Udacity
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.
Developers with deep learning basics. This is an advanced course in Computer Vision, running about ~37 hours (about 2 months part-time).
$249/mo subscription (4-month bundle $212/mo). Udacity All Access subscription pricing seen 2026-11-01; estimated 37 hours of content.
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.
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.
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.