hoisee
Follow
Stars
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
A library for generating and evaluating synthetic tabular data for privacy, fairness and data augmentation.
This repository contains examples of fine-tuning Harmonized Landsat and Sentinel-2 (HLS) Prithvi foundation model.
Graph Neural Network Library for PyTorch
Code & Data for "Tabular Transformers for Modeling Multivariate Time Series" (ICASSP, 2021)
Synthetic data generators for tabular and time-series data
A comprehensive library for machine learning and numerical computing. Apply Machine Learning with Rust leveraging first principles.
pySLAM is a visual SLAM pipeline in Python for monocular, stereo and RGBD cameras. It supports many modern local and global features, different loop-closing methods, a volumetric reconstruction pip…
A toy implementation of monocular SLAM written while livestreaming
📝 Design doc template & examples for machine learning systems (requirements, methodology, implementation, etc.)
This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023
Google Research
An educational resource to help anyone learn deep reinforcement learning.
Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
A curated list of awesome neural radiance fields papers
A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
Minimal solvers for calibrated camera pose estimation
Fit interpretable models. Explain blackbox machine learning.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Source code for Twitter's Recommendation Algorithm
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
A curated, but incomplete, list of data-centric AI resources.