Learn more >
A place for developers to find and use free and open source deep learning models.
Deploy model-serving microservices from the Model Asset Exchange on Red Hat OpenShift.
Aug 16, 2019
Artificial intelligenceData science+
Facial Age Estimator
Use your arms to make music
Image Caption Generator
Learning Path: An introduction to the Model Asset Exchange
See all events
Nov 01, 2018
See all announcements
Aug 05, 2019
Artificial intelligenceDeep learning+
Take a look at new MAX models for natural language processing tasks and new pens on CodePen.
Jul 09, 2019
Generate a summarized description of a body of text
Jun 18, 2019
Take a look at how the Model Asset eXchange works.
Jun 04, 2019
Detect 6 types of toxicity in user comments
May 28, 2019
Estimate the phonetic distance between Chinese words and get similar sounding candidate words.
May 22, 2019
Deploy deep learning models from the Model Asset Exchange to production with IBM Cloud and Kubernetes.
May 20, 2019
Use an open source age estimation deep learning model to detect faces and estimate their age in a web application.
Apr 22, 2019
Create your own music based on your arm movements in front of a webcam.
Apr 17, 2019
Explore a visual tracking-based annotation method for video streaming.
Mar 29, 2019
Upscale an image by a factor of 4, while generating photo-realistic details.
Detect the sentiment captured in short pieces of text
Mar 28, 2019
Artificial intelligenceMAX - Model Asset eXchange
Use a free, open-source deep learning model to detect different types of objects in an image, then interact with them in a drag-and-drop web application.
Process image, video, audio, or text data using deep learning models from the Model Asset Exchange in Node-RED flows.
IoTMAX - Model Asset eXchange+
Learn how to create a customized node for a RESTful deep learning microservice, providing access to that service's API in your Node-RED flows.
Learn about a new batch of models, encompassing audio, natural language processing, and image recognition.
Identify nuclei in a microscopy image and assign each pixel of the image to a particular nucleus
Use an open source image caption generator deep learning model to filter images based on their content in a web application.
Use an open source object detector deep learning model to display and filter objects recognized in an image in a web application.
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.
Mar 27, 2019
Artificial intelligenceAudio Modeling+
Converts spoken words into text form.
Mar 18, 2019
The Model Asset Exchange is place for developers to find and use free and open source deep learning models. Complete this learning path to explore the model zoo and learn how to consume these models in a web application or Node-RED flow.
Mar 15, 2019
Predict the emotional state of people in an image from their facial expressions
Jan 22, 2019
Learn how MAX is a place for developers to find and use free, open source, state-of-the-art deep learning models for common application domains, such as text, image, audio, and video processing.
Jan 02, 2019
Deploy deep learning models as a microservice and consume them in your applications or services.
Dec 12, 2018
Detect and extract faces in an image and complete the corrupted portions.
Detect humans in an image and estimate the pose for each person.
Apache SparkArtificial intelligence+
The past, present, and future of open source and AI at IBM.
Oct 31, 2018
Locate and tag named entities in text.
Sep 21, 2018
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.
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.
Detect 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 Yelp® 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.
Classify sporting activities in videos.
Predict hourly weather features given historical data for a specific location
Generates word embedding vectors from text files.
Protect communications with adversarial neural cryptography.
Artificial intelligenceAudio Classification+
Identify sounds in short audio clips.
Back to top