Introduction to Machine Learning for the Arts

Title: StyleGan Particle System Project Video (UE Realtime Gameplay): StyleGan Latent Spacewalk Video from Runway: One sentence description: Niagara Particle system in Unreal Engine driven by StyleGan latent spacewalk Video.  Project summary:  My project is essentially a way to generate digital art with the help of StyleGan and machine learning algorithms. I am using the Niagara particle … Continue reading Final Project Documentation

Proposal Guidelines It’s up to you to determine how to best present your idea. Be prepared to present for a few minutes with visual aids. Show us your inspirations or make a prototype (even if it’s just on paper). At a minimum, prepare the following: Project Title: One sentence description: Can you summarize your idea … Continue reading Final Project Proposal

Model Training Collect your own image or text dataset and train a generative model in RunwayML. Render a latent walk video with the output (for images) or text output samples (for text): I tried to train my own StyleGan model for generative abstract artworks or distictive textures. The dataset I trained it with is 100 … Continue reading Assignment 9

DenseDepth The model is developed to predict depth from 2D images. Depth estimation from images is used for scene understanding and reconstruction. The model is able to achieve detailed high-resolution depth maps using an encoder and decoder to extract features from the pre-trained neural network.  The model is trained with the NYU Depth v2 and … Continue reading Assignment 8

Coding Exercise Doodle generation For this week’s assignment, I am just playing around with generating doodles with the sketchRNN model. Instead of using the mouse, the interaction I experimented with is using the webcam and the handpose model to draw parts of the doodles. I can’t think of a way to end the drawing and … Continue reading Assignment 7

Interactive Real-Time Gesture Data I’m a bit short on time this week due to midterms. I decided to continue working on my sketch from Assignment 4, which is training a handpose regression model. Basically, the idea is to control the R, G, and B color of the background with three-finger. Although I got it to … Continue reading Assignment 5

https://editor.p5js.org/hnc247/sketches/pEnrjusYC For this week’s assignment, I tweaked the handpose example we built in class into a regression model. I was inspired by the color pose regression tutorial and trained the output as a background color regression. I added two more inputs (coordinates of the middle finger), so each of the three fingers can control the corresponding … Continue reading Assignment 4

Model and Data Biography Reflection Maybe there should be a feature in which users could contribute images willingly, especially for data that are sensitive or difficult to collect. I would like to know the differences between the normal dataset and the larger commercial and research partner dataset. I’m curious about how powerful the full dataset … Continue reading Assignment 3: Model and Data Biography & PoseNet Model

Original Game: Unidentified Aerial Phenomenon Original game code: https://editor.p5js.org/hnc247/sketches/0jTM-VlBm Full-screen mode:https://editor.p5js.org/hnc247/full/0jTM-VlBm STG game (short for Shoot ’em up) The player controls the UFO with keypresses, left and right to change directions, up to move forward, and space bar to shoot lasers. The player needs to shoots out laser to shatter the obstacles coming from each direction. … Continue reading UFO Game + Teachable Machine

Explore ImageNet. What surprises you about this data set? What questions do you have? Thinking back to last week’s assignment, can you think of any ethical considerations around how this data was collected Are there privacy considerations with the data? I think the only way for ImageNet to make improvements in its accuracy is to … Continue reading Assignment 1B