robertcsordas Goto Github PK

aicamera

Demonstration of using Caffe2 inside an Android application.

arch-efiboot

Boot EFISTUB linux kernels on UEFI systems not supporting kernel command line

babi-t2t

The bAbI question-answering dataset ported into T2T.

cifs_old

Compile old CIFS module as a kernel module in linux, becase new kernels CIFS is broken for our data server.

cluster_tool

cmt_bidder

Bidding distribution tool for Microsoft CMT

convnetjs-rldemo

Webserver-less RNN from karpathy's convnetjs

cpu_usage_per_user

Display CPU usage per user

ctlpp

Codebase for our EMNLP 2022 paper "CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations"

dnc

Experiments on Differentiable Neural Computer

dqn

Simple DQN implementation in pytorch

fblualib

Facebook libraries and utilities for Lua

firmware

The firmware of the Ultimate Hacking Keyboard

foomatic-filters-4.0.6-mac-os-11

Mac OS 11 patched version of foomatic-rip, needed for min12xxw

gaussian_process_test

home_size

Prints the size of home directories of all users on Linux

inceptionresnetv2test

Basic test for InceptionResnetV2 pretrained model

indexedpng

A library for loading palette indexed PNG images for Torch

kagglefish

Simple classifier for Kaggle fish classification challenge.

linear_layer_as_attention

The official repository for our paper "The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention".

linux-intel-undervolt-tool

Scripts for undervolting 6+th gen Intel i* CPUs and their internal GPU.

linux_gpu_switch

Easy to use script to turn Nvidia GPU on/off on Linux.

min12xxw-backup

Unofficial git repository for the min12xxw driver

mobilecg-ii

Open source ECG holter

modules

The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.

moe

Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"

moe_attention

Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"

moe_layer

sigma-MoE layer

moeut

molecule_gen

Implementation of "Learning Deep Generative Models"