Repository Index

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.

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

• asr
• speech
• speech-recognition
• speech-to-text

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

• deep-learning
• speech
• speech-recognition
• speech-to-text

Reinforcement Learning environments based on the 1993 game Doom :godmode:

• deep-learning
• reinforcement-learning
• python
• vizdoom

Little Ball of Fur - A graph sampling extension library for NetworKit and NetworkX (CIKM 2020)

• graph
• graph-sampling
• network-sampling
• random-walk

Image quality is an open source software library for Image Quality Assessment (IQA).

• artificial-intelligence
• machine-learning
• image-quality-assessment
• computer-vision

Seamless long-form MiniMax H3 video generation for ComfyUI with native AV latent continuity, chunked sampling, session resume, and Spectrum/Sage/Sol compatibility.

Arduino Text-to-Speech Library

• text-to-speech
• arduino
• tts
• speech

A Macau food recommendation Agent built on Thompson Sampling + StackedPareto weight fusion, with a full evaluation pipeline (5-fold CV, bootstrap CIs, stress tests) on 5,000 simulated users and 100k interactions. Competition entry for the QwenPaw AI Developer Challenge.

The repository host gives no description.

Semi-Supervised Learning with Ladder Networks in Keras. Get 98% test accuracy on MNIST with just 100 labeled examples !

An Elixir Evolutive Neural Network framework à la G.Sher

• elixir
• actuators
• sensor
• mutations

A curated dataset of malware and benign Windows executable samples for malware researchers

• machine-learning
• deep-learning
• malware-research
• malware-detection

The Text Mining Elixir

• text-mining
• text-analysis

A fast, simple, memory-efficient graph layout algorithm for visualizing networks in D3

• javascript
• d3js
• graph
• visualization

Dataset of packed PE samples

• dataset
• pe-files
• upx
• samples

Video game review datasets scraped from the Steam website (http://store.steampowered.com/). Data includes review text, number of hours that the reviewer played the game, number of friends, groups, etc.

This repository contains the official PyTorch implementation of GeoDA algorithm. GeoDA is a Black-box attack to generate adversarial example for image classifiers.

Implementation of "Adversarial Frontier Stitching for Remote Neural Network Watermarking" in TensorFlow.

• tensorflow
• tensorflow2
• watermarking
• neural-network

Reducing Bias in Modeling Real-world Password Strength via Deep Learning and Dynamic Dictionaries

Dataset of packed ELF samples

• samples
• dataset
• upx
• malware-analysis