Teach machines to see. From convolutional networks to vision transformers and diffusion models, with the Stanford course that defined the field and practical alternatives.
Sorted cheapest first. Click a column header to re-sort. Developers with deep learning basics.
| Course | Level | Duration | Price | Certificate | |
|---|---|---|---|---|---|
Kaggle |
intermediate | ~4 hours (6 lessons) | Free | Yes | Visit |
Stanford University |
advanced | 10 weeks (one quarter) | Free | No | Visit |
DeepLearning.AI · Coursera |
intermediate | 2 weeks at 10 hrs/week (~14 hours) | Free to audit Free to audit · $49/mo |
Yes | Visit |
IBM · Coursera |
intermediate | 2 weeks at 10 hrs/week (~24 hours) | Free to audit Free to audit · $49/mo |
Yes | Visit |
Udacity |
advanced | ~37 hours (about 2 months part-time) | Paid $249/mo |
Yes | Visit |
No payment required. Several of these are complete university courses.
Build an image classifier with convolutional networks and transfer learning in Keras, with notebooks you run in the browser. A compact starting point for Kaggle users who want to enter their first vision competition.
The definitive computer vision deep learning course, with public notes and assignments on CNNs, training tricks, detection, segmentation, generative models, and vision transformers. Self-study it when you want to build vision systems from scratch rather than only call APIs.
Watch everything free; pay only if you want graded assignments and a credential.
Implements object detection, image segmentation, and model interpretability (class activation maps, saliency) in TensorFlow. For TensorFlow users who already know CNN basics and want to ship detection and segmentation models.
Covers image basics, OpenCV and Pillow processing, classical classifiers, CNNs, and object detection, ending with a deployed web app project. Suited to developers who want applied vision skills without the graduate-level math of CS231n.
Structured programs with instructors, cohorts, projects or formal credentials.
Three reviewed projects (facial keypoint detection, image captioning, landmark detection and SLAM) teach CNNs, RNN-CNN hybrids, and localization in PyTorch. Good for learners who want graded portfolio projects in applied vision and robotics perception.
Transformers, large language models, fine-tuning, and building with foundation models.