2d1ff1cult Goto Github PK

bulkhead-shockload

Code translated from FORTRAN66 to C to calculate parachute shock loads. For use with UNLV SEDS' Spaceport America Cup 10K COTS rocket.

cosernn

Code for the paper "Contextual and Sequential User Embeddings for Large-Scale Music Recommendation".

ddbot

Discord Drake Bot - an attempt at using RNNs and LSTMs for rapping bots

deletelater

gamarker

A simple gyro/accel marker intended for classroom use

hacking-books

hpr-rocket-avionics

Code for data acquisition electronics on a Tripoli Level 1 High Power Rocket (HPR)

hungabunga

HungaBunga: Brute-Force all sklearn models with all parameters using .fit .predict!

meshconvolution

Code for Mesh Convolution Using a Learned Kernel Basis

opencv

Open Source Computer Vision Library

pml-book

"Probabilistic Machine Learning" - a book series by Kevin Murphy

rocketcea

RocketCEA Wraps The NASA Fortran CEA Code

unlv_seds_spark2

vcmeshconv

Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to capture fine-grained deformations. Furthermore, these methods can only be applied to a template-specific surface mesh, and is not applicable to more general meshes, like tetrahedrons and non-manifold meshes. While more general graph convolution methods can be employed, they lack performance in reconstruction precision and require higher memory usage. In this paper, we propose a non-template-specific fully convolutional mesh autoencoder for arbitrary registered mesh data. It is enabled by our novel convolution and (un)pooling operators learned with globally shared weights and locally varying coefficients which can efficiently capture the spatially varying contents presented by irregular mesh connections. Our model outperforms state-of-the-art methods on reconstruction accuracy. In addition, the latent codes of our network are fully localized thanks to the fully convolutional structure, and thus have much higher interpolation capability than many traditional 3D mesh generation models.