wd-v1-4-convnextv2-tagger-v2

我要开发同款
匿名用户2024年07月31日
25阅读
所属分类aiPytorch
开源地址https://modelscope.cn/models/mirror013/wd-v1-4-convnextv2-tagger-v2
授权协议apache-2.0

作品详情

WD 1.4 ConvNextV2 Tagger V2

Supports ratings, characters and general tags.

Trained using https://github.com/SmilingWolf/SW-CV-ModelZoo.
TPUs used for training kindly provided by the TRC program.

Dataset

Last image id: 5944504
Trained on Danbooru images with IDs modulo 0000-0899.
Validated on images with IDs modulo 0950-0999.
Images with less than 10 general tags were filtered out.
Tags with less than 600 images were filtered out.

Validation results

P=R: threshold = 0.3710, F1 = 0.6862

Final words

Subject to change and updates.
Downstream users are encouraged to use tagged releases rather than relying on the head of the repo.

声明:本文仅代表作者观点,不代表本站立场。如果侵犯到您的合法权益,请联系我们删除侵权资源!如果遇到资源链接失效,请您通过评论或工单的方式通知管理员。未经允许,不得转载,本站所有资源文章禁止商业使用运营!
下载安装【程序员客栈】APP
实时对接需求、及时收发消息、丰富的开放项目需求、随时随地查看项目状态

评论