tf-var-attention

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Open3D: A Modern Library for 3D Data Processing

COLMAP - Structure-from-Motion and Multi-View Stereo

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

A concise but complete full-attention transformer with a set of promising experimental features from various papers

:man: Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"

Graph Attention Networks (https://arxiv.org/abs/1710.10903)

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)