Join us for Code @ Think 2019 | San Francisco | February 12 – 15 Register now Limited availability
A collection of free, open-source deep learning models.
Recognize and extract faces in an image and complete the corrupted portions.
Dec 12, 2018
Image Caption Generator
Deploy a deep learning-powered ‘Magic cropping tool’
Detect humans in an image and estimate the pose for each person.
Oct 31, 2018
Locate and tag named entities in text.
Oct 25, 2018
Artificial IntelligenceData Science+
Use an open source image segmentation deep learning model to detect different types of objects from within submitted images, then interact with them in a drag-and-drop web application interface to combine them or create new images.
Sep 21, 2018
Artificial IntelligenceDeep Learning+
Classify sporting activities in videos.
Predict hourly weather features given historical data for a specific location
Generates word embedding vectors from text files.
Artificial IntelligenceIBM Developer Model Asset Exchange+
Protect communications with adversarial neural cryptography.
Recognize faces in an image and extract embedding vectors for each face.
Artificial IntelligenceAudio Classification+
Identify sounds in short audio clips.
Generate a new image that mixes the content of a source image with the style of another image.
Artificial IntelligenceAudio Feature Extraction+
Generate embedding vectors from audio files.
Adds color to black and white images.
Artificial IntelligenceAudio Modeling+
Generate short audio clips of speech commands and lo-fi instrumental samples.
Identify objects in an image, additionally assigning each pixel of the image to a particular object.
Detect whether a mitosis exists in an image of breast cancer tumor cells.
Identify objects in images using a third-generation deep residual network.
Recognize faces in an image and estimate the age of each face.
Generate names based on a dataset of existing baby names.
Generate captions that describe the contents of images.
Generate English-language text similar to the news articles in the One Billion Words data set.
Localize and identify multiple objects in a single image.
Identify objects in images using a first-generation deep residual network.
Generate English-language text similar to the text in the YelpB. review data set.
Classify images according to the place/location labels in the Places365 data set.
Train a neural network component that can add spatial transformations such as translation and rotation to larger models.
Sep 20, 2018
Use an open source age estimation deep learning model to detect faces and estimate their age in a web application.
Sep 05, 2018
Use an open source object detector deep learning model to display and filter objects recognized in an image in a web application.
Jul 13, 2018
Train a deep learning model to classify audio embeddings on Watson Machine Learning and perform inference/evaluation with Watson Studio.
Jul 12, 2018
Use an open source image caption generator deep learning model to filter images based on their content in a web application.
Back to top