sapdo Goto Github PK

abandoned-object-detection

Detection of abandoned objects in a video frame

abandoned_object_detection_yolo4

TensorRT YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet

adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

ai-privacy-toolkit

A toolkit for tools and techniques related to the privacy and compliance of AI models.

aif360

A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

air-pollution-image-dataset-from-india-and-nepal

Air Pollution Image Dataset from India and Nepal

aix360

Interpretability and explainability of data and machine learning models

arcgis-python-api

Documentation and samples for ArcGIS API for Python

cliff_summ

Code for EMNLP 2021 paper "CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization"

communication-cost-consensus

Simulations from the paper "Communication cost of consensus for nodes with limited memory"

d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 400 universities from 60 countries including Stanford, MIT, Harvard, and Cambridge.

deeptables

DeepTables: Deep-learning Toolkit for Tabular data

distributed-k-means-communication-cost

This is a python implementation of "Distributed k-Means and k-Median Clustering on General Topologies" by Maria Florina Balcan et al. (http://www.cs.cmu.edu/~ninamf/papers/distr_clust.pdf) || • The concept of coreset was used for efficient k-means clustering of data in distributed settings. • With reduction in communication cost, the k-means cost obtained (using coresets) was as low as the one obtained by running Lloyd’s algorithm on the global dataset. ||

diversenmt

Source code for the AAAI 2020 long paper <Modeling Fluency and Faithfulness for Diverse Neural Machine Translation>.

dynamask

This repository contains the implementation of Dynamask, a method to identify the features that are salient for a model to issue its prediction when the data is represented in terms of time series. For more details on the theoretical side, please read our ICML 2021 paper: 'Explaining Time Series Predictions with Dynamic Masks'.

explainer

The official repository containing the source code to the explAIner publication.

federatedal

Federated Adversrial Learning/ Training Framework. A testing ground for conducting relevant research.

fedml

A Research-Industry integrated Federated Learning Library, backed by FedML, Inc (https://FedML.ai). Supporting distributed computing, mobile/IoT on-device training, and standalone simulation. Best Paper Award at NeurIPS 2020 Federated Learning workshop. Join our Slack Community:(https://join.slack.com/t/fedml/shared_invite/zt-havwx1ee-a1xfOUrATNfc9DFqU~r34w)

fedpso

FedPSO: Federated Learning Using Particle Swarm Optimization to Reduce Communication Costs

flam

ipmi2019-attnmel

IPMI2019 paper - Melanoma Recognition via Visual Attention

kserve

Serverless Inferencing on Kubernetes

kubeflow-examples

A repository to host extended examples and tutorials

lime

Lime: Explaining the predictions of any machine learning classifier

mace

Model Agnostic Concept based Explanations

metagraspnet

MetaGraspNet: a large-scale benchmark dataset for vision-driven robotic grasping via physics-based metaverse synthesis -100,000 images across 5 difficulty levels

mnist-data

Creating a model to identify MNIST data using fastai and google colab

mnist-federated

Experiments on MNIST dataset and federated training using Flower framework

pe-pm2.5

PM2.5 estimation paper

pytorch-grad-cam

Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Examples for classification, object detection, segmentation, embedding networks and more. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM