Stars
The AMLSim project is intended to provide a multi-agent based simulator that generates synthetic banking transaction data together with a set of known money laundering patterns - mainly for the pur…
Reinforcement Learning with Model Predictive Control
This repository stores the main codes for the DeepOPF projects.
These scripts explore galaxy/quasar/star classification from optical and infrared magnitudes using supervised machine learning.
A collection of resources and papers on Diffusion Models
Simulation of X-ray projections on GPU: benchmarking gVirtualXray with clinically realistic phantoms
An Empirical Framework for Domain Generalization In Clinical Settings
Implementations of Fourier Transform, Laplacian Pyramids, Edge Detection
Domain adaptation made easy. Fully featured, modular, and customizable.
Code for our NeurIPS 2019 *spotlight* "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"
Provable adversarial robustness at ImageNet scale
A fast re-implementation of CLEVER https://openreview.net/pdf?id=BkUHlMZ0b in PyTorch
[pip install medmnist] 18x Standardized Datasets for 2D and 3D Biomedical Image Classification
This repo contains a PyTorch implementation of the paper: "Evidential Deep Learning to Quantify Classification Uncertainty"
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Unofficial Pytorch implementation of the paper 'AutoAugment: Learning Augmentation Strategies From Data' experiment on CIFAR-10 with WideResNet 28-10
A PyTorch Library for Multi-Task Learning
The implementation of "End-to-End Multi-Task Learning with Attention" [CVPR 2019].
Latex code for making neural networks diagrams
Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch
A PyTorch port of the Neural 3D Mesh Renderer
Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow
A PyTorch implementation of EfficientNet