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
[ICME 2021 Oral] CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning

CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning This repository is the official PyTorch implementation of CORE-Text, a

Jingyang Lin 18 Aug 11, 2022
Geometric Sensitivity Decomposition

Geometric Sensitivity Decomposition This repo is the official implementation of A Geometric Perspective towards Neural Calibration via Sensitivity Dec

16 Dec 26, 2022
《Improving Unsupervised Image Clustering With Robust Learning》(2020)

Improving Unsupervised Image Clustering With Robust Learning This repo is the PyTorch codes for "Improving Unsupervised Image Clustering With Robust L

Sungwon Park 129 Dec 27, 2022
NeurIPS 2021, self-supervised 6D pose on category level

SE(3)-eSCOPE video | paper | website Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimation Xiaolong Li, Yijia Weng,

Xiaolong 63 Nov 22, 2022
Benchmark for evaluating open-ended generation

OpenMEVA Contributed by Jian Guan, Zhexin Zhang. Thank Jiaxin Wen for DeBugging. OpenMEVA is a benchmark for evaluating open-ended story generation me

25 Nov 15, 2022
PyTorch Language Model for 1-Billion Word (LM1B / GBW) Dataset

PyTorch Large-Scale Language Model A Large-Scale PyTorch Language Model trained on the 1-Billion Word (LM1B) / (GBW) dataset Latest Results 39.98 Perp

Ryan Spring 114 Nov 04, 2022
Categorical Depth Distribution Network for Monocular 3D Object Detection

CaDDN CaDDN is a monocular-based 3D object detection method. This repository is based off of [OpenPCDet]. Categorical Depth Distribution Network for M

Toronto Robotics and AI Laboratory 289 Jan 05, 2023
Official implementation of NeurIPS'21: Implicit SVD for Graph Representation Learning

isvd Official implementation of NeurIPS'21: Implicit SVD for Graph Representation Learning If you find this code useful, you may cite us as: @inprocee

Sami Abu-El-Haija 16 Jan 08, 2023
Datasets, Transforms and Models specific to Computer Vision

torchvision The torchvision package consists of popular datasets, model architectures, and common image transformations for computer vision. Installat

13.1k Jan 02, 2023
Python Interview Questions

Python Interview Questions Clone the code to your computer. You need to understand the code in main.py and modify the content in if __name__ =='__main

ClassmateLin 575 Dec 28, 2022
This is a collection of simple PyTorch implementations of neural networks and related algorithms. These implementations are documented with explanations,

labml.ai Deep Learning Paper Implementations This is a collection of simple PyTorch implementations of neural networks and related algorithms. These i

labml.ai 16.4k Jan 09, 2023
A PyTorch implementation of ViTGAN based on paper ViTGAN: Training GANs with Vision Transformers.

ViTGAN: Training GANs with Vision Transformers A PyTorch implementation of ViTGAN based on paper ViTGAN: Training GANs with Vision Transformers. Refer

Hong-Jia Chen 127 Dec 23, 2022
Official implementation of our paper "Learning to Bootstrap for Combating Label Noise"

Learning to Bootstrap for Combating Label Noise This repo is the official implementation of our paper "Learning to Bootstrap for Combating Label Noise

21 Apr 09, 2022
Highly comparative time-series analysis

〰️ hctsa 〰️ : highly comparative time-series analysis hctsa is a software package for running highly comparative time-series analysis using Matlab (fu

Ben Fulcher 569 Dec 21, 2022
CUda Matrix Multiply library.

cumm CUda Matrix Multiply library. cumm is developed during learning of CUTLASS, which use too much c++ template and make code unmaintainable. So I de

49 Dec 27, 2022
Python package for downloading ECMWF reanalysis data and converting it into a time series format.

ecmwf_models Readers and converters for data from the ECMWF reanalysis models. Written in Python. Works great in combination with pytesmo. Citation If

TU Wien - Department of Geodesy and Geoinformation 31 Dec 26, 2022
Official Pytorch implementation for video neural representation (NeRV)

NeRV: Neural Representations for Videos (NeurIPS 2021) Project Page | Paper | UVG Data Hao Chen, Bo He, Hanyu Wang, Yixuan Ren, Ser-Nam Lim, Abhinav S

hao 214 Dec 28, 2022
Single Image Random Dot Stereogram for Tensorflow

TensorFlow-SIRDS Single Image Random Dot Stereogram for Tensorflow SIRDS is a means to present 3D data in a 2D image. It allows for scientific data di

Greg Peatfield 5 Aug 10, 2022
Final project code: Implementing BicycleGAN, for CIS680 FA21 at University of Pennsylvania

680 Final Project: BicycleGAN Haoran Tang Instructions 1. Training To train the network, please run train.py. Change hyper-parameters and folder paths

Haoran Tang 0 Apr 22, 2022
A 1.3B text-to-image generation model trained on 14 million image-text pairs

minDALL-E on Conceptual Captions minDALL-E, named after minGPT, is a 1.3B text-to-image generation model trained on 14 million image-text pairs for no

Kakao Brain 604 Dec 14, 2022