CS231n 2025——作业参考与学习笔记导航页
最近我完成了 2025 年春季 Stanford CS231n — Deep Learning for Computer Vision 的课程作业并撰写了全章节的学习笔记。下面整理了这些笔记的链接，方便各位朋友访问。
已完成的作业代码已放置在 github 仓库: https://github.com/Kang-Jay/CS231n-2025。
笔记链接
| Assignment | Chapter | Topic | Notes |
|---|---|---|---|
| Assignment1 | 1-1 | kNN | https://blog.csdn.net/x2114754480/article/details/149572662 |
| 1-2 | Softmax | https://blog.csdn.net/x2114754480/article/details/149689949 | |
| 1-3 | Two-Layer Neural Network | https://blog.csdn.net/x2114754480/article/details/149866392 | |
| 1-4 | Image Features | https://blog.csdn.net/x2114754480/article/details/152214887 | |
| 1-5 | Fully-Connected Neural Network | https://blog.csdn.net/x2114754480/article/details/149941584 | |
| Assignment2 | 2-1 | Batch Normalization | https://blog.csdn.net/x2114754480/article/details/150061156 |
| 2-2 | Dropout | https://blog.csdn.net/x2114754480/article/details/150119299 | |
| 2-3 | CNN | https://blog.csdn.net/x2114754480/article/details/150401794 | |
| 2-4 | PyTorch on CIFAR-10 | https://blog.csdn.net/x2114754480/article/details/150459008 | |
| 2-5 | Image Captioning with Vanilla RNNs | https://blog.csdn.net/x2114754480/article/details/150938350 | |
| Assignment3 | 3-1 | Image Captioning with Transformers | https://blog.csdn.net/x2114754480/article/details/151654125 |
| 3-2 | Self-Supervised Learning | https://blog.csdn.net/x2114754480/article/details/151694699 | |
| 3-3 | DDPM | https://blog.csdn.net/x2114754480/article/details/151864627 | |
| 3-4 | CLIP and DINO | https://blog.csdn.net/x2114754480/article/details/151946399 |
课程资源
课程官网: Stanford University CS231n: Deep Learning for Computer Vision
作业介绍: CS231n Assignments
作业源码下载链接:
- Assignment1: https://cs231n.github.io/assignments/2025/assignment1_colab.zip
- Assignment2: https://cs231n.github.io/assignments/2025/assignment2_colab.zip
- Assignment3: https://www.mediafire.com/file/az17sl7q7eroxi2/assignment3.zip/file
课程 PPT: https://cs231n.stanford.edu/schedule.html
2025 课程视频:
- Bilibili: https://www.bilibili.com/video/BV1b1agz5ERC
- Youtube: https://youtu.be/2fq9wYslV0A
你也可以在这里下载我个人整理的资源 (三次作业原始代码, 所有章节的 PPT, 以及笔记中的一些模型结构图): https://www.mediafire.com/file/1mhnbhu129o82vl/Resources.zip/file
说明：内容为个人整理与实现，难免有疏漏，还望各位读者包涵。欢迎通过 GitHub issues 或 CSDN 评论区讨论问题与改进。如需私下联系，可发邮件至 kang-jay@qq.com。