A Benchmark For Measuring Systematic Generalization of Multi-Hierarchical Reasoning

Related tags

Deep LearningOrchard
Overview

Orchard Dataset

This repository contains the code used for generating the Orchard Dataset, as seen in the Multi-Hierarchical Reasoning in Sequences: State-of-the-Art Neural Sequence Models Fail To Generalize paper. The coode to train and test Transformers and Bi-directional LSTM models was adapted from
Fairseq.

Software Requirements

Python 3.6, PyTorch 1.4 are required for the current codebase. Install apex to enable fp16 training.

Steps

  1. Install PyTorch and apex by running pip install -r requirements.txt

  2. Generate Orchard

  • Generate Orchard-easy Dataset with MIN-MAX operators. python generate_tree.py --c 0 --mm --size 50 --dir /path_to_data/

    • Generate Orchard-hard Dataset with FIRST-LAST operators. python generate_tree.py --c 1.0 --fl --size 50 --dir /path_to_data/
  1. Pre-process Dataset

    • Pre-process Dataset to generate translation dictionaries python preprocess.py --trainpref /path_to_data/train --validpref /path_to_data/valid --source-lang input --target-lang label --task translation --testpref /path_to_data --destdir /path_to_data
  2. Train model

    • Train Transformer python train.py /path_to_data/ --save-dir /path_to_data/ --task translation --source-lang input --target-lang label --batch-size 128 --arch transformer --optimizer adam --lr 5e-4 --lr-scheduler inverse_sqrt --fp16 --adam-betas '(0.9, 0.98)' --weight-decay 1.2e-6 --clip-norm 1. --dropout 0.3 --save-interval 50 --max-epoch 500

    • Train LSTM python train.py data-orchard-mmc --save-dir data-orchard-mmc --task translation --arch lstm --source-lang input --target-lang label --batch-size 128 --save-interval 100 --max-epoch 500 --lr 5e-3 --fp16

  3. Generate predictions

    • Test model on depth of tree 7 python generate.py /path_to_data/test7 --path /path_to_data/checkpoint500.pt --batch-size 32 --beam 5
Owner
Bill Pung
Data Scientist working on Artificial Intelligence. Happy to connect on LinkedIn: https://www.linkedin.com/in/billptw/
Bill Pung
Semantic similarity computation with different state-of-the-art metrics

Semantic similarity computation with different state-of-the-art metrics Description • Installation • Usage • License Description TaxoSS is a semantic

6 Jun 22, 2022
Semantic segmentation task for ADE20k & cityscapse dataset, based on several models.

semantic-segmentation-tensorflow This is a Tensorflow implementation of semantic segmentation models on MIT ADE20K scene parsing dataset and Cityscape

HsuanKung Yang 83 Oct 13, 2022
Image-Scaling Attacks and Defenses

Image-Scaling Attacks & Defenses This repository belongs to our publication: Erwin Quiring, David Klein, Daniel Arp, Martin Johns and Konrad Rieck. Ad

Erwin Quiring 163 Nov 21, 2022
A new framework, collaborative cascade prediction based on graph neural networks (CCasGNN) to jointly utilize the structural characteristics, sequence features, and user profiles.

CCasGNN A new framework, collaborative cascade prediction based on graph neural networks (CCasGNN) to jointly utilize the structural characteristics,

5 Apr 29, 2022
A Moonraker plug-in for real-time compensation of frame thermal expansion

Frame Expansion Compensation A Moonraker plug-in for real-time compensation of frame thermal expansion. Installation Credit to protoloft, from whom I

58 Jan 02, 2023
This is RFA-Toolbox, a simple and easy-to-use library that allows you to optimize your neural network architectures using receptive field analysis (RFA) and create graph visualizations of your architecture.

ReceptiveFieldAnalysisToolbox This is RFA-Toolbox, a simple and easy-to-use library that allows you to optimize your neural network architectures usin

84 Nov 23, 2022
A cross-lingual COVID-19 fake news dataset

CrossFake An English-Chinese COVID-19 fake&real news dataset from the ICDMW 2021 paper below: Cross-lingual COVID-19 Fake News Detection. Jiangshu Du,

Yingtong Dou 11 Dec 01, 2022
Vehicles Counting using YOLOv4 + DeepSORT + Flask + Ngrok

A project for counting vehicles using YOLOv4 + DeepSORT + Flask + Ngrok

Duong Tran Thanh 37 Dec 16, 2022
Cluttered MNIST Dataset

Cluttered MNIST Dataset A setup script will download MNIST and produce mnist/*.t7 files: luajit download_mnist.lua Example usage: local mnist_clutter

DeepMind 50 Jul 12, 2022
PyTorch implementations of neural network models for keyword spotting

Honk: CNNs for Keyword Spotting Honk is a PyTorch reimplementation of Google's TensorFlow convolutional neural networks for keyword spotting, which ac

Castorini 475 Dec 15, 2022
Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers

Official TensorFlow implementation of the unsupervised reconstruction model using zero-Shot Learned Adversarial TransformERs (SLATER). (https://arxiv.

ICON Lab 22 Dec 22, 2022
Multi Task RL Baselines

MTRL Multi Task RL Algorithms Contents Introduction Setup Usage Documentation Contributing to MTRL Community Acknowledgements Introduction M

Facebook Research 171 Jan 09, 2023
Implementation of H-UCRL Algorithm

Implementation of H-UCRL Algorithm This repository is an implementation of the H-UCRL algorithm introduced in Curi, S., Berkenkamp, F., & Krause, A. (

Sebastian Curi 25 May 20, 2022
[CVPR2021] Invertible Image Signal Processing

Invertible Image Signal Processing This repository includes official codes for "Invertible Image Signal Processing (CVPR2021)". Figure: Our framework

Yazhou XING 281 Dec 31, 2022
Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch.

SE3 Transformer - Pytorch Implementation of SE3-Transformers for Equivariant Self-Attention, in Pytorch. May be needed for replicating Alphafold2 resu

Phil Wang 207 Dec 23, 2022
Rule Based Classification Project For Python

Rule-Based-Classification-Project (ENG) Business Problem: A game company wants to create new level-based customer definitions (personas) by using some

Deniz Can OĞUZ 4 Oct 29, 2022
Local-Global Stratified Transformer for Efficient Video Recognition

DualFormer This repo is the implementation of our manuscript entitled "Local-Global Stratified Transformer for Efficient Video Recognition". Our model

Sea AI Lab 19 Dec 07, 2022
[CoRL 21'] TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo

TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo Lukas Koestler1*    Nan Yang1,2*,†    Niclas Zeller2,3    Daniel Cremers1

TUM Computer Vision Group 744 Jan 04, 2023
Official Pytorch Implementation of: "Semantic Diversity Learning for Zero-Shot Multi-label Classification"(2021) paper

Semantic Diversity Learning for Zero-Shot Multi-label Classification Paper Official PyTorch Implementation Avi Ben-Cohen, Nadav Zamir, Emanuel Ben Bar

28 Aug 29, 2022
ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet, ICCV 2021 Update: 2021/03/11: update our new results. Now our T2T-ViT-14 w

YITUTech 1k Dec 31, 2022