A latent text-to-image diffusion model

This repository contains implementations and illustrative code to accompany DeepMind publications

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Solutions of Reinforcement Learning, An Introduction

RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything

全中文注释.(The loss function of retinanet based on pytorch).(You can use it on one-stage detection task or classifical task, to solve data imbalance influence).用于one-stage目标检测算法,提升检测效果.你也可以在分类任务中使用该损失函…

Official Jax Implementation of MaskGIT

PyTorch Implementation of Deformable Convolution

A companion code for my Medium post