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

Owner
Andrej
I like to train Deep Neural Nets on large datasets.
Andrej
ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs

ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs This is the code of paper ConE: Cone Embeddings for Multi-Hop Reasoning over Knowl

MIRA Lab 33 Dec 07, 2022
A quick recipe to learn all about Transformers

Transformers have accelerated the development of new techniques and models for natural language processing (NLP) tasks.

DAIR.AI 772 Dec 31, 2022
6D Grasping Policy for Point Clouds

GA-DDPG [website, paper] Installation git clone https://github.com/liruiw/GA-DDPG.git --recursive Setup: Ubuntu 16.04 or above, CUDA 10.0 or above, py

Lirui Wang 48 Dec 21, 2022
Official PyTorch implementation of the preprint paper "Stylized Neural Painting", accepted to CVPR 2021.

Official PyTorch implementation of the preprint paper "Stylized Neural Painting", accepted to CVPR 2021.

Zhengxia Zou 1.5k Dec 28, 2022
DiAne is a smart fuzzer for IoT devices

Diane Diane is a fuzzer for IoT devices. Diane works by identifying fuzzing triggers in the IoT companion apps to produce valid yet under-constrained

seclab 28 Jan 04, 2023
For the paper entitled ''A Case Study and Qualitative Analysis of Simple Cross-Lingual Opinion Mining''

Summary This is the source code for the paper "A Case Study and Qualitative Analysis of Simple Cross-Lingual Opinion Mining", which was accepted as fu

1 Nov 10, 2021
This package is for running the semantic SLAM algorithm using extracted planar surfaces from the received detection

Semantic SLAM This package can perform optimization of pose estimated from VO/VIO methods which tend to drift over time. It uses planar surfaces extra

Hriday Bavle 125 Dec 02, 2022
Utility code for use with PyXLL

pyxll-utils There is no need to use this package as of PyXLL 5. All features from this package are now provided by PyXLL. If you were using this packa

PyXLL 10 Dec 18, 2021
Learning to See by Looking at Noise

Learning to See by Looking at Noise This is the official implementation of Learning to See by Looking at Noise. In this work, we investigate a suite o

Manel Baradad Jurjo 82 Dec 24, 2022
Bayesian Neural Networks in PyTorch

We present the new scheme to compute Monte Carlo estimator in Bayesian VI settings with almost no memory cost in GPU, regardles of the number of sampl

Jurijs Nazarovs 7 May 03, 2022
Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation

Auto-Seg-Loss By Hao Li, Chenxin Tao, Xizhou Zhu, Xiaogang Wang, Gao Huang, Jifeng Dai This is the official implementation of the ICLR 2021 paper Auto

61 Dec 21, 2022
NUANCED is a user-centric conversational recommendation dataset that contains 5.1k annotated dialogues and 26k high-quality user turns.

NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions Overview NUANCED is a user-centric conversational recommen

Facebook Research 18 Dec 28, 2021
Bringing Computer Vision and Flutter together , to build an awesome app !!

Bringing Computer Vision and Flutter together , to build an awesome app !! Explore the Directories Flutter · Machine Learning Table of Contents About

Padmanabha Banerjee 14 Apr 07, 2022
TensorFlow CNN for fast style transfer

Fast Style Transfer in TensorFlow Add styles from famous paintings to any photo in a fraction of a second! It takes 100ms on a 2015 Titan X to style t

1 Dec 14, 2021
基于DouZero定制AI实战欢乐斗地主

DouZero_For_Happy_DouDiZhu: 将DouZero用于欢乐斗地主实战 本项目基于DouZero 环境配置请移步项目DouZero 模型默认为WP,更换模型请修改start.py中的模型路径 运行main.py即可 SL (baselines/sl/): 基于人类数据进行深度学习

1.5k Jan 08, 2023
StarGAN - Official PyTorch Implementation (CVPR 2018)

StarGAN - Official PyTorch Implementation ***** New: StarGAN v2 is available at https://github.com/clovaai/stargan-v2 ***** This repository provides t

Yunjey Choi 5.1k Jan 04, 2023
Official implementation for “Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior”

Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior. The code will release soon. Implementation Python3 PyTorch=1.0 NVIDIA GPU+

FengZhang 34 Dec 04, 2022
Implementation of Diverse Semantic Image Synthesis via Probability Distribution Modeling

Diverse Semantic Image Synthesis via Probability Distribution Modeling (CVPR 2021) Paper Zhentao Tan, Menglei Chai, Dongdong Chen, Jing Liao, Qi Chu,

tzt 45 Nov 17, 2022
Rocket-recycling with Reinforcement Learning

Rocket-recycling with Reinforcement Learning Developed by: Zhengxia Zou I have long been fascinated by the recovery process of SpaceX rockets. In this

Zhengxia Zou 202 Jan 03, 2023
Optimal Camera Position for a Practical Application of Gaze Estimation on Edge Devices,

Optimal Camera Position for a Practical Application of Gaze Estimation on Edge Devices, Linh Van Ma, Tin Trung Tran, Moongu Jeon, ICAIIC 2022 (The 4th

Linh 11 Oct 10, 2022