Skip to main content

MMKG Models

Project description

视觉关系检测使用说明

1. 算法描述

该算法用于图像中的视觉关系检测(VRD)。该算法基于PyTorch框架开发,输入一张图片,算法会检测图片中的视觉关系对。

2. 依赖及安装

CUDA版本: 11.3 其他依赖库的安装命令如下:

conda install pytorch==1.10.1 torchvision==0.11.2 torchaudio==0.10.1 cudatoolkit=11.3 -c pytorch -c conda-forge

可使用如下命令下载安装算法包:

pip install -U mmkg-vrd

3. 使用示例及运行参数说明

需要准备 pretrained_ckpt, labelmap_file, freq_prior 三个文件,可以通过 mmkg-vrd 上所提供的链接进行下载

from mmkg_vrd import VRD

vrd = VRD(
    pretrained_ckpt='custom_io/ckpt/RX152FPN_reldn_oi_best.pth',
    labelmap_file='custom_io/ji_vrd_labelmap.json', 
    freq_prior='custom_io/vrd_frequency_prior_include_background.npy', 
)

vrd.det_and_vis(
    img_file='custom_io/imgs/1024px-Gen_Robert_E_Lee_on_Traveler_at_Gettysburg_Pa.jpg',
    save_file='custom_io/out/1024px-Gen_Robert_E_Lee_on_Traveler_at_Gettysburg_Pa.reldn_relation.jpg')

print('all done')

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

mmkg_vrd-0.2.0-cp37-cp37m-manylinux1_x86_64.whl (5.5 MB view details)

Uploaded CPython 3.7m

File details

Details for the file mmkg_vrd-0.2.0-cp37-cp37m-manylinux1_x86_64.whl.

File metadata

File hashes

Hashes for mmkg_vrd-0.2.0-cp37-cp37m-manylinux1_x86_64.whl
Algorithm Hash digest
SHA256 c93e6e55b9f653b83c6e30043b2c0a11dbb6a9879d337322620a84020e3e9154
MD5 9a2b196eb75716ee10639282b023ff9d
BLAKE2b-256 5509db93129e22e4150f5a829b5a0ec399213f74e6198c4ebe4d5a477da97966

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page