Scaling Vision with Sparse Mixture of Experts

Related tags

Deep Learningvmoe
Overview

Scaling Vision with Sparse Mixture of Experts

This repository contains the code for training and fine-tuning Sparse MoE models for vision (V-MoE) on ImageNet-21k, reproducing the results presented in the paper:

We will soon provide a colab analysing one of the models that we have released, as well as "config" files to train from scratch and fine-tune checkpoints. Stay tuned.

Installation

Simply clone this repository.

The file requirements.txt contains the requirements that can be installed via PyPi. However, we recommend installing jax, flax and optax directly from GitHub, since we use some of the latest features that are not part of any release yet.

In addition, you also have to clone the Vision Transformer repository, since we use some parts of it.

If you want to use RandAugment to train models (which we recommend if you train on ImageNet-21k or ILSVRC2012 from scratch), you must also clone the Cloud TPU repository, and name it cloud_tpu.

Checkpoints

We release the checkpoints containing the weights of some models that we trained on ImageNet (either ILSVRC2012 or ImageNet-21k). All checkpoints contain an index file (with .index extension) and one or multiple data files ( with extension .data-nnnnn-of-NNNNN, called shards). In the following list, we indicate only the prefix of each checkpoint. We recommend using gsutil to obtain the full list of files, download them, etc.

  • V-MoE S/32, 8 experts on the last two odd blocks, trained from scratch on ILSVRC2012 with RandAugment: gs://vmoe_checkpoints/vmoe_s32_last2_ilsvrc2012_randaug_medium.
  • V-MoE B/16, 8 experts on every odd block, trained from scratch on ImageNet-21k with RandAugment: gs://vmoe_checkpoints/vmoe_b16_imagenet21k_randaug_strong.
    • Fine-tuned on ILSVRC2012: gs://vmoe_checkpoints/vmoe_b16_imagenet21k_randaug_strong_ft_ilsvrc2012

Disclaimers

This is not an officially supported Google product.

Owner
Google Research
Google Research
Bi-level feature alignment for versatile image translation and manipulation (Under submission of TPAMI)

Bi-level feature alignment for versatile image translation and manipulation (Under submission of TPAMI) Preparation Clone the Synchronized-BatchNorm-P

Fangneng Zhan 12 Aug 10, 2022
Unimodal Face Classification with Multimodal Training

Unimodal Face Classification with Multimodal Training This is a PyTorch implementation of the following paper: Unimodal Face Classification with Multi

Wenbin Teng 3 Jul 06, 2022
Codes for ACL-IJCNLP 2021 Paper "Zero-shot Fact Verification by Claim Generation"

Zero-shot-Fact-Verification-by-Claim-Generation This repository contains code and models for the paper: Zero-shot Fact Verification by Claim Generatio

Liangming Pan 47 Jan 01, 2023
NER for Indian languages

CL-NERIL: A Cross-Lingual Model for NER in Indian Languages Code for the paper - https://arxiv.org/abs/2111.11815 Setup Setup a virtual environment Th

Akshara P 0 Nov 24, 2021
Multi-modal co-attention for drug-target interaction annotation and Its Application to SARS-CoV-2

CoaDTI Multi-modal co-attention for drug-target interaction annotation and Its Application to SARS-CoV-2 Abstract Environment The test was conducted i

Layne_Huang 7 Nov 14, 2022
Implementation for our ICCV 2021 paper: Dual-Camera Super-Resolution with Aligned Attention Modules

DCSR: Dual Camera Super-Resolution Implementation for our ICCV 2021 oral paper: Dual-Camera Super-Resolution with Aligned Attention Modules paper | pr

Tengfei Wang 110 Dec 20, 2022
Isaac Gym Reinforcement Learning Environments

Isaac Gym Reinforcement Learning Environments

NVIDIA Omniverse 714 Jan 08, 2023
Unofficial PyTorch Implementation of "DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features"

Pytorch Implementation of Deep Orthogonal Fusion of Local and Global Features (DOLG) This is the unofficial PyTorch Implementation of "DOLG: Single-St

DK 96 Jan 06, 2023
(Python, R, C/C++) Isolation Forest and variations such as SCiForest and EIF, with some additions (outlier detection + similarity + NA imputation)

IsoTree Fast and multi-threaded implementation of Extended Isolation Forest, Fair-Cut Forest, SCiForest (a.k.a. Split-Criterion iForest), and regular

141 Dec 29, 2022
Hso-groupie - A pwnable challenge in Real World CTF 4th

Hso-groupie - A pwnable challenge in Real World CTF 4th

Riatre Foo 42 Dec 05, 2022
Official implementation of the paper ``Unifying Nonlocal Blocks for Neural Networks'' (ICCV'21)

Spectral Nonlocal Block Overview Official implementation of the paper: Unifying Nonlocal Blocks for Neural Networks (ICCV'21) Spectral View of Nonloca

91 Dec 14, 2022
最新版本yolov5+deepsort目标检测和追踪,支持5.0版本可训练自己数据集

使用YOLOv5+Deepsort实现车辆行人追踪和计数,代码封装成一个Detector类,更容易嵌入到自己的项目中。

422 Dec 30, 2022
Code for paper entitled "Improving Novelty Detection using the Reconstructions of Nearest Neighbours"

NLN: Nearest-Latent-Neighbours A repository containing the implementation of the paper entitled Improving Novelty Detection using the Reconstructions

Michael (Misha) Mesarcik 4 Dec 14, 2022
Code for the paper "Can Active Learning Preemptively Mitigate Fairness Issues?" presented at RAI 2021.

Can Active Learning Preemptively Mitigate Fairness Issues? Code for the paper "Can Active Learning Preemptively Mitigate Fairness Issues?" presented a

ElementAI 7 Aug 12, 2022
A simple algorithm for extracting tree height in sparse scene from point cloud data.

TREE HEIGHT EXTRACTION IN SPARSE SCENES BASED ON UAV REMOTE SENSING This is the offical python implementation of the paper "Tree Height Extraction in

6 Oct 28, 2022
Graph Analysis From Scratch

Graph Analysis From Scratch Goal In this notebook we wanted to implement some functionalities to analyze a weighted graph only by using algorithms imp

Arturo Ghinassi 0 Sep 17, 2022
Where2Act: From Pixels to Actions for Articulated 3D Objects

Where2Act: From Pixels to Actions for Articulated 3D Objects The Proposed Where2Act Task. Given as input an articulated 3D object, we learn to propose

Kaichun Mo 69 Nov 28, 2022
A model which classifies reviews as positive or negative.

SentiMent Analysis In this project I built a model to classify movie reviews fromn the IMDB dataset of 50K reviews. WordtoVec : Neural networks only w

Rishabh Bali 2 Feb 09, 2022
An unofficial personal implementation of UM-Adapt, specifically to tackle joint estimation of panoptic segmentation and depth prediction for autonomous driving datasets.

Semisupervised Multitask Learning This repository is an unofficial and slightly modified implementation of UM-Adapt[1] using PyTorch. This code primar

Abhinav Atrishi 11 Nov 25, 2022
TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform

TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform

2.6k Jan 04, 2023