A collection of libraries to optimise AI model performances

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Web-based SQLite database browser written in Python

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation

HybridNets: End-to-End Perception Network

Repository containing the material required to reproduce the results of the paper "Vision-Based Fall Detection with Convolutional Neural Networks"

Local Powerpointer - A beautiful powerpoint generator which uses the power of local running large language models to generate the powerpoint slides.

Carla 0.9.15 and Autoware Universe Humble

Distilled coarse part of LoFTR adapted for compatibility with TensorRT and embedded divices

[ECCV 2022] An End-to-End Transformer Model for Crowd Localization

Efficient Deep Learning for Stereo Matching Tensorflow 2.x

[VietAI Reseach] Impliment Question Rewriting for Conversational Question Answering