Stanford CS231N: Deep Learning for Computer Vision: study plan and how long it takes
The Stanford Online playlist is 18 videos and 21.2 hours long. Here's how long it takes at different paces, a week-by-week schedule built from the real videos, and a planner that turns it into your own daily plan.
18 videos · 21.2 hours · Stanford Online
Stanford CS231N (2025) is the classic course on deep learning for computer vision. It covers image classification, loss functions and optimization, neural networks and backpropagation, CNNs and architectures, training techniques, and newer topics like transformers for vision, generative models and multimodal models.
Each lecture is around 70 minutes, and the assignments are on the course site.
Who it's for: Learners with Python, linear algebra and basic ML who want a deep understanding of computer vision models.
How long does it take?
The full playlist is 21.2 hours across 18 videos. Here's roughly how many days that is at different daily watch times and speeds, counting video time only:
| Daily time | At 1x | At 1.5x | At 2x |
|---|---|---|---|
| 30 min a day | 43 days | 29 days | 22 days |
| 1 h a day | 22 days | 15 days | 11 days |
| 2 h a day | 11 days | 8 days | 6 days |
Make your own schedule
The playlist link is already filled in. Press Plan, set how much time you have each day and your speed, and you'll get a day-by-day schedule with a finish date and a calendar file. It reads the live playlist, so new videos are included.
Week-by-week schedule
A sample plan at 1 hour a day and normal speed, using whole videos so none is split across days. That's 3 weeks in total. For a different pace, start date or speed, use the planner above.
Week 1Videos 1–7 · 8h 6m
Day 1 · 1h 3m
- 1Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 1: Introduction1h 3m
Day 2 · 1h 7m
- 2Stanford CS231N | Spring 2025 | Lecture 2: Image Classification with Linear Classifiers1h 7m
Day 3 · 1h 9m
- 3Stanford CS231N | Spring 2025 | Lecture 3: Regularization and Optimization1h 9m
Day 4 · 1h 17m
- 4Stanford CS231N | Spring 2025 | Lecture 4: Neural Networks and Backpropagation1h 17m
Day 5 · 1h 8m
- 5Stanford CS231N | Spring 2025 | Lecture 5: Image Classification with CNNs1h 8m
Day 6 · 1h 11m
- 6Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 6: CNN Architectures1h 11m
Day 7 · 1h 12m
- 7Stanford CS231N | Spring 2025 | Lecture 7: Recurrent Neural Networks1h 12m
Week 2Videos 8–14 · 8h 21m
Day 8 · 1h 7m
- 8Stanford CS231N | Spring 2025 | Lecture 8: Attention and Transformers1h 7m
Day 9 · 1h 14m
- 9Stanford CS231N | Spring 2025 | Lecture 9: Object Detection, Image Segmentation, Visualizing1h 14m
Day 10 · 1h 9m
- 10Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 10: Video Understanding1h 9m
Day 11 · 1h 13m
- 11Stanford CS231N | Spring 2025 | Lecture 11: Large Scale Distributed Training1h 13m
Day 12 · 1h 15m
- 12Stanford CS231N | Spring 2025 | Lecture 12: Self-Supervised Learning1h 15m
Day 13 · 1h 13m
- 13Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 13: Generative Models 11h 13m
Day 14 · 1h 12m
- 14Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 14: Generative Models 21h 12m
Week 3Videos 15–18 · 4h 46m
Day 15 · 1h 12m
- 15Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 15: 3D Vision1h 12m
Day 16 · 1h 10m
- 16Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 16: Vision and Language1h 10m
Day 17 · 1h 19m
- 17Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 17: Robot Learning1h 19m
Day 18 · 1h 5m
- 18Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 18: Human-Centered AI1h 5m
Tips for finishing
- Do the first assignment (k-NN, SVM, softmax and a two-layer network in NumPy). It's where most of the learning happens.
- Watch at 1.25x and pause on the slides; they're information-dense.