MADE (Masked Autoencoder Density Estimation) implementation in PyTorch

Overview

pytorch-made

This code is an implementation of "Masked AutoEncoder for Density Estimation" by Germain et al., 2015. The core idea is that you can turn an auto-encoder into an autoregressive density model just by appropriately masking the connections in the MLP, ordering the input dimensions in some way and making sure that all outputs only depend on inputs earlier in the list. Like other autoregressive models (char-rnn, pixel cnns, etc), evaluating the likelihood is very cheap (a single forward pass), but sampling is linear in the number of dimensions.

figure 1

The authors of the paper also published code here, but it's a bit wordy, sprawling and in Theano. Hence my own shot at it with only ~150 lines of code and PyTorch <3.

examples

First we download the binarized mnist dataset. Then we can reproduce the first point on the plot of Figure 2 by training a 1-layer MLP of 500 units with only a single mask, and using a single fixed (but random) ordering as so:

python run.py --data-path binarized_mnist.npz -q 500

which converges at binary cross entropy loss of 94.5, as shown in the paper. We can then simultaneously train a larger model ensemble (with weight sharing in the one MLP) and average over all of the models at test time. For instance, we can use 10 orderings (-n 10) and also average over the 10 at inference time (-s 10):

python run.py --data-path binarized_mnist.npz -q 500 -n 10 -s 10

which gives a much better test loss of 79.3, but at the cost of multiple forward passes. I was not able to reproduce single-forward-pass gains that the paper alludes to when training with multiple masks, might be doing something wrong.

usage

The core class is MADE, found in made.py. It inherits from PyTorch nn.Module so you can "slot it into" larger architectures quite easily. To instantiate MADE on 1D inputs of MNIST digits for example (which have 28*28 pixels), using one hidden layer of 500 neurons, and using a single but random ordering we would do:

model = MADE(28*28, [500], 28*28, num_masks=1, natural_ordering=False)

The reason we plug the size of the output (3rd argument) into MADE is that one might want to use relatively complicated output distributions, for example a gaussian distribution would normally be parameterized by a mean and a standard deviation for each dimension, or you could bin the output range into buckets and output logprobs for a softmax, or mixture parameters, etc. In the simplest example in this code we use binary predictions, where are only parameterized by one number, hence the number of the input dimensions happens to equal the number of outputs.

License

MIT

You might also like...
Pytorch implementation of MaskGIT: Masked Generative Image Transformer

Pytorch implementation of MaskGIT: Masked Generative Image Transformer

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

Re-implememtation of MAE (Masked Autoencoders Are Scalable Vision Learners) using PyTorch.

mae-repo PyTorch re-implememtation of "masked autoencoders are scalable vision learners". In this repo, it heavily borrows codes from codebase https:/

Molecular AutoEncoder in PyTorch

MolEncoder Molecular AutoEncoder in PyTorch Install $ git clone https://github.com/cxhernandez/molencoder.git && cd molencoder $ python setup.py insta

Recurrent Variational Autoencoder that generates sequential data implemented with pytorch

Pytorch Recurrent Variational Autoencoder Model: This is the implementation of Samuel Bowman's Generating Sentences from a Continuous Space with Kim's

Details about the wide minima density hypothesis and metrics to compute width of a minima

wide-minima-density-hypothesis Details about the wide minima density hypothesis and metrics to compute width of a minima This repo presents the wide m

SMD-Nets: Stereo Mixture Density Networks
SMD-Nets: Stereo Mixture Density Networks

SMD-Nets: Stereo Mixture Density Networks This repository contains a Pytorch implementation of "SMD-Nets: Stereo Mixture Density Networks" (CVPR 2021)

This YoloV5 based model is fit to detect people and different types of land vehicles, and displaying their density on a fitted map, according to their coordinates and detected labels.
This YoloV5 based model is fit to detect people and different types of land vehicles, and displaying their density on a fitted map, according to their coordinates and detected labels.

This YoloV5 based model is fit to detect people and different types of land vehicles, and displaying their density on a fitted map, according to their

Official code of the paper
Official code of the paper "Expanding Low-Density Latent Regions for Open-Set Object Detection" (CVPR 2022)

OpenDet Expanding Low-Density Latent Regions for Open-Set Object Detection (CVPR2022) Jiaming Han, Yuqiang Ren, Jian Ding, Xingjia Pan, Ke Yan, Gui-So

Comments
  • Reproduce example

    Reproduce example

    Hello, I tried to reproduce the example of the first figure (3 inputs, 3 outputs and 2 dense layers of 4 neurons) and the mask is not the same (result: https://imgur.com/5P5C2fn). imagen

    output  0 depends on inputs:                             [] : OK
    output  1 depends on inputs:                             [] : OK
    output  2 depends on inputs:                         [0, 1] : OK
    

    So two outputs remain without dependence. What could be the problem? Thank you.

    opened by carlogarro 0
  • log-likelihood of order/connectivity-agnostic training

    log-likelihood of order/connectivity-agnostic training

    Here you simply average over the logits. However, did I understand correctly that the order/connectivity-agnostic training amounts to a mixture model with $p(x) = \sum_{o} p(x, o)$ ? If so, it appears that one needs to compute log-likelihood for each mask and then perform logsumexp to obtain the mixture log-likelihood.

    opened by wangleiphy 0
Owner
Andrej
I like to train Deep Neural Nets on large datasets.
Andrej
Mae segmentation - Reproduction of semantic segmentation using masked autoencoder (mae)

ADE20k Semantic segmentation with MAE Getting started Install the mmsegmentation

null 97 Dec 17, 2022
CoSMA: Convolutional Semi-Regular Mesh Autoencoder. From Paper "Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes"

Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes Implementation of CoSMA: Convolutional Semi-Regular Mesh Autoencoder arXiv p

Fraunhofer SCAI 10 Oct 11, 2022
PyTorch implementations of algorithms for density estimation

pytorch-flows A PyTorch implementations of Masked Autoregressive Flow and some other invertible transformations from Glow: Generative Flow with Invert

Ilya Kostrikov 546 Dec 5, 2022
Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation principle for unnormalized statistical models." (Gutmann and Hyvarinen, AISTATS 2010)

Noise Contrastive Estimation for pyTorch Overview This repository contains a re-implementation of the Noise Contrastive Estimation algorithm, implemen

Denis Emelin 42 Nov 24, 2022
Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network

DroneCrowd Paper Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark. Introduction This paper proposes a space-time multi-scale atte

VisDrone 98 Nov 16, 2022
Estimation of human density in a closed space using deep learning.

Siemens HOLLZOF challenge - Human Density Estimation Add project description here. Installing Dependencies: Install Python3 either system-wide, user-w

null 3 Aug 8, 2021
This program presents convolutional kernel density estimation, a method used to detect intercritical epilpetic spikes (IEDs)

Description This program presents convolutional kernel density estimation, a method used to detect intercritical epilpetic spikes (IEDs) in [Gardy et

Ludovic Gardy 0 Feb 9, 2022
Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners This repository is built upon BEiT, thanks very much! Now, we on

Zhiliang Peng 2.3k Jan 4, 2023
PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners for self-supervised ViT.

MAE for Self-supervised ViT Introduction This is an unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners for self-sup

null 36 Oct 30, 2022
An pytorch implementation of Masked Autoencoders Are Scalable Vision Learners

An pytorch implementation of Masked Autoencoders Are Scalable Vision Learners This is a coarse version for MAE, only make the pretrain model, the fine

FlyEgle 214 Dec 29, 2022