Generative Flow Networks for Discrete Probabilistic Modeling

Last update: Dec 20, 2022

Related tags

Overview

Energy-based GFlowNets

Code for Generative Flow Networks for Discrete Probabilistic Modeling by Dinghuai Zhang, Nikolay Malkin, Zhen Liu, Alexandra Volokhova, Aaron Courville, Yoshua Bengio.

Example

Synthetic tasks

python -m synthetic.train --data checkerboard --lr 1e-3 --type tblb --hid_layer 3 --hid 256 --print_every 100 --glr 1e-3 --zlr 1 --rand_coef 0 --back_ratio 0.5 --lin_k 1 --warmup_k 1e5 --with_mh 1

Discrete image modeling

python -m deepebm.ebm --model mlp-256 --lr 1e-4 --type tblb --hid_layer 3 --hid 256 --glr 1e-3 --zlr 1 --rand_coef 0 --back_ratio 0.5 --lin_k 1 --warmup_k 5e4 --with_mh 1 --print_every 100 --mc_num 5

DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation

DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation This project hosts the code for implementing the DCT-MASK algorithms

57 Nov 27, 2022

Official codes for the paper "Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech"

ResDAVEnet-VQ Official PyTorch implementation of Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech What is in this repo? M

21 Aug 23, 2022

This is 2nd term discrete maths project done by UCU students that uses backtracking to solve various problems.

Backtracking Project Sponsors This is a project made by UCU students: Olha Liuba - crossword solver implementation Hanna Yershova - sudoku solver impl

4 Oct 17, 2021

An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations Implementation of the method described in the Speech Resynthesis from Di

253 Jan 6, 2023

Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions

torch-imle Concise and self-contained PyTorch library implementing the I-MLE gradient estimator proposed in our NeurIPS 2021 paper Implicit MLE: Backp

249 Jan 3, 2023

Auto HMM: Automatic Discrete and Continous HMM including Model selection

29 Dec 7, 2022

This Jupyter notebook shows one way to implement a simple first-order low-pass filter on sampled data in discrete time.

How to Implement a First-Order Low-Pass Filter in Discrete Time We often teach or learn about filters in continuous time, but then need to implement t

4 Aug 24, 2022

Projecting interval uncertainty through the discrete Fourier transform

Projecting interval uncertainty through the discrete Fourier transform This repo

1 Mar 2, 2022

Implementation of the method described in the Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations Implementation of the method described in the Speech Resynthesis from Di

4 Mar 11, 2022

Comments

Question about Evaluate MDD and NLL

Dear Mr. Dinghuai,

Thanks for your great work.

I have a question about estimating MDD. As in (In Dai et al. (2020)), the MMD result is calculated within a fixed group of 4000 samples, which are loaded from a data file. Your work reports an average of 10 repeat results, each with 4000 samples. It looks like your code is missing some line of code to compute MMD. My question is do you still keep a fixed group of 4000 true samples and repeat sampling distinct 10 groups of GflowNets Sample. Or using distinct 10 groups of 4000 true samples. And, for NLL do you keep 4000 true samples fixed or not.

Thanks Mr. Dinghuai

opened by anhhndo 1
Question about learning GFN on the checkerboard dataset

Hi, Dinghuai

Thanks for your great work.

I have a question about reproducing the result on the checkerboard dataset using the GFlowNet_Randf_TB. The result I obtained was not meaningful. However, the successful result (as in the paper) can be obtained by using the learned backward policy PB GFlowNet_LearnedPb_TB.

I am a little confused why a random backward policy cannot work on the checkerboard dataset. Because I think we can always find a right forward policy corresponding to a certain backward policy. Maybe I missed something to tune.

Any comment would be quite helpful. Thanks in advance!

Best, Shanchao

opened by yangysc 0

Owner

Narsil-Dinghuai Zhang

Student @ Mila. Previous undergraduate @ Peking University.

GitHub

Generative Flow Networks

Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation Implementation for our paper, submitted to NeurIPS 2021 (also chec

381 Jan 4, 2023

Just Go with the Flow: Self-Supervised Scene Flow Estimation

Just Go with the Flow: Self-Supervised Scene Flow Estimation Code release for the paper Just Go with the Flow: Self-Supervised Scene Flow Estimation,

50 Nov 22, 2022

Drslmarkov - Distributionally Robust Structure Learning for Discrete Pairwise Markov Networks

Distributionally Robust Structure Learning for Discrete Pairwise Markov Networks

1 Nov 24, 2022

InferPy: Deep Probabilistic Modeling with Tensorflow Made Easy

InferPy: Deep Probabilistic Modeling Made Easy InferPy is a high-level API for probabilistic modeling written in Python and capable of running on top

141 Oct 13, 2022

(ICCV 2021) ProHMR - Probabilistic Modeling for Human Mesh Recovery

ProHMR - Probabilistic Modeling for Human Mesh Recovery Code repository for the paper: Probabilistic Modeling for Human Mesh Recovery Nikos Kolotouros

209 Dec 13, 2022

A Python library for Deep Probabilistic Modeling

Abstract DeeProb-kit is a Python library that implements deep probabilistic models such as various kinds of Sum-Product Networks, Normalizing Flows an

46 Dec 26, 2022

Minimal PyTorch implementation of Generative Latent Optimization from the paper "Optimizing the Latent Space of Generative Networks"

Minimal PyTorch implementation of Generative Latent Optimization This is a reimplementation of the paper Piotr Bojanowski, Armand Joulin, David Lopez-

117 Nov 27, 2022