more competetive, because ours is easier to handle.

5. Delivery
We will do the advertisement and do the maintainance for our program for all the time.
We will add more game mode in the near future.
We will beautify the game UI in the future.
The game will support multiplayer mode in the future. You can play with your friends from anywhere in the world.

6. Summary
I learn a lot from this experiment. It shows me the basic frame of making a program, and I also learnt how to use ink knives to design the basic UI of a program. It is the first time I use NABCD model, it teaches me how to think systematically and put the idea into use. In all, I believe that I can do better in the next experiment.

img

...全文

相关推荐

冀教版初中英语单词表(7_9).docx

冀教版初中英语单词表(7_9).docx

xxiang85

chrome-win64-151.0.7904.0(Canary).zip

chrome-win64-151.0.7904.0(Canary).zip

wdxnzhh

变电站精细化设计施工标准(电气部分)

变电站精细化设计施工标准(电气部分).pdf。文档内容齐全,中间有页码不对,是因为这是两个文档合成的,不影响内容完整,内容为图片,不是源文档。

bigshentu

chromedriver-mac-x64-159.0.8133.0(Canary).zip

chromedriver-mac-x64-159.0.8133.0(Canary).zip

LCG元

YOLO26算法工业车间光伏组件热点与系列故障目标检测+训练好的模型+174张数据集+pyqt可视化界面.zip

附训练好的 YOLO 权重与 PyQt 可视化检测界面,页面底部含可视化效果预览,毕设/课设开箱即用。 【数据集概况】 · 检测类别(中文):[系列故障(Falla serie), 热点(Punto caliente)] · 训练集:153 张 · 验证集:14 张 · 测试集:7 张 · 总计:174 张 该数据集聚焦于工业车间内光伏组件的热成像检测场景,专门针对太阳能电池板在运行过程中出现的局部异常进行精准识别,具有明确的工程诊断价值与质量控制意义。数据采集覆盖多种典型热异常模式,为光伏系统运维中的早期隐患预警提供了高质量视觉样本支撑。... 【训练曲线与评估图】 【模型训练配置】 参数 | 值 模型 | yolo26n 训练轮数 | 100 epochs 输入尺寸 | 640x640 批次大小 | 24 优化器 | auto 初始学习率 | 0.01 训练设备 【关键指标汇总】 训练了 85 个 epoch,最终轮指标: 指标 | 数值 mAP50 | **0.8734** mAP50-95 | 0.3870 Precision | 0.8062 Recall | 0.8306 train/box_loss | 2.1071 train/cls_loss | 0.9683 val/box_loss | 1.9784 val/cls_loss | 0.6732 【训练过程分析】 从数据加载那一刻起,整个训练过程仿佛是在一条崎岖不平的道路上前进。训练初期,模型的收敛速度颇为迅速,loss 值稳步降低,到第 20 轮时,box_loss 从初始值 2.1071 下降到 1.85,但并未显著波动,仿佛遇到了平台期。从第 40 轮到 60 轮,训练过程变得愈发缓慢,loss 下降幅度逐渐减小,尤其是 cls_... 使用场景:毕业设计、课程设计、深度学习入门、工业场景落地验证。

guo_xiao_xiao_
评论
收藏 已收藏
分享
返回顶部