Posted several new GitHub repos tonight - most of the recent materials are in repo format because the demos/activities are starting to get a little more complex than single Jupyter notebooks. You can find everything on the GitHub repos page via the nav bar above. Please reach out on Slack if you have any trouble running anything. Here is the new stuff:

  1. RNN demo/activity: gperdrizet/RNNs, intro to RNNs (learning the alphabet) and NLP/GRUs (Twitter sentiment analysis), activity prompts you to improve the twitter model by implementing a hybrid CNN/RNN model.

  2. YOLO26 activity: gperdrizet/YOLO26, simple Streamlit web app that does real-time object detection via your webcam. Activity prompts you to deploy the app for yourself and then extend its functionality.

  3. Mask detection capstone solution: gperdrizet/face-mask-detection - my incremental capstone 10 solution, includes lots of data augmentation and some more advanced training techniques, final test set accuracy 99.8%. Includes live deployment of Streamlit web app.

  4. CIFAR-10 project: gperdrizet/CIFAR10 - our in-house CNN and ResNet 50 are both hovering around 91% overall accuracy, still hoping to definitively beat ResNet over the weekend!