Stars
Vector search engine inside Milvus, integrating FAISS, HNSW, DiskANN.
Residual Quantization with Implicit Neural Codebooks
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
SWIG is a software development tool that connects programs written in C and C++ with a variety of high-level programming languages.
C library to compute the Hamming weight of arrays
Official implementation of "Watermarking Images in Self-Supervised Latent-Spaces"
Open source implementation of "A Self-Supervised Descriptor for Image Copy Detection" (SSCD).
Lightweight CLI download accelerator
A library for end-to-end learning of embedding index and retrieval model
GGNN: State of the Art Graph-based GPU Nearest Neighbor Search
QuickerADC is an implementation of highly-efficient product quantizers leveraging SIMD shuffle instructions integrated into FAISS
This technique modifies image data so that any model trained on it will bear an identifiable mark.
A lightweight benchmark for approximate nearest neighbor search
Efficient similarity search and clustering for Ruby
Implementation of ip-nsw from Non-metric Similarity Graphs for Maximum Inner Product Search
To Index or Not to Index: Optimizing Exact Maximum Inner Product Search
This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423
Code for "MultiGrain: a unified image embedding for classes and instances"
Open source implementation of "Spreading Vectors for Similarity Search"
Deep Clustering for Unsupervised Learning of Visual Features
Navigating Spreading-out Graph For Approximate Nearest Neighbor Search
Tensors and Dynamic neural networks in Python with strong GPU acceleration
ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation
Presenting Low-shot Visual Recognition by Shrinking and Hallucinating Features