aerinkim Goto Github PK

ab3dmot

Official Python Implementation for "3D Multi-Object Tracking: A Baseline and New Evaluation Metrics", IROS 2020, ECCVW 2020

ads-platform-tools

Tools and utilities for the Twitter Ads Platform in Python and Perl.

ams_pytorch

Pytorch code that shows ADAM can fail to converge to an optimal solution even in simple one-dimensional convex settings.

andrewng_ml_python

Assignments for Andrew Ng's Machine Learning course implemented in Python, according to https://github.com/mstampfer/Coursera-Stanford-ML-Python format

augmix

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

awesome-public-datasets

A topic-centric list of high-quality open datasets in public domains. By everyone, for everyone!

chatbot-ui

An open source ChatGPT UI.

cleanlab

Find label errors in datasets, weak supervision, and learning with noisy labels.

cs224d

cse544

UW CSEP544: Database Management Systems

data-validation

Library for exploring and validating machine learning data

dl_implementation_note

evals

Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

facedetect

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

fathom

Reference workloads for modern deep learning methods.

fitzpatrick17k

flexgen

Running large language models like GPT-3/OPT-175B on a single GPU. Up to 100x faster than other offloading systems.

glove

GloVe model for distributed word representation

glove_pretrain

Steps to load pre-trained glove vector on GloVe.c file.

gym

A toolkit for developing and comparing reinforcement learning algorithms.

learning_to_execute

Learning to Execute

lidar-bonnetal

Semantic and Instance Segmentation of LiDAR point clouds for autonomous driving

malmo

Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. We aim to inspire a new generation of research into challenging new problems presented by this unique environment. --- For installation instructions, scroll down to *Getting Started* below, or visit the project page for more information:

mediapipe

MediaPipe is the simplest way for researchers and developers to build world-class ML solutions and applications for mobile, edge, cloud and the web.

metaflow

Build and manage real-life data science projects with ease.

metal

Snorkel MeTaL: A framework for training models with multi-task weak supervision

minichain

A tiny library for coding with large language models.

mklpy

A package for Multiple Kernel Learning in Python