sunghyo

google-research

Google Research

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

dolly

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

PaLM-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

automl

Google Brain AutoML

Yet-Another-EfficientDet-Pytorch

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

zi2zi

Learning Chinese Character style with conditional GAN

python-coding-interview

A middle-to-high level open source algorithm book designed with coding interview at heart!

DB

A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".

uncertainty-toolbox

Uncertainty Toolbox: a Python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization

gen-efficientnet-pytorch

Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS

deep_gcns_torch

Pytorch Repo for DeepGCNs (ICCV'2019 Oral, TPAMI'2021), DeeperGCN (arXiv'2020) and GNN1000(ICML'2021): https://www.deepgcns.org

pytorch-normalizing-flows

Normalizing flows in PyTorch. Current intended use is education not production.

research-charnet

CharNet: Convolutional Character Networks

fair_self_supervision_benchmark

Scaling and Benchmarking Self-Supervised Visual Representation Learning

DCL

Destruction and Construction Learning for Fine-grained Image Recognition

Scene-Text-Detection

volto

React-based frontend for the Plone Content Management System

wsolevaluation

Evaluating Weakly Supervised Object Localization Methods Right (CVPR 2020)

meta-weight-net

NeurIPS'19: Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting (Pytorch implementation for noisy labels).

locating-objects-without-bboxes

PyTorch code for "Locating objects without bounding boxes" - Loss function and trained models

Seeing-Motion-in-the-Dark

Seeing Motion in the Dark. ICCV19

opencv_transforms_torchvision

opencv reimplement for transforms in torchvision

ganseeing

Seeing what a GAN cannot generate. Visualizes and quantifies object classes within scenes that are outside the range of a GAN.

neural-fonts

GAN을 활용한 한글 폰트 제작 프로젝트

r2d2

[ICLR'19] Meta-learning with differentiable closed-form solvers

astmt

Attentive Single-tasking of Multiple Tasks