Deep Learning Specialization: Convolutional Neural Networks: study plan and how long it takes
The DeepLearningAI playlist is 42 videos and 6.0 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.
42 videos · 6.0 hours · DeepLearningAI
Course 4 of the Deep Learning Specialization covers computer vision: convolutions, padding and strides, pooling, classic architectures (LeNet, AlexNet, VGG), ResNets and Inception, data augmentation, object detection with YOLO and anchor boxes, face recognition with one-shot learning, and neural style transfer.
The videos are short and follow the course's four-week structure.
Who it's for: Learners who know neural network basics and want to understand CNNs and computer vision.
How long does it take?
The full playlist is 6.0 hours across 42 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 | 13 days | 9 days | 7 days |
| 1 h a day | 7 days | 5 days | 4 days |
| 2 h a day | 4 days | 3 days | 2 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 30 minutes 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 1–17 · 2h 46m
Day 1 · 25m
- 1C4W1L01 Computer Vision6m
- 2C4W1L02 Edge Detection Examples12m
- 3C4W1L03 More Edge Detection8m
Day 2 · 30m
- 4C4W1L04 Padding10m
- 5C4W1L05 Strided Convolutions9m
- 6C4W1L06 Convolutions Over Volumes11m
Day 3 · 25m
- 7C4W1L07 One Layer of a Convolutional Net16m
- 8C4W1L08 Simple Convolutional Network Example9m
Day 4 · 22m
- 9C4W1L09 Pooling Layers11m
- 10C4W1L10 CNN Example12m
Day 5 · 13m
- 11C4W1L11 Why Convolutions10m
- 12C4W2L01 Why look at case studies?3m
Day 6 · 25m
- 13C4W2L02 Classic Network18m
- 14C4W2L03 Resnets7m
Day 7 · 26m
- 15C4W2L04 Why ResNets Work9m
- 16C4W2L05 Network In Network7m
- 17C4W2L06 Inception Network Motivation10m
Week 2Videos 18–40 · 2h 49m
Day 8 · 23m
- 18C4W2L07 Inception Network9m
- 19C4W2L08 Using Open Source Implementation5m
- 20C4W2L09 Transfer Learning9m
Day 9 · 22m
- 21C4W2L10 Data Augmentation10m
- 22C4W2L11 State of Computer Vision13m
Day 10 · 24m
- 23C4W3L01 Object Localization12m
- 24C4W3L02 Landmark Detection6m
- 25C4W3L03 Object Detection6m
Day 11 · 24m
- 26C4W3L04 Convolutional Implementation Sliding Windows11m
- 27C4W3L06 Intersection Over Union4m
- 28C4W3L07 Nonmax Suppression8m
Day 12 · 28m
- 29C4W3L08 Anchor Boxes10m
- 30C4W3L09 YOLO Algorithm7m
- 31C4W3L10 Region Proposals6m
- 32C4W4L01 What is face recognition5m
Day 13 · 25m
- 33C4W4L02 One Shot Learning5m
- 34C4W4L03 Siamese Network5m
- 35C4W4L04 Triplet loss16m
Day 14 · 24m
- 36C4W4L05 Face Verification6m
- 37C4W4L06 What is neural style transfer?2m
- 38C4W4L07 What are deep CNs learning?8m
- 39C4W4L08 Cost Function4m
- 40C4W4L09 Content Cost Function4m
Week 3Videos 41–42 · 26m
Day 15 · 26m
- 41C4W4L10 Style Cost Function17m
- 42C4W4L11 1D and 3D Generalizations9m
Tips for finishing
- Compute output sizes for each convolution example by hand; it's the most common source of bugs in real CNN code.
- For more depth, follow it with Stanford CS231N.