facebookresearch,Meta Research,github

bitsandbytes

Library for 8-bit optimizers and quantization routines.

bo_pr

Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization

body2hands

A method to estimate 3D hand gestures from 3D body motion input in body languages.

bounding_data_reconstruction

Repo for the paper "Bounding Training Data Reconstruction in Private (Deep) Learning".

brica

Word-order biases in deep-agent emergent communication

c3dm

Code for Canonical 3D Deformable Mapping (C3DM) paper

c3dpo_nrsfm

C3DPO - Canonical 3D Pose Networks for Non-rigid Structure From Motion.

calibration_membership

Public implementation of the paper "On the Importance of Difficulty Calibration in Membership Inference Attacks".

canife

Crafting canaries to measure empirical privacy of DP-FL training under a realistic threat model.

carbonexplorer

Carbon Explorer helps evaluating solutions make datacenters operate on renewable energy.

cascade

Implementation of CASCADE in Learning General World Models in a Handful of Reward-Free Deployments (NeurIPS 22).

causalmotifs

Replication code for "Causal Network Motifs Identifying Heterogeneous Spillover Effects in A/B Tests", TheWebConf2021.

causalskilllearning

Codebase for project about unsupervised skill learning via variational inference and causality.

cc_net

Tools to download and cleanup Common Crawl data

ccqa

CCQA A New Web-Scale Question Answering Dataset for Model Pre-Training

The codes reproduce the figures and statistics in the paper, "Calibration of P-values for calibration and for deviation of a subpopulation from the full population," by Mark Tygert. The repo also provides the LaTeX and BibTeX sources required for replicating the paper.

certified-removal

Certified Removal from Machine Learning Models

clara

CLARA: Confidence of Labels and Raters

classifier-balancing

This repository contains code for the paper "Decoupling Representation and Classifier for Long-Tailed Recognition", published at ICLR 2020

classyvision

An end-to-end PyTorch framework for image and video classification

clevr-dataset-gen

A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

clevr-iep

Inferring and Executing Programs for Visual Reasoning

clinical-trial-parser

Library for converting clinical trial eligibility criteria to a machine-readable format.

clockwork

Recurring batch data pipelines are a staple of the modern enterprisescale data warehouse. As a data warehouse scales to support more products and services, a growing number of interdependent pipelines running at various cadences can give rise to periodic resource bottlenecks for a cluster. This resource contention results in pipelines starting at unpredictable times each day and consequently variable landing times for the data artifacts they produce. The variability gets compounded by the dependency structure of the workload, and the resulting unpredictability can disrupt the project workstreams which consume this data. We present Clockwork, a delay-based global scheduling framework for data pipelines which improves landing time stability by spreading out tasks throughout the day. Whereas most scheduling algorithms optimize for makespan or average job completion times, Clockwork’s execution plan optimizes for stability in task completion times while also targeting predifined pipeline. Online experiments comparing this novel scheduling algorithm and a previously proposed greedy procrastinating heurstic show tasks complete almost an hour earlier on average, while exhibiting lower landing time variance and producing significantly less competition for resources in a target cluster.

facebookresearch Goto Github PK

Meta Research's Projects

Recommend Projects

Recommend Topics

Recommend Org