AlessioQuercia

awesome-public-datasets

A topic-centric list of HQ open datasets.

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

codimd

CodiMD - Realtime collaborative markdown notes on all platforms.

SupContrast

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

line_profiler

Line-by-line profiling for Python

alphatensor

releasing-research-code

Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

GitHub-userscripts

Userscripts to add functionality to GitHub

involution

[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

mario-gpt

[Neurips 2023] Generating Mario Levels with GPT2. Code for the paper "MarioGPT: Open-Ended Text2Level Generation through Large Language Models" https://arxiv.org/abs/2302.05981

lovely-tensors

Tensors, for human consumption

focal_loss_pytorch

A PyTorch Implementation of Focal Loss.

class-balanced-loss

Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019

sam

genv

GPU environment and cluster management with LLM support

pytorch-classification-uncertainty

This repo contains a PyTorch implementation of the paper: "Evidential Deep Learning to Quantify Classification Uncertainty"

deepproblog

DeepProbLog is an extension of ProbLog that integrates Probabilistic Logic Programming with deep learning by introducing the neural predicate.

autograd-hacks

focal_calibration

Code for the paper "Calibrating Deep Neural Networks using Focal Loss"

powersgd

Practical low-rank gradient compression for distributed optimization: https://arxiv.org/abs/1905.13727

selection-via-proxy

entropy-sgd

Lua implementation of Entropy-SGD

sgd-influence

Python codes for influential instance estimation

lnl_sr

Learning with Noisy Labels via Sparse Regularization, ICCV2021

error-feedback-SGD

SGD with compressed gradients and error-feedback: https://arxiv.org/abs/1901.09847

lightning-diffusion_component

DIHCL

Curriculum Learning by Dynamic Instance Hardness (NeurIPS 2020)