Stars
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
Library for Meta-Recognition and Weibull based calibration of SVM data.
Code and data for the research paper "Towards Open Set Deep Networks" A Bendale, T Boult, CVPR 2016
An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization
Kapok: Python Library for PolInSAR Forest Height Estimation Using UAVSAR Data
Prepare 30m resolution tree-height map for Nilgiri Bioshphere Reserve using Google Earth Engine. Uses GEDI, Landsat-8, ALOS-PALSAR, Sentinel-1 data products.
implementation of several GANs with pytorch
A game theoretic approach to explain the output of any machine learning model.
Interpreting DNNs, Relative attributing propagation
Library containing PyTorch implementations of various adversarial attacks and resources
Foolbox implementation for NeurIPS 2021 Paper: "Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints".
A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
砂糖代理(SGA)是用于游戏等自动化执行的脚本。目前可添加环行旅舍、原神、MAA、三月七助手和尘白禁区模块。更多详情可搜索B站账号 绘星痕,查看使用说明。
Concept Relevance Propagation for Localization Models, accepted at SAIAD workshop at CVPR 2023.
👾 Fast and simple video download library and CLI tool written in Go
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time
A modern download manager that supports all platforms. Built with Golang and Flutter.
JDet is an object detection benchmark based on Jittor. Mainly focus on aerial image object detection (oriented object detection).
Open source dataset; multimodal fusion;remote sensing;optical images; SAR images;deep learning
PyTorch implementation of adversarial attacks [torchattacks]
A PyTorch implementation of D-RISE