Specific instructions for running each application are included in a README inside each app folder. A description of each application follows:
Train a classifier on microphone audio recordings.
View a collection of audio samples organized via t-SNE on extracted audio features. Works both on a collection (folder) of individual files, or a single audio file which can is segmented by onsets or beats.
Train an image classifier on a webcam feed.
Train an image regression on a webcam feed.
(in progress) This app combines ConvnetRegressor and ConvnetClassifier into one app with an interface. This should eventually replace the former two.
View the activations of a trained convnet.
Similar to convnet classifier, but optimized toward classifying images of hand-drawings.
Train a model and do real time classification of face poses.
Perform facial gestures over time and classify them using Dynamic Time Warping.
Train a model and do real time regression of face poses.
Automatically scrape Go board position from online-go.com and make next move recommendations.
View a collection of images organized via t-SNE on extracted features from a convnet, where the feature extraction is done from a python script and the results are imported into the app.
The same as ImageTSNEViewer (above), but handles the feature extraction and t-SNE assignment internally, and optionally allows for assignment to grid.
Search for most similar images in an image collection, given a query image. Analyze it first, then save the results for real-time browsing.
Fast search and retrieval of similar images in a database to a query image, webcam feed, video, or screengrabber.
Fast search and retrieval of similar images in a database to multiple objects found in a query image, webcam feed, video, or screengrabber.
Boiled down example showing how to train a model and do real time regression with mouse position as the input.
Do real-time object detection from 9000 classes on a webcam feed, video, or screengrabber.