Ryan Wong's starred repositories
docusaurus
Easy to maintain open source documentation websites.
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
PyTorch-VAE
A Collection of Variational Autoencoders (VAE) in PyTorch.
pytorch-openpose
pytorch implementation of openpose including Hand and Body Pose Estimation.
pytorch_scatter
PyTorch Extension Library of Optimized Scatter Operations
pytorch-seq2seq
An open source framework for seq2seq models in PyTorch.
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.
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.
py-denseflow
Extract TVL1 optical flows in python (multi-process && multi-server)
Truncated-Loss
PyTorch implementation of the paper "Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels" in NIPS 2018
bi-tempered-loss-pytorch
Unofficial port to pytorch of parts of https://github.com/google/bi-tempered-loss