vit-pytorch is a comprehensive PyTorch library implementing dozens of Vision Transformer (ViT) architectures and extensions, along with self-supervised pretraining methods (MAE, DINO, SimMIM, MP3, LeJEPA) and video transformers (ViViT, NaViT-3D, CCT-3D). It is a research-oriented codebase offering a consistent API across models, all accepting standard hyperparameters like image_size, patch_size, depth, and heads. The library covers a wide spectrum of attention mechanisms (cross-attention, shifted windows, channel attention, sparse gating), tokenization strategies (patch merging, region-based, t2t, SPT), and training utilities (recorders, extractors, distillation wrappers). While primarily a collection of model implementations, it also includes action transformers for robotics (VAT, VAAT) and N-dimensional ViTs, demonstrating both breadth and depth of recent transformer research. The code is highly modular, relying on shared building blocks such as Attention, FeedForward, and Transformer classes, with heavy but well-organized use of einops for tensor manipulation. Some variants are experimental and may lack the polish of the core models, but the overall architecture is clean and serves as a valuable reference for implementing and comparing ViT variations. The repository is actively maintained, with recent commits and a large user base, but its sheer size and variety mean that not every model is exhaustively tested—core components are covered by basic forward-pass tests, while many advanced variants rely on the underlying patterns being sound.
PyGCL is a PyTorch-based library for Graph Contrastive Learning (GCL) that provides modular components for building GCL models. The library implements graph augmentation techniques, contrasting architectures, contrastive objectives, and negative sampling strategies. It features clean abstractions that separate concerns across different graph frameworks (PyG and DGL), standardized evaluation utilities, and comprehensive examples demonstrating usage. The architecture follows a modular design with distinct modules for augmentors, losses, models, evaluation, and utilities, allowing users to mix and match components to build custom GCL algorithms.
E-RayZer is a self-supervised 3D reconstruction system that takes unordered multi-view images as input and outputs estimated camera poses, target-view renders, Gaussian point clouds, and turntable videos. The system uses a transformer-based architecture to estimate camera poses and scene representations, then renders novel views using differentiable Gaussian splatting. It includes a Gradio demo interface for easy inference, along with training and evaluation scripts for the DL3DV dataset. The model is trained without ground truth camera poses or depth information, learning to reconstruct 3D scenes purely from multi-view image consistency.
byol-pytorch is a Python library that implements Bootstrap Your Own Latent (BYOL), a self-supervised learning method for image representations. The core contribution is the `BYOL` module, which wraps any PyTorch image backbone (e.g., ResNet) and trains it without labels by maximizing agreement between two augmented views of the same image. The library derives its behavior from code rather than promises: it computes a cosine loss between online predictions and target projections, where the target encoder is an exponential moving average of the online encoder (or the online encoder itself for the SimSiam variant). It also supports optional Simplicial Embeddings (SEM) and custom augmentation pipelines.
This repository implements VTP (Visual Tokenizer Pre-training), a framework for pre-training visual tokenizers using a combination of contrastive, self-supervised, and reconstruction learning objectives. The system provides a unified model architecture that supports CLIP-style image-text contrastive learning, DINOv2-style self-supervised learning, and image reconstruction. It includes training scripts, evaluation tools for zero-shot classification, linear probing, and reconstruction metrics, as well as integration with LightningDiT for generation evaluation. The codebase features a HuggingFace-compatible model implementation, modular transformer components, and various utility functions for image processing and metric calculation.