Computer Vision
Teach machines to see: CNNs, transfer learning, YOLO detection, segmentation, ViT, and CLIP.
Before this: Deep Learning.
-
1h 03m
Step 1Deep learning for vision
Stanford CS231n lecture 1: the field in one hour.
Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 1: IntroductionStanford Online
-
9 min
Step 2CNNs explained
Filters, feature maps, and pooling.
Convolutional Neural Networks (CNNs) explaineddeeplizard
-
22 min
Step 3Build a CNN in PyTorch
Train an image classifier from scratch.
PyTorch Tutorial 14 - Convolutional Neural Network (CNN)Patrick Loeber
-
1h 11m
Step 4CNN architectures
AlexNet to ResNet: what each one changed.
Stanford CS231N Deep Learning for Computer Vision | Spring 2025 | Lecture 6: CNN ArchitecturesStanford Online
-
15 min
Step 5Transfer learning
Reuse a pretrained network and train on a few hundred images.
PyTorch Tutorial 15 - Transfer LearningPatrick Loeber
huggingface/pytorch-image-models★ 37.3k -
3 min
Step 6Data augmentation
Get more out of small datasets for free.
Data Augmentation explaineddeeplizard
roboflow/notebooks★ 9.7k -
17 min
Step 7How YOLO works
Real-time object detection in one pass.
How YOLO Object Detection WorksDeepBean
-
21 min
Step 8Train YOLO on your own data
Label, train, and run a detector in Colab.
How to Train YOLO Object Detection Models in Google Colab (YOLO26, YOLO11, YOLOv8)Edje Electronics
ultralytics/ultralytics★ 63.6k -
11 min
Step 9U-Net segmentation
Classify every pixel, the architecture diffusion models also use.
The U-Net (actually) explained in 10 minutesrupert ai
-
13 min
Step 10Segment Anything
A foundation model that segments any object from a click.
Explaining the Segment Anything Model - Network architecture, Dataset, TrainingNeural Breakdown with AVB
facebookresearch/sam2★ 20.2k -
17 min
Step 11Vision transformers
Images as sequences of patches, with code.
Vision Transformer Quick Guide - Theory and Code in (almost) 15 minDeepFindr
-
18 min
Step 12CLIP
Connect images and text in one embedding space.
How AI 'Understands' Images (CLIP) - ComputerphileComputerphile
openai/CLIP★ 34.6k
Build it
Watching isn't learning. Pick one and put it on GitHub.
- Fine-tune a pretrained model on 5 classes of your own photos, 50 images each.
- Train a YOLO detector on a custom dataset and run it on a video from your phone.
- Build text-to-image search over 1,000 of your photos with CLIP embeddings.