dividiti

ck-caffe

Collective Knowledge workflow for Caffe to automate installation across diverse platforms and to collaboratively evaluate and optimize Caffe-based workloads across diverse hardware, software and data sets (compilers, libraries, tools, models, inputs):

ck-request-asplos18-mobilenets-armcl-opencl

CK workflow, portable packages and other artifacts for the ReQuEST-ASPLOS'18 submission:

ck-zeromq

CK repository for experiments with ZeroMQ, LoadGen and TensorRT

ck-mlperf

Collective Knowledge repository to automate MLPerf - a broad ML benchmark suite for measuring performance of ML software frameworks, ML hardware accelerators, and ML cloud platforms:

ck-tensorflow

Collective Knowledge components for TensorFlow (code, data sets, models, packages, workflows):

inference

Reference implementations of inference benchmarks

inference_results_v0.5

MLPerf Inference v0.5 Results

inference_results_v0.7

ck

Collective Knowledge (CK) is a small Python library that helps to decompose complex research projects into reusable and cross-linked components (wrappers for code, data, models and results), automation actions and portable workflows with unified APIs, CLI, and JSON I/O. You can find more info and real-world use cases at the project website:

ck-analytics

Collective Knowledge repository with actions to unify the access to different predictive analytics engines (scipy, R, DNN) from software, command line and web-services via CK JSON API:

ck-armnn

Collective Knowledge workflows for ArmNN

ck-autotuning

CK automation actions to let users implement portable, customizable and reusable program workflows for reproducible, collaborative and multi-objective benchmarking, optimization and SW/HW co-design:

ck-coral

Collective Knowledge workflows for the Coral EdgeTPU accelerator

ck-crowdtuning

Collective Knowledge crowd-tuning extension to let users crowdsource their experiments (using portable Collective Knowledge workflows) such as performance benchmarking, auto tuning and machine learning across diverse platforms with Linux, Windows, MacOS and Android provided by volunteers. Demo of DNN crowd-benchmarking and crowd-tuning:

ck-ehive

CK workflows for the eHive project

ck-env

CK repository with components and automation actions to enable portable workflows across diverse platforms including Linux, Windows, MacOS and Android. It includes software detection plugins and meta packages (code, data sets, models, scripts, etc) with the possibility of multiple versions to co-exist in a user or system environment:

ck-graph-analytics

Collective Knowledge repository with workflows and packages for graph analytics applications

ck-math

Collective Knowledge packages for various mathematical libs to be plugged into portable and customizable CK research workflows:

ck-nntest

CK-NNTest: collaboratively validating, benchmarking and optimizing neural net operators across platforms, frameworks and datasets

ck-object-detection

CK research workflows for object detection

ck-old-packages

Collective Knowledge repository to archive outdated packages

ck-openvino

Collective Knowledge workflows for OpenVINO Toolkit (Deep Learning Deployment Toolkit)

ck-pytorch

Integration of PyTorch to Collective Knowledge workflow framework to provide unified CK JSON API for AI (customized builds across diverse libraries and hardware, unified AI API, collaborative experiments, performance optimization and model/data set tuning):

ck-quantum

Miscellaneous resources for Quantum Collective Knowledge

ck-tensorrt

Collective Knowledge repository for NVIDIA's TensorRT

ck-web

Collective Knowledge web extension to browse CK repositories, visualize interactive graphs and articles, render CK-based websites, implement simple web services with JSON API (for example to crowdsource experiments or unify access to DNN). Demos of interactive articles, graphs and crowdsourced experiments:

ck-website

CK repository for cKnowledge.org website:

ctuning-programs

Collective Knowledge extension with unified and customizable benchmarks (with extensible JSON meta information) to be easily integrated with customizable and portable Collective Knowledge workflows. You can easily compile and run these benchmarks using different compilers, environments, hardware and OS (Linux, MacOS, Windows, Android). More info:

inference_policies

Please use for issues related to inference policies, including suggested changes

policies

General policies