AbrahamYabo

google-research

Google Research

tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

detr

End-to-End Object Detection with Transformers

tushare

TuShare is a utility for crawling historical data of China stocks

deep-high-resolution-net.pytorch

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

data-augmentation-review

List of useful data augmentation resources. You will find here some not common techniques, libraries, links to GitHub repos, papers, and others.

lambda-networks

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

pyalgotrade-cn

pyalgotrade tailored for Chinese stock market

hand3d

Network estimating 3D Handpose from single color images

open-aff

code and trained models for "Attentional Feature Fusion"

I2L-MeshNet_RELEASE

Official PyTorch implementation of "I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image", ECCV 2020

Pose2Mesh_RELEASE

Official Pytorch implementation of "Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose", ECCV 2020

MonocularTotalCapture

Code for CVPR19 paper "Monocular Total Capture: Posing Face, Body and Hands in the Wild"

hand-graph-cnn

3D Hand Shape and Pose Estimation from a Single RGB Image

bort

Repository for the paper "Optimal Subarchitecture Extraction for BERT"

softmax-splatting

an implementation of softmax splatting for differentiable forward warping using PyTorch

epipolar-transformers

Epipolar Transformers (best paper award, CVPR 2020 workshop)

TDAN-VSR-CVPR-2020

TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution, CVPR 2020

opendr

stock-prediction

Stock price prediction with recurrent neural network. The data is from the Chinese stock.

Improved-Body-Parts

Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

3DHandShapePosefromRGB

3D Hand Shape and Pose Estimation from a Single RGB Image

3dhand

denseReg

3D hand pose estimation via dense regression

chinese-stock-api

Python API to get stock data in Chinese market

osmesa

OSMesa is an OpenStreetMap processing stack based on GeoTrellis and Apache Spark

chinese-stock-Financial-Index

计算**A股所有股票的3年平均财务指标

fusenet-hand-pose

Implementation of E. Kazakos, C. Nikou, I. A. Kakadiaris. On the Fusion of RGB and Depth Information for Hand Pose Estimation, ICIP, 2018.

fingerprint_liveness

Compares several different machine learning models and statistical features to predict the liveness of the fingerprint biometric.

FingerprintLivenessDetection-project