ALEXKIRNAS

fastapi

FastAPI framework, high performance, easy to learn, fast to code, ready for production

PaddleDetection

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

kornia

Geometric Computer Vision Library for Spatial AI

mmagic

OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.

DALI

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

sort

Simple, online, and realtime tracking of multiple objects in a video sequence.

face.evoLVe

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

Pytorch_Retinaface

Retinaface get 80.99% in widerface hard val using mobilenet0.25.

habitat-sim

A flexible, high-performance 3D simulator for Embodied AI research.

sedona

A cluster computing framework for processing large-scale geospatial data

optimus

:truck: Agile Data Preparation Workflows made easy with Pandas, Dask, cuDF, Dask-cuDF, Vaex and PySpark

DetectoRS

DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

ASL

Official Pytorch Implementation of: "Asymmetric Loss For Multi-Label Classification"(ICCV, 2021) paper

dist-keras

Distributed Deep Learning, with a focus on distributed training, using Keras and Apache Spark.

GFocal

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection, NeurIPS2020

L3C-PyTorch

PyTorch Implementation of the CVPR'19 Paper "Practical Full Resolution Learned Lossless Image Compression"

sparktorch

Train and run Pytorch models on Apache Spark.

FOST

FOST is a general forecasting tool, which demonstrate our experience and advanced technology in practical forecasting domains, including temporal, spatial-temporal and hierarchical forecasting. Current general forecasting tools (Gluon-TS by amazon, Prophet by facebook etc.) can not process and model structural graph data, especially in spatial domains, also those tools suffer from tradeoff between usability and accuracy. To address these challenges, we design and develop FOST and aims to empower engineers and data scientists to build high-accuracy and easy-usability forecasting tools.

eql.detectron2

The official implementation of Equalization Loss for Long-Tailed Object Recognition (CVPR 2020) based on Detectron2. https://arxiv.org/abs/2003.05176

autoalbument

AutoML for image augmentation. AutoAlbument uses the Faster AutoAugment algorithm to find optimal augmentation policies. Documentation - https://albumentations.ai/docs/autoalbument/

PuzzleMix

Official PyTorch implementation of "Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup" (ICML'20)

SnapMix

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data (AAAI 2021)

graftr

graftr: an interactive shell to view and edit PyTorch checkpoints.

Divide-and-Co-training

[TIP 2022] Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training. Plus, an image classification toolbox includes ResNet, Wide-ResNet, ResNeXt, ResNeSt, ResNeXSt, SENet, Shake-Shake, DenseNet, PyramidNet, and EfficientNet.

SpaceNet_SAR_Buildings_Solutions

The winning solutions for the SpaceNet 6 Challenge

xview2_solution

2nd place solution for Xview2 challenge https://xview2.org/

xView2-Solution

kaggle-telegram-notifier

Simple script that notifies you when Kaggle kernel submission completes using Telegram

python-mosaic

A simple tool to add mosaic effect to images

gym-taxi-v2-v3-solution

Solution for OpenAI Gym Taxi-v2 and Taxi-v3 using Sarsa Max and Expectation Sarsa + hyperparameter tuning with HyperOpt