Press "Enter" to skip to content

一键深度学习:将常用深度学习算法集成在ImagePy软件

本站内容均来自兴趣收集,如不慎侵害的您的相关权益,请留言告知,我们将尽快删除.谢谢.

日常工作中,调用深度学习算法通常需要在命令行中进行,该过程通常涉及复杂的流程,比如修改配置文件、指定文件路径、打开命令行调用算法运行。此时如果能有一个图形界面软件实现“一键调用”,就会极大地节省工作量,提高工作效率,避免来来回回地反复修改文件、执行命令等。

 

最近新写了一个库,就是把常用的深度学习算法都集成在了ImagePy中,这样用户和开发者就能直接在ImagePy中愉快地“玩”算法了。

 

OneButtonDeepLearning

 

该仓库在 这里https://github.com/qixinbo/OneButtonDeepLearning

 

宗旨就是:让深度学习算法触手可及、一键调用,不必每次在命令行进行复杂配置。

 

使用方法

 

只需将要使用的模型文件夹复制到 imagepy/plugins 文件夹下,再次启动ImagePy后即可在菜单栏看到该算法。

 

配置环境

 

如果运行深度学习算法的环境没有事先搭建好,那幺在模型的 menus 下都有一个配置文件,直接运行:

 

pip install -r requirements.txt

 

即可下载相应的依赖包。

 

当前模型

 

光学字符识别OCR

 

PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools that help users train better models and apply them into practice.

 

 

目标检测YOLOv5

 

YOLOv5 is a family of compound-scaled object detection models trained on the COCO dataset.

 

 

人脸识别

 

InsightFace is an open source 2D&3D deep face analysis toolbox, and efficiently implements a rich variety of state of the art algorithms of face recognition, face detection and face alignment, which optimized for both training and deployment.

 

 

胞状物体分割Cellpose

 

Cellpose is a generalist algorithm for cell and nucleus segmentation.

 

 

胞状物体分割BulkSeg

 

BulkSeg which is inspired by Cellpose, is a fast and generalist algorithm for segmenting bulk-like objects.

物体分割DeepLab

 

DeepLab is a state-of-art deep learning model for semantic image segmentation, where the goal is to assign semantic labels (e.g., person, dog, cat and so on) to every pixel in the input image.

Be First to Comment

发表评论

您的电子邮箱地址不会被公开。 必填项已用*标注