A package for tagging photo, all the tags will be combine to a sentence.
Project description
light-tagger简单的打标工具,可以用于实现各类打标并合并成一句话。
目录
Top News
2023-08:仓库创建,更新wd14打标。
所需环境
按需要的requirements.txt配置即可
pip install -r requirements.txt
(Optional) 为了方便调用,可使用
pip install light-tagger
或者
git clone https://github.com/bubbliiiing/light-tagger.git
cd light-tagger
python setup.py install
快速安装。
然后,我们就可以在别的project里面使用light-tagger。
预测步骤
a、Demo
- 下载完库后解压,运行predict.py即可。
python predict.py
b、在别的项目中使用light-tagger**。
- 首先导入TaggerPredictor。
from light_tagger import TaggerPredictor
- 根据模型名称创建模型。
# "SmilingWolf/wd-v1-4-convnext-tagger-v2"
# "SmilingWolf/wd-v1-4-convnextv2-tagger-v2.onnx"
# "SmilingWolf/wd-v1-4-swinv2-tagger-v2"
# "SmilingWolf/wd-v1-4-vit-tagger-v2"
model_name = "SmilingWolf/wd-v1-4-convnext-tagger-v2"
model = TaggerPredictor(model_name)
- 传入图片并且进行预测
model(raw_image)
输入输出格式
a、inputs
当前必要输入为image。
无论是numpy格式还是PIL均可,使用RGB色域。
b、outputs
当前输出均为字典,通过不同的key调用不同的输出。
1.wd14
sentence代表打标结果汇总的一句话;
probs代表相对于总标签集合,每个标签的得分;
tags_list代表打标结果对应的list;
{
"sentence": "general, sensitive, 1girl, long hair, smile, shirt, sitting, outdoors, barefoot, water, plaid, ocean, animal, beach, dog, leash, sand, plaid shirt",
"tags_list": ['general', 'sensitive', '1girl', 'long hair', 'smile', 'shirt', 'sitting', 'outdoors', 'barefoot', 'water', 'plaid', 'ocean', 'animal', 'beach', 'dog', 'leash', 'sand', 'plaid shirt'],
"probs": [3.5740888e-01, 6.6963732e-01, 4.4209361e-03, ... 4.7683716e-06, 7.1525574e-07, 4.7683716e-07],
}
Reference
Project details
Release history Release notifications | RSS feed
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
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file light_tagger-0.0.2-py3-none-any.whl.
File metadata
- Download URL: light_tagger-0.0.2-py3-none-any.whl
- Upload date:
- Size: 16.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c2040b24acf653c402039967938b91b348cd07943e117fa2d035b52c554dcb39
|
|
| MD5 |
c579e5a4fb9fdd738ca38cb794012602
|
|
| BLAKE2b-256 |
14dc22763e2095f62ace46dece44feaa7436ee9b948868d5b53ea98f1b3150d0
|