Stars
FlagScale is a large model toolkit based on open-sourced projects.
Latex code for making neural networks diagrams
Flops counter for neural networks in pytorch framework
FilterForward: Scaling Video Analytics on Constrained Edge Nodes
Code for Membership Inference Attack against Machine Learning Models (in Oakland 2017)
pytorch implementation of Parametric Noise Injection for adversarial defense
PyTorch implementations of Generative Adversarial Networks.
DEEPSEC: A Uniform Platform for Security Analysis of Deep Learning Model
Ongoing research training transformer models at scale
PyTorch deep learning projects made easy.
Count the MACs / FLOPs of your PyTorch model.
This work combines differential privacy and multi-party computation protocol to achieve distributed machine learning.
This project's goal is to evaluate the privacy leakage of differentially private machine learning models.
Code for "Analyzing Federated Learning through an Adversarial Lens" https://arxiv.org/abs/1811.12470
autodp: A flexible and easy-to-use package for differential privacy
Differential Privacy Preservation in Deep Learning under Model Attacks
Prototype implementation of Prio, a system for the private computation of aggregate statistics.
PyTorch Tutorial for Deep Learning Researchers
和我一步步部署 kubernetes 集群
Sample code and build environments for MPC frameworks