mathpluscode

grok-1

Grok open release

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

shields

Concise, consistent, and legible badges in SVG and raster format

flash-attention

Fast and memory-efficient exact attention

ml-engineering

Machine Learning Engineering Open Book

segmentation_models.pytorch

Semantic segmentation models with pretrained backbones. PyTorch.

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

torchtune

A Native-PyTorch Library for LLM Fine-tuning

Segment-and-Track-Anything

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

PPO-PyTorch

Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch

awesome-segment-anything

Tracking and collecting papers/projects/others related to Segment Anything.

VideoMAE

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

scvi-tools

Deep probabilistic analysis of single-cell and spatial omics data

nnFormer

Awesome-Masked-Autoencoders

A collection of literature after or concurrent with Masked Autoencoder (MAE) (Kaiming He el al.).

omnivore

Omnivore: A Single Model for Many Visual Modalities

MultiMAE

MultiMAE: Multi-modal Multi-task Masked Autoencoders, ECCV 2022

VideoMAEv2

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

mae_st

Official Open Source code for "Masked Autoencoders As Spatiotemporal Learners"

MedNeXt

MedNeXt is a fully ConvNeXt architecture for 3D medical image segmentation (MICCAI 2023).

Spike-Driven-Transformer

Offical implementation of "Spike-driven Transformer" (NeurIPS2023)

forecast-mae

[ICCV'2023] Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders

ViT-Lens

[CVPR 2024] ViT-Lens: Towards Omni-modal Representations

FullyConvolutionalTransformer

Official implementation of The Fully Convolutional Transformer for Medical Image Segmentation

m3ae_public

Multimodal Masked Autoencoders (M3AE): A JAX/Flax Implementation

SelfMedMAE

Code for ISBI 2023 paper "Self Pre-training with Masked Autoencoders for Medical Image Classification and Segmentation"

CrossMAE

Official Implementation of the CrossMAE paper: Rethinking Patch Dependence for Masked Autoencoders

semi-proto-seg

designed for semi-supervised prostate segmentation with lesion prototype used