evcu Goto Github PK

awesome-pruning

A curated list of neural network pruning resources.

bigdata2017

circuitpython_projects

Some qController programming

crypto2017fall

cuda-sudoku-solver

cv2016

Homeworks for Computer Vision Class given by Rob Fergus in 2016 Fall

ds1004

evcu.github.io

exp.bootstrp

This repo is a bootstrap for experiments and includes helper functions scripts for pytorch training and slurm job scheduler.

feds

FEDS for Facial Expression Detection System

fml-fa16-project

hpc2017

kmeans-openmpi

Open-mpi implementation of K-means.

lists

Some lists for good

meta-dataset

metaoptnet

Meta-Learning with Differentiable Convex Optimization (CVPR 2019 Oral)

micrograd

A tiny autograd engine and a neural net library on top of it, potentially for educational purposes

nalwe

Results of various trained w2v models.

nn

numpy_autograd

a simple implementation of autograd engine

playground

Play with neural networks!

propertycrawler

Property Advert Crawler

pyprobml

Python code for "Machine learning: a probabilistic perspective" (2nd edition)

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorchpruner

rigl

End-to-end training of sparse deep neural networks with little-to-no performance loss.

short-distance-stepping

Short distance human stepping includes a lot of variants. Stance type, stepping length, location, turning side, step type are some of these variants which make short distance human stepping hard to model. Prototyping and understanding short distance human stepping is quite important for virtual prototyping human locomotion. The solution to tackle this problem should be accurate and fast. In the experiment made by Mr. Pisupati, marker data is converted into 2-D body and feet trajectories.

sparse-building-blocks-dnns

Comparison of sparse vs. dense matrix encodings for pruned fully connected and convolutional neural network layers on a GPU