Kyle Sayers's repositories
ATAK_push_cots
Push Cursor on Target messages to TAK clients with attachments and other information
Competitive-Drawing
A game where players compete to draw differing prompts on a shared canvas, as scored by a computer vision model
GMMPytorch
Easy to read Pytorch implementation of same-family gaussian mixture models. Features separable parameter optimization and singularity mitigation
BinaryStringRL
Implementation and replication of results found in OpenAI's "Hindsight Experience Replay"
ScrambleGenerator
Generate word scrambles using GPT3.5. Scrambles minimize character entropy and maximize fun
distance-optimization
Given a list of points and target distances between them, this algorithm optimizes their positions with respect to MSE loss.
SketchGeneration
Probabilistic sequence generation of sketch drawings which builds on Google Brain's "A Neural Representation of Sketch Drawings"
AlgorithmsEricksonSolutions
My solutions to exercises in Algorithms by Jeff Erickson
cuda_playground
Testing with CUDA-accelerated programs
deepsparse
Sparsity-aware deep learning inference runtime for CPUs
GMMScratch
A from-scratch implementation of Gaussian Mixture Models
netron
Visualizer for neural network, deep learning and machine learning models
SketchCNN-AE
Train an autoencoder to encode partially drawn images from Google's Quickdraw Dataset. This autoencoder can then be used to bootstrap downstream tasks such as image classification or stroke generation.
stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
the-ultimate-tile-stitcher
Scape and Stitch tiles from map services and save as orthomap geotifs