School Category
Entry ID
789
Participation Type/參賽類型
Team
Expected Stream/參賽組別
Stream 1: Identifying an educational problem and proposing a solution.
Participation Type/參賽類型
Team
School Name/學校名稱
佛山市南海区狮山石门高级中学
Team Name/參賽隊伍名:
shootcraft
Participant information (Team Members) / 參賽者信息(小組成員)
Row ID Full name in Chinese/中文全名 Full name in English/英文全名 Gender/性別 Current Year of Study/目前就讀的年級
1 邓剑鹏 dengjianpeng Male/男性 Grade 10 (Secondary 4)/中學十年級(中四)
2 邓云键 Yunjian Deng Male/男性 Grade 11 (Secondary 5)/中學十一年級(中五)
3 梁与 Yu Liang Male/男性 Grade 10 (Secondary 4)/中學十年級(中四)
4 曾炫玮 Zeng Xuanwei Male/男性 Grade 10 (Secondary 4)/中學十年級(中四)
Full name of responsible teacher/負責老師全名
闫灵麟/李忠伟
Mobile phone number of teacher/手提電話
13590570069(闫灵麟)/13202957315(李忠伟)
Email address of teacher /電郵地址
Email hidden; Javascript is required.
Project Information / 作品信息
Project Title/參賽作品名
运用pyTorch深度学习模型的树种识别平台
Use of Tool/運用工具
Generative AI Tools
Expected Stream/參賽組別
Stream 1: Identifying an educational problem and proposing a solution.
1) Please put forward a problem encountered in daily life related to School, Family, Community or Subject-learning, and clearly describe and explain how problems or needs affect life or learning. (No more than 200 words)/請提出一個日常生活遇到的與學校、家庭、社會或學科學習相關的問題,並清楚描述及解釋這問題或需要如何影響生活或學習。(不多於 200 字)

中学生普遍缺乏对植物的基本认知,校园常见绿植如桂花、玉兰常被误认,家庭阳台绿化多停留在观赏层面,社区植物标识系统缺失。这种"自然盲区"导致学生难以将生物课本知识与现实联结,例如分不清单子叶与双子叶植物特征,更遑论理解生态循环。长期脱离自然观察,不仅削弱科学探究能力,更使青少年错失通过植物认知培育生命责任感的机会,间接影响未来环境保护意识的形成。

2) Please describe the solution and how to use Artificial Intelligence, computational thinking and computer programming technology. (No more than 200 words)/請描述解決方案及當中如何使用人工智能、運算思維及電腦編程技術。(不多於 200 字)

该方案使用 PyTorch 实现图像分类,通过torchvision加载预训练的 ResNet18 模型,对模型最后一层进行微调以适配自定义数据集。数据增强提升模型泛化能力,交叉熵损失函数和 Adam 优化器训练模型,训练完成后保存模型参数。运用人工智能的迁移学习,通过计算思维将问题拆解为数据处理、模型构建与训练,以 Python 和 PyTorch 编程实现图像分类任务

3)Please explain why the proposed solution is the best solution. (No more than 200 words)/請解釋為何提議的解決方案是最好的方案。(不多於 200 字)

该解决方案具有显著优势:在技术选型上,借助 PyTorch 框架与 torchvision 库,充分利用 ResNet18 预训练模型的迁移学习能力,大幅减少训练时间与计算资源消耗;数据处理方面,精心设计的增强策略有效提升数据多样性,增强模型泛化性;训练环节采用 Adam 优化器与交叉熵损失函数,确保优化高效且收敛稳定;参数设置合理平衡训练速度与精度。整体代码结构清晰,兼具实用性与扩展性,能够快速落地并适应不同场景需求,是兼具高效性与可靠性的优质解决方案

Do you have additional materials to upload?/你有補充资料要上傳嗎?
No
PIC
Personal Information Collection Statement (PICS)/收集個人資料聲明:
1. The personal data collected in this form will be used for activity-organizing, record keeping and reporting only. The collected personal data will be purged within 6 years after the event.
2. Please note that it is obligatory to provide the personal data required.
3. Your personal data collected will be kept by the LTTC and will not be transferred to outside parties.
4. You have the right to request access to and correction of information held by us about you. If you wish to access or correct your personal data, please contact our staff at lttc@eduhk.hk.
5. The University’s Privacy Policy Statement can be access at https://www.eduhk.hk/en/privacy-policy.
Agreement
  • I have read and agree to the competition rules and privacy policy/我已閱讀並同意比賽規則和隱私權政策。