Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms.

Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms.

Related Repos



DongfeiJi Distribute_Polynomial Distributed Training, Fitting y=2x+10 Introduce This is the simplest example of distributed tensorflow. The function is to estimate two parameters of the formula: Y = 2 * X + 10 The parameters ne
 

geekyutao A paper list of image inpainting
 

ConnorJL GPT2 Disclaimer: This is not the official GPT2 implementation! I've done my best to follow the specifications of the original GPT2 model as closely as possible, but be warned that I have not been able to replicate the full perfor
 

google-research Google Research Football This repository contains an RL environment based on open-source game Gameplay Football. It was created by the Google Brain team for research purposes. Useful links: (NEW!) GRF Tournament - take part
 

GoogleCloudPlatform Google Cloud AI Developer Relations This repository contains content produced by Google Cloud AI Developer Relations for machine learning and artificial intelligence. The content covers a wide spectrum from educational, traini
 

jhjacobsen Invertible Residual Networks Official Pytorch implementation of i-ResNets. i-ResNets define a family of fully invertible deep networks, built by constraining the Lipschitz constant of standard residual network blocks. Reference
 

dimenwarper List of resources for bayesian inference
 

bzhangGo Source code for "A Lightweight Recurrent Network for Sequence Modeling"