This is the paddle code for SeBoW(Self-Born wiring for neural trees), a kind of neural tree born form a large search space

Overview

SeBoW: Self-Born Wiring for neural trees(PaddlePaddle version)

methodology

This is the paddle code for SeBoW(Self-Born wiring for neural trees), a kind of neural decision tree born form a large search space, published as a conference paper on ICCV 2021, written by [Ying Chen](https://www.vipazoo.cn/people/chenying.html) et al. The code was written by [Haoling Li](https://github.com/HollyLee2000) and Ying Chen, and supported by Jie Song. This paddle implementation produces results comparable to the original PyTorch veision.

Prerequisites

  • Linux or Window
  • Python 3
  • CPU or NVIDIA GPU + CUDA CuDNN

Getting Started

Installation

  • Clone this repo:
git clone https://github.com/HollyLee2000/SeBoW-paddle
cd SeBoW-paddle

train/test introduction

  • Edit ForestModel.py to choose your dataset and Forest structure(the original large search space), by now only Cifar100 dataset has been tested on this paddle version. If you want to conduct on other datasets you need just do some adjustment and rewirte the dataloder

  • run train_cifar100_ForestModel.py to get the result of the forest model.

  • run sender_select.py to get the output of the sender(average router probability for each section of the Forest model), then retain the node in i-th section if its conditional probability obtained from previous senders is greater than the threshold C/(2 × Ci), in the original paper, C=2 and Ci means the number of the learners in i-th section.

  • run receiver_droupout.py, choose the only parent of each node with the largest weight in sampling vectors produced by the receiver, then you will get the final tree-structure.

  • Edit Forest_to_tree.py to apply your tree-structured model, during the retraining phase you will run train_tree.py to retrain the derived neural tree from scratch

  • The inference can be executed in two manners: multi-path inference and single-path inference. Multipath inference computes the weighted predictive distribution by running over all possible paths in the derived neural tree, such that all solvers in the tree will contribute to the final prediction(you have done this). However, in the single-path inference, only the most probable paths are executed based on the routing probability from routers, which enjoys less inference cost with some accuracy drop. You can run single-inference.py to apply this, but don't forget to adjust the structure of Tree_single_inference.py

Acknowledgments

The work is inspired by VIPA.

Owner
HollyLee
HollyLee
WaveFake: A Data Set to Facilitate Audio DeepFake Detection

WaveFake: A Data Set to Facilitate Audio DeepFake Detection This is the code repository for our NeurIPS 2021 (Track on Datasets and Benchmarks) paper

Chair for Sys­tems Se­cu­ri­ty 27 Dec 22, 2022
Matching python environment code for Lux AI 2021 Kaggle competition, and a gym interface for RL models.

Lux AI 2021 python game engine and gym This is a replica of the Lux AI 2021 game ported directly over to python. It also sets up a classic Reinforceme

Geoff McDonald 74 Nov 03, 2022
MakeItTalk: Speaker-Aware Talking-Head Animation

MakeItTalk: Speaker-Aware Talking-Head Animation This is the code repository implementing the paper: MakeItTalk: Speaker-Aware Talking-Head Animation

Adobe Research 285 Jan 08, 2023
Implementation for our ICCV 2021 paper: Dual-Camera Super-Resolution with Aligned Attention Modules

DCSR: Dual Camera Super-Resolution Implementation for our ICCV 2021 oral paper: Dual-Camera Super-Resolution with Aligned Attention Modules paper | pr

Tengfei Wang 110 Dec 20, 2022
Pytorch implementation of CVPR2021 paper "MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation"

MUST-GAN Code | paper The Pytorch implementation of our CVPR2021 paper "MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generat

TianxiangMa 46 Dec 26, 2022
A Python package for causal inference using Synthetic Controls

Synthetic Control Methods A Python package for causal inference using synthetic controls This Python package implements a class of approaches to estim

Oscar Engelbrektson 107 Dec 28, 2022
Pytorch implementation of COIN, a framework for compression with implicit neural representations 🌸

COIN 🌟 This repo contains a Pytorch implementation of COIN: COmpression with Implicit Neural representations, including code to reproduce all experim

Emilien Dupont 104 Dec 14, 2022
Hypernetwork-Ensemble Learning of Segmentation Probability for Medical Image Segmentation with Ambiguous Labels

Hypernet-Ensemble Learning of Segmentation Probability for Medical Image Segmentation with Ambiguous Labels The implementation of Hypernet-Ensemble Le

Sungmin Hong 6 Jul 18, 2022
Generic image compressor for machine learning. Pytorch code for our paper "Lossy compression for lossless prediction".

Lossy Compression for Lossless Prediction Using: Training: This repostiory contains our implementation of the paper: Lossy Compression for Lossless Pr

Yann Dubois 84 Jan 02, 2023
Clustering with variational Bayes and population Monte Carlo

pypmc pypmc is a python package focusing on adaptive importance sampling. It can be used for integration and sampling from a user-defined target densi

45 Feb 06, 2022
Aesara is a Python library that allows one to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays.

Aesara is a Python library that allows one to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays.

Aesara 898 Jan 07, 2023
[SDM 2022] Towards Similarity-Aware Time-Series Classification

SimTSC This is the PyTorch implementation of SDM2022 paper Towards Similarity-Aware Time-Series Classification. We propose Similarity-Aware Time-Serie

Daochen Zha 49 Dec 27, 2022
ColossalAI-Examples - Examples of training models with hybrid parallelism using ColossalAI

ColossalAI-Examples This repository contains examples of training models with Co

HPC-AI Tech 185 Jan 09, 2023
This code provides various models combining dilated convolutions with residual networks

Overview This code provides various models combining dilated convolutions with residual networks. Our models can achieve better performance with less

Fisher Yu 1.1k Dec 30, 2022
Autonomous Driving on Curvy Roads without Reliance on Frenet Frame: A Cartesian-based Trajectory Planning Method

C++/ROS Source Codes for "Autonomous Driving on Curvy Roads without Reliance on Frenet Frame: A Cartesian-based Trajectory Planning Method" published in IEEE Trans. Intelligent Transportation Systems

Bai Li 88 Dec 23, 2022
This repository contains the code for TACL2021 paper: SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization

SummaC: Summary Consistency Detection This repository contains the code for TACL2021 paper: SummaC: Re-Visiting NLI-based Models for Inconsistency Det

Philippe Laban 24 Jan 03, 2023
SciFive: a text-text transformer model for biomedical literature

SciFive SciFive provided a Text-Text framework for biomedical language and natural language in NLP. Under the T5's framework and desrbibed in the pape

Long Phan 54 Dec 24, 2022
Unified tracking framework with a single appearance model

Paper: Do different tracking tasks require different appearance model? [ArXiv] (comming soon) [Project Page] (comming soon) UniTrack is a simple and U

ZhongdaoWang 300 Dec 24, 2022
Official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.

Vision Transformer with Progressive Sampling This is the official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.

yuexy 123 Jan 01, 2023
Context-Sensitive Misspelling Correction of Clinical Text via Conditional Independence, CHIL 2022

cim-misspelling Pytorch implementation of Context-Sensitive Spelling Correction of Clinical Text via Conditional Independence, CHIL 2022. This model (

Juyong Kim 11 Dec 19, 2022