Data

Tools

Indexes

Applications

Experiments

Open Source Science

rpi-hmif

https://github.com/sssaid3688/rpi-hmif

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.9%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: sssaid3688
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 9.64 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 2 years ago · Last pushed about 2 years ago
Metadata Files
Readme License Citation

README.md

RPI-HMIF

Architecture

We highly suggest you using Anaconda to manage your python environment.

Dataset

The MNRE dataset comes from https://github.com/thecharm/Mega, many thanks. You can download the Twitter2015 and Twitter2017 dataset with detected visual objects using folloing command: bash wget 120.27.214.45/Data/ner/multimodal/data.tar.gz tar -xzvf data.tar.gz - The twitter15 dataset with detected visual objects is stored in data:

  • twitter15_detect：Detected objects using RCNN
  • twitter2015_aux_images：Detected objects using visual grouding
  • twitter2015_images： Original images
  • train.txt: Train set
  • ... ## How to install pip install -r requirements.txt python setup.py install ## How to Run

Quick start

Download the PLM and set vit_name in train.yaml and predict.yaml as the directory of the PLM.

The script run.py acts as a main function to the project, you can run the experiments by replacing the unspecified options in the following command with the corresponding values:

shell cd example/ner/multimodal CUDA_VISIBLE_DEVICES=$1 python run.py

or run the script run.py directly via pycharm.

Owner

  • Name: OH
  • Login: sssaid3688
  • Kind: user

Citation (CITATION.cff) 

cff-version: "1.0.0"
message: "If you use this toolkit, please cite it using these metadata."
title: "deepke"
repository-code: "https://https://github.com/zjunlp/DeepKE"
authors: 
  - family-names: Zhang
    given-names: Ningyu
  - family-names: Xu
    given-names: Xin
  - family-names: Tao
    given-names: Liankuan
  - family-names: Yu
    given-names: Haiyang
  - family-names: Ye
    given-names: Hongbin
  - family-names: Qiao
    given-names: Shuofei
  - family-names: Xie
    given-names: Xin
  - family-names: Chen
    given-names: Xiang
  - family-names: Li
    given-names: Zhoubo
  - family-names: Li
    given-names: Lei
  - family-names: Liang
    given-names: Xiaozhuan
  - family-names: Yao
    given-names: Yunzhi
  - family-names: Deng
    given-names: Shumin
  - family-names: Wang
    given-names: Peng
  - family-names: Zhang
    given-names: Wen
  - family-names: Zhang
    given-names: Zhenru
  - family-names: Tan
    given-names: Chuanqi
  - family-names: Chen
    given-names: Qiang
  - family-names: Xiong
    given-names: Feiyu
  - family-names: Huang
    given-names: Fei
  - family-names: Zheng
    given-names: Guozhou
  - family-names: Chen
    given-names: Huajun
preferred-citation:
  type: article
  title: "DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population"
  authors:
  - family-names: Zhang
    given-names: Ningyu
  - family-names: Xu
    given-names: Xin
  - family-names: Tao
    given-names: Liankuan
  - family-names: Yu
    given-names: Haiyang
  - family-names: Ye
    given-names: Hongbin
  - family-names: Qiao
    given-names: Shuofei
  - family-names: Xie
    given-names: Xin
  - family-names: Chen
    given-names: Xiang
  - family-names: Li
    given-names: Zhoubo
  - family-names: Li
    given-names: Lei
  - family-names: Liang
    given-names: Xiaozhuan
  - family-names: Yao
    given-names: Yunzhi
  - family-names: Deng
    given-names: Shumin
  - family-names: Wang
    given-names: Peng
  - family-names: Zhang
    given-names: Wen
  - family-names: Zhang
    given-names: Zhenru
  - family-names: Tan
    given-names: Chuanqi
  - family-names: Chen
    given-names: Qiang
  - family-names: Xiong
    given-names: Feiyu
  - family-names: Huang
    given-names: Fei
  - family-names: Zheng
    given-names: Guozhou
  - family-names: Chen
    given-names: Huajun
  journal: "http://arxiv.org/abs/2201.03335"
  year: 2022

GitHub Events

Total
Last Year

Dependencies

docker/Dockerfile docker
  • ubuntu 18.04 build
requirements.txt pypi
  • Jinja2 ==3.1.2
  • datasets ==2.13.2
  • huggingface_hub ==0.11.0
  • hydra-core ==1.0.6
  • ipdb ==0.13.11
  • jieba ==0.42.1
  • matplotlib ==3.4.1
  • nltk ==3.8
  • numpy ==1.21.0
  • openai ==0.28.0
  • opt-einsum ==3.3.0
  • protobuf ==3.20.1
  • pyhocon ==0.3.60
  • pytorch-crf ==0.7.2
  • scikit-learn ==0.24.1
  • seqeval ==1.2.2
  • tensorboard ==2.4.1
  • tensorboardX ==2.5.1
  • torch >=1.5,<=1.11
  • tqdm ==4.66.1
  • transformers ==4.26.0
  • ujson ==5.6.0
  • wandb ==0.12.7
setup.py pypi