An example of Scatterbrain implementation (combining local attention and Performer)

Overview

We use the template from https://github.com/ashleve/lightning-hydra-template. Please read the instructions there to understand the repo structure.

Implementation & Experiments

An example of Scatterbrain implementation (combining local attention and Performer) is in the file src/models/modules/attention/sblocal.py.

T2T-ViT inference on ImageNet

To run the T2T-ViT inference on ImageNet experiment:

  1. Download the pretrained weights from the [T2T-ViT repo][https://github.com/yitu-opensource/T2T-ViT/releases]:
mkdir -p checkpoints/t2tvit
cd checkpoints/t2tvit
wget https://github.com/yitu-opensource/T2T-ViT/releases/download/main/81.7_T2T_ViTt_14.pth.tar
  1. Convert the weights to the format compatible with our implementation of T2T-ViT:
# cd to scatterbrain path
python scripts/convert_checkpoint_t2t_vit.py checkpoints/t2tvit/81.7_T2T_ViTt_14.pth.tar
  1. Download the ImageNet dataset (just the validation set will suffice). Below, /path/to/imagenet refers to the directory that contains the train and val directories.
  2. Run the inference experiments:
python run.py experiment=imagenet-t2tvit-eval.yaml model/t2tattn_cfg=full datamodule.data_dir=/path/to/imagenet/ eval.ckpt=checkpoints/t2tvit/81.7_T2T_ViTt_14.pth.tar  # 81.7% acc
python run.py experiment=imagenet-t2tvit-eval.yaml model/t2tattn_cfg=local datamodule.data_dir=/path/to/imagenet/ eval.ckpt=checkpoints/t2tvit/81.7_T2T_ViTt_14.pth.tar  # 80.6% acc
python run.py experiment=imagenet-t2tvit-eval.yaml model/t2tattn_cfg=performer datamodule.data_dir=/path/to/imagenet/ eval.ckpt=checkpoints/t2tvit/81.7_T2T_ViTt_14.pth.tar  # 77.8-79.0% acc (there's randomness)
python run.py experiment=imagenet-t2tvit-eval.yaml model/t2tattn_cfg=sblocal datamodule.data_dir=/path/to/imagenet/ eval.ckpt=checkpoints/t2tvit/81.7_T2T_ViTt_14.pth.tar  # 81.1% acc

Requirements

Python 3.8+, Pytorch 1.9+, torchvision, torchtext, pytorch-fast-transformers, munch, einops, timm, hydra-core, hydra-colorlog, python-dotenv, rich, pytorch-lightning, lightning-bolts.

We provide a Dockerfile that lists all the required packages.

Citation

If you use this codebase, or otherwise found our work valuable, please cite:

@inproceedings{chen2021scatterbrain,
  title={Scatterbrain: Unifying Sparse and Low-rank Attention},
  author={Beidi Chen and Tri Dao and Eric Winsor and Zhao Song and Atri Rudra and Christopher R\'{e}},
  booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
  year={2021}
}
Owner
HazyResearch
We are a CS research group led by Prof. Chris Ré.
HazyResearch
Code for the published paper : Learning to recognize rare traffic sign

Improving traffic sign recognition by active search This repo contains code for the paper : "Learning to recognise rare traffic signs" How to use this

samsja 4 Jan 05, 2023
PED: DETR for Crowd Pedestrian Detection

PED: DETR for Crowd Pedestrian Detection Code for PED: DETR For (Crowd) Pedestrian Detection Paper PED: DETR for Crowd Pedestrian Detection Installati

36 Sep 13, 2022
PyTorch implementation of "A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

FullSubNet This Git repository for the official PyTorch implementation of "A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech E

郝翔 357 Jan 04, 2023
PyElecCL - Electron Monte Carlo Second Checks

PyElecCL Python program to perform second checks for electron Monte Carlo radiat

Reese Haywood 3 Feb 22, 2022
An AutoML Library made with Optuna and PyTorch Lightning

An AutoML Library made with Optuna and PyTorch Lightning Installation Recommended pip install -U gradsflow From source pip install git+https://github.

GradsFlow 294 Dec 17, 2022
A PyTorch implementation for PyramidNets (Deep Pyramidal Residual Networks)

A PyTorch implementation for PyramidNets (Deep Pyramidal Residual Networks) This repository contains a PyTorch implementation for the paper: Deep Pyra

Greg Dongyoon Han 262 Jan 03, 2023
Official Implementation of Swapping Autoencoder for Deep Image Manipulation (NeurIPS 2020)

Swapping Autoencoder for Deep Image Manipulation Taesung Park, Jun-Yan Zhu, Oliver Wang, Jingwan Lu, Eli Shechtman, Alexei A. Efros, Richard Zhang UC

449 Dec 27, 2022
Pytorch implementation of the Variational Recurrent Neural Network (VRNN).

VariationalRecurrentNeuralNetwork Pytorch implementation of the Variational RNN (VRNN), from A Recurrent Latent Variable Model for Sequential Data. Th

emmanuel 251 Dec 17, 2022
Unofficial keras(tensorflow) implementation of MAE model from Masked Autoencoders Are Scalable Vision Learners

MAE-keras Unofficial keras(tensorflow) implementation of MAE model described in 'Masked Autoencoders Are Scalable Vision Learners'. This work has been

Yewon 11 Jun 12, 2022
DAN: Unfolding the Alternating Optimization for Blind Super Resolution

DAN-Basd-on-Openmmlab DAN: Unfolding the Alternating Optimization for Blind Super Resolution We reproduce DAN via mmediting based on open-sourced code

AlexZou 72 Dec 13, 2022
TilinGNN: Learning to Tile with Self-Supervised Graph Neural Network (SIGGRAPH 2020)

TilinGNN: Learning to Tile with Self-Supervised Graph Neural Network (SIGGRAPH 2020) About The goal of our research problem is illustrated below: give

59 Dec 09, 2022
Raster Vision is an open source Python framework for building computer vision models on satellite, aerial, and other large imagery sets

Raster Vision is an open source Python framework for building computer vision models on satellite, aerial, and other large imagery sets (including obl

Azavea 1.7k Dec 22, 2022
The code for our paper CrossFormer: A Versatile Vision Transformer Based on Cross-scale Attention.

CrossFormer This repository is the code for our paper CrossFormer: A Versatile Vision Transformer Based on Cross-scale Attention. Introduction Existin

cheerss 238 Jan 06, 2023
PyTorch Implementation of NCSOFT's FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis

FastPitchFormant - PyTorch Implementation PyTorch Implementation of FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis. Qu

Keon Lee 63 Jan 02, 2023
Generative Adversarial Networks(GANs)

Generative Adversarial Networks(GANs) Vanilla GAN ClusterGAN Vanilla GAN Model Structure Final Generator Structure A MLP with 2 hidden layers of hidde

Zhenbang Feng 2 Nov 05, 2021
Implementation of hyperparameter optimization/tuning methods for machine learning & deep learning models

Hyperparameter Optimization of Machine Learning Algorithms This code provides a hyper-parameter optimization implementation for machine learning algor

Li Yang 1.1k Dec 19, 2022
Unified file system operation experience for different backend

megfile - Megvii FILE library Docs: http://megvii-research.github.io/megfile megfile provides a silky operation experience with different backends (cu

MEGVII Research 76 Dec 14, 2022
Official Pytorch Implementation for Splicing ViT Features for Semantic Appearance Transfer presenting Splice

Splicing ViT Features for Semantic Appearance Transfer [Project Page] Splice is a method for semantic appearance transfer, as described in Splicing Vi

Omer Bar Tal 253 Jan 06, 2023
Official implementation of Deep Reparametrization of Multi-Frame Super-Resolution and Denoising

Deep-Rep-MFIR Official implementation of Deep Reparametrization of Multi-Frame Super-Resolution and Denoising Publication: Deep Reparametrization of M

Goutam Bhat 39 Jan 04, 2023
Pytorch implementation of OCNet series and SegFix.

openseg.pytorch News 2021/09/14 MMSegmentation has supported our ISANet and refer to ISANet for more details. 2021/08/13 We have released the implemen

openseg-group 1.1k Dec 23, 2022