LogAvgExp - Pytorch Implementation of LogAvgExp

Related tags

Deep Learningpytorchlogsumexp
Overview

LogAvgExp - Pytorch

Implementation of LogAvgExp for Pytorch

Install

$ pip install logavgexp-pytorch

Usage

import torch
from logavgexp_pytorch import logavgexp

# basically it is an improved logsumexp (differentiable max)
# normalized for length

x = torch.arange(1000)
y = logavgexp(x, dim = 0, temp = 0.01) # ~998.8

# more than 1 dimension

x = torch.randn(1, 2048, 5)
y = logavgexp(x, dim = 1, temp = 0.2) # (1, 5)

# keep dimension

x = torch.randn(1, 2048, 5)
y = logavgexp(x, dim = 1, temp = 0.2, keepdim = True) # (1, 1, 5)

# masking (False for mask out with large negative value)

x = torch.randn(1, 2048, 5)
m = torch.randint(0, 2, (1, 2048, 1)).bool()

y = logavgexp(x, mask = m, dim = 1, temp = 0.2, keepdim = True) # (1, 1, 5)

With learned temperature

# learned temperature
import torch
from torch import nn
from logavgexp_pytorch import logavgexp

learned_temp = nn.Parameter(torch.ones(1) * -5).exp().clamp(min = 1e-8) # make sure temperature can't hit 0

x = torch.randn(1, 2048, 5)
y = logavgexp(x, temp = learned_temp, dim = -1) # (1, 5)

Or you can use the LogAvgExp class to handle the learned temperature parameter

import torch
from logavgexp_pytorch import LogAvgExp

logavgexp = LogAvgExp(
    temp = 0.01,
    dim = 1,
    learned_temp = True
)

x = torch.randn(1, 2048, 5)
y = logavgexp(x) # (1, 5)

Citations

@misc{lowe2021logavgexp,
    title   = {LogAvgExp Provides a Principled and Performant Global Pooling Operator}, 
    author  = {Scott C. Lowe and Thomas Trappenberg and Sageev Oore},
    year    = {2021},
    eprint  = {2111.01742},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG}
}
You might also like...
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

This repository holds NVIDIA-maintained utilities to streamline mixed precision and distributed training in Pytorch. Some of the code here will be included in upstream Pytorch eventually. The intention of Apex is to make up-to-date utilities available to users as quickly as possible.

NVIDIA Corporation 6.9k Jan 3, 2023
Objective of the repository is to learn and build machine learning models using Pytorch. 30DaysofML Using Pytorch
Objective of the repository is to learn and build machine learning models using Pytorch. 30DaysofML Using Pytorch

30 Days Of Machine Learning Using Pytorch Objective of the repository is to learn and build machine learning models using Pytorch. List of Algorithms

Mayur 119 Nov 24, 2022
Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch
Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch

Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch

Pytorch Lightning 1.4k Jan 1, 2023
Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks
Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks

Amazon Forest Computer Vision Satellite Image tagging code using PyTorch / Keras Here is a sample of images we had to work with Source: https://www.ka

Mamy Ratsimbazafy 360 Dec 10, 2022
The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.
The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

This is a curated list of tutorials, projects, libraries, videos, papers, books and anything related to the incredible PyTorch. Feel free to make a pu

Ritchie Ng 9.2k Jan 2, 2023
Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks
Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks

Amazon Forest Computer Vision Satellite Image tagging code using PyTorch / Keras Here is a sample of images we had to work with Source: https://www.ka

Mamy Ratsimbazafy 359 Jan 5, 2023
A bunch of random PyTorch models using PyTorch's C++ frontend
A bunch of random PyTorch models using PyTorch's C++ frontend

PyTorch Deep Learning Models using the C++ frontend Gettting started Clone the repo 1. https://github.com/mrdvince/pytorchcpp 2. cd fashionmnist or

Vince 0 Jul 13, 2021
PyTorch Autoencoders - Implementing a Variational Autoencoder (VAE) Series in Pytorch.

PyTorch Autoencoders Implementing a Variational Autoencoder (VAE) Series in Pytorch. Inspired by this repository Model List check model paper conferen

Subin An 8 Nov 21, 2022
PyTorch-LIT is the Lite Inference Toolkit (LIT) for PyTorch which focuses on easy and fast inference of large models on end-devices.

PyTorch-LIT PyTorch-LIT is the Lite Inference Toolkit (LIT) for PyTorch which focuses on easy and fast inference of large models on end-devices. With

Amin Rezaei 157 Dec 11, 2022
Comments
  • Enhancement: 2d Pooling

    Enhancement: 2d Pooling

    Could put in 2d pooling for an easy to drop in alternative to AvgPool2d by using pixel_unshuffle for cases where there's exact divisions of an input shape, or padding and unfold for overlapping windows / strides that aren't equal to the window size.

    I don't know how fast Unfold is or if there's a better way to do the operation; I tried checking the PyTorch github to see how it does AvgPool2d for strides that aren't equal to the window size behind the scenes but I can never seem to figure out which version of the operation is the one that's used, it's defined in so many places it's beyond me.

    I've once seen an alternative to pixel unshuffle that used grouped conv2d, a kernel that put each position into its own channel output, and stride, but I can't seem to find it again. It was useful because you could adjust the stride and then it'd be like Unfold, but I never got around to testing if it was actually faster.

    opened by torridgristle 6
  • learned temperature stagnates at a low value (a high value is expected)

    learned temperature stagnates at a low value (a high value is expected)

    Hi,

    Big thanks for your pytorch implementation of the logavgexp !

    I noticed that it is easy for logavgexp to reproduce the max operator (temperature goes nicely to 0); but it has trouble reproducing the mean operator, the temperature stagnates in the following example at 0.35; do your have an explanation for that or ways to circumvent this issue? Thanks !

    import torch
torch.manual_seed(12345)
from logavgexp_pytorch import LogAvgExp

B = 10
N = 20
x = torch.randn(B,N)
#y, _ = x.max(dim=-1, keepdim=True)
y    = x.mean(dim=-1, keepdim=True)
logavgexp = LogAvgExp(
    temp = 1,
    dim = 1,
    learned_temp = True,
    keepdim = True)

optimizer = torch.optim.Adam(logavgexp.parameters(), lr=0.01)
loss_func = torch.nn.MSELoss()
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer,
                                                       factor=0.5,
                                                       patience=100,
                                                       verbose=True)

for i in range(10000):
    prediction = logavgexp(x)
    loss = loss_func(prediction, y) 
    optimizer.zero_grad()
    loss.backward()        
    optimizer.step()
    scheduler.step(loss, epoch=i)
    print(f"ite: {i}, loss: {loss.item():.2e}, temperature: {logavgexp.temp.exp().item():.4f}")
    opened by ldv1 0
Releases(0.0.6)
Owner
Phil Wang
Working with Attention. It's all we need
Phil Wang
GitHub Repository
IEEE Winter Conference on Applications of Computer Vision 2022 Accepted

SSKT(Accepted WACV2022) Concept map Dataset Image dataset CIFAR10 (torchvision) CIFAR100 (torchvision) STL10 (torchvision) Pascal VOC (torchvision) Im

1 Nov 17, 2022
๐ŸŒพ PASTIS ๐ŸŒพ Panoptic Agricultural Satellite TIme Series

๐ŸŒพ PASTIS ๐ŸŒพ Panoptic Agricultural Satellite TIme Series (optical and radar) The PASTIS Dataset Dataset presentation PASTIS is a benchmark dataset for

86 Jan 04, 2023
Source code for our paper "Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures"

Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures Code for the Multiplex Molecular Graph Neural Network (M

shzhang 59 Dec 10, 2022
Analyses of the individual electric field magnitudes with Roast.

Aloi Davide - PhD Student (UoB) Analysis of electric field magnitudes (wp2a dataset only at the moment) and correlation analysis with Dynamic Causal M

Davide Aloi 7 Dec 15, 2022
Refactoring dalle-pytorch and taming-transformers for TPU VM

Text-to-Image Translation (DALL-E) for TPU in Pytorch Refactoring Taming Transformers and DALLE-pytorch for TPU VM with Pytorch Lightning Requirements

Kim, Taehoon 61 Nov 07, 2022
(ICCV 2021) Official code of "Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing."

Dressing in Order (DiOr) ๐Ÿ‘š [Paper] ๐Ÿ‘– [Webpage] ๐Ÿ‘— [Running this code] The official implementation of "Dressing in Order: Recurrent Person Image Gene

Aiyu Cui 277 Dec 28, 2022
RoboDesk A Multi-Task Reinforcement Learning Benchmark

RoboDesk A Multi-Task Reinforcement Learning Benchmark If you find this open source release useful, please reference in your paper: @misc{kannan2021ro

Google Research 66 Oct 07, 2022
A PyTorch implementation of DenseNet.

A PyTorch Implementation of DenseNet This is a PyTorch implementation of the DenseNet-BC architecture as described in the paper Densely Connected Conv

Brandon Amos 771 Dec 15, 2022
StyleGAN2-ADA - Official PyTorch implementation

Abstract: Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmenta

NVIDIA Research Projects 3.2k Dec 30, 2022
Sound Event Detection with FilterAugment

Sound Event Detection with FilterAugment Official implementation of Heavily Augmented Sound Event Detection utilizing Weak Predictions (DCASE2021 Chal

43 Aug 28, 2022
Pre-Trained Image Processing Transformer (IPT)

Pre-Trained Image Processing Transformer (IPT) By Hanting Chen, Yunhe Wang, Tianyu Guo, Chang Xu, Yiping Deng, Zhenhua Liu, Siwei Ma, Chunjing Xu, Cha

HUAWEI Noah's Ark Lab 332 Dec 18, 2022
ML model to classify between cats and dogs

Cats-and-dogs-classifier This is my first ML model which can classify between cats and dogs. Here the accuracy is around 75%, however , the accuracy c

Sharath V 4 Aug 20, 2021
DAT4 - General Assembly's Data Science course in Washington, DC

DAT4 Course Repository Course materials for General Assembly's Data Science course in Washington, DC (12/15/14 - 3/16/15). Instructors: Sinan Ozdemir

Kevin Markham 779 Dec 25, 2022
A PyTorch implementation of EventProp [https://arxiv.org/abs/2009.08378], a method to train Spiking Neural Networks

Spiking Neural Network training with EventProp This is an unofficial PyTorch implemenation of EventProp, a method to compute exact gradients for Spiki

Pedro Savarese 35 Jul 29, 2022
Code to reproduce the results for Compositional Attention

Compositional-Attention This repository contains the official implementation for the paper Compositional Attention: Disentangling Search and Retrieval

Sarthak Mittal 58 Nov 30, 2022
MAVE: : A Product Dataset for Multi-source Attribute Value Extraction

The dataset contains 3 million attribute-value annotations across 1257 unique categories on 2.2 million cleaned Amazon product profiles. It is a large, multi-sourced, diverse dataset for product attr

Google Research Datasets 89 Jan 08, 2023
Implementation of Retrieval-Augmented Denoising Diffusion Probabilistic Models in Pytorch

Retrieval-Augmented Denoising Diffusion Probabilistic Models (wip) Implementation of Retrieval-Augmented Denoising Diffusion Probabilistic Models in P

Phil Wang 55 Jan 01, 2023
PyTorch code for our ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"

PyTorch code for our ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"

Yulun Zhang 1.2k Dec 26, 2022
An easy-to-use app to visualise attentions of various VQA models.

Ask Me Anything: A tool for visualising Visual Question Answering (AMA) An easy-to-use app to visualise attentions of various VQA models. Please click

Apoorve 37 Nov 13, 2022
HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement

HiFi++ : a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement This is the unofficial implementation of Vocoder part of

Rishikesh (เค‹เคทเคฟเค•เฅ‡เคถ) 118 Dec 29, 2022