ryanwongsa

docusaurus

Easy to maintain open source documentation websites.

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

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

fairseq

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

faiss

A library for efficient similarity search and clustering of dense vectors.

fastText

Library for fast text representation and classification.

fiftyone

The open-source tool for building high-quality datasets and computer vision models

PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

aim

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

nlpaug

Data augmentation for NLP

deit

Official DeiT repository

pytorch-openpose

pytorch implementation of openpose including Hand and Body Pose Estimation.

sam

SAM: Sharpness-Aware Minimization (PyTorch)

pytorch_scatter

PyTorch Extension Library of Optimized Scatter Operations

pytorch-seq2seq

An open source framework for seq2seq models in PyTorch.

bpemb

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

Neighborhood-Attention-Transformer

Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022

ml_collections

ML Collections is a library of Python Collections designed for ML use cases.

WLASL

WACV 2020 "Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison"

InterHand2.6M

Official PyTorch implementation of "InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image", ECCV 2020

textaugment

TextAugment: Text Augmentation Library

torch_videovision

Transforms for video datasets in pytorch

UniPose

We propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual seg- mentation and joint localization to estimate the human pose in a single stage, with high accuracy, without relying on statistical postprocessing methods. The Waterfall module in UniPose leverages the efficiency of progressive filter- ing in the cascade architecture, while maintaining multi- scale fields-of-view comparable to spatial pyramid config- urations. Additionally, our method is extended to UniPose- LSTM for multi-frame processing and achieves state-of-the- art results for temporal pose estimation in Video. Our re- sults on multiple datasets demonstrate that UniPose, with a ResNet backbone and Waterfall module, is a robust and efficient architecture for pose estimation obtaining state-of- the-art results in single person pose detection for both sin- gle images and videos.

attention_flow

py-denseflow

Extract TVL1 optical flows in python (multi-process && multi-server)

S3D

Release of the pretrained S3D Network in PyTorch (ECCV 2018)

Truncated-Loss

PyTorch implementation of the paper "Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels" in NIPS 2018

bsl1k

BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues, ECCV 2020

bi-tempered-loss-pytorch

Unofficial port to pytorch of parts of https://github.com/google/bi-tempered-loss

SOLOv2