Won't opencv-python and opencv-contrib-python conflict with each other? They are both in requirements!

[sisrfeng]

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem

• 系统环境/System Environment：
• 版本号/Version：Paddle： PaddleOCR： 问题相关组件/Related components：
• 运行指令/Command Code：
• 完整报错/Complete Error Message：

我们提供了AceIssueSolver来帮助你解答问题，你是否想要它来解答(请填写yes/no)?/We provide AceIssueSolver to solve issues, do you want it? (Please write yes/no):no

请尽量不要包含图片在问题中/Please try to not include the image in the issue.

From google's Bard

You're absolutely right! Having both opencv-python and opencv-contrib-python listed in the requirements.txt of the PaddleOCR GitHub repository can indeed lead to conflicts. Here's why:

1. Redundancy: opencv-contrib-python is essentially an extension of opencv-python, containing additional modules and algorithms. Installing both packages installs many of the same files, potentially causing version clashes and unexpected behavior.
2. Version Mismatch: If the specified versions of opencv-python and opencv-contrib-python differ, pip might not be able to resolve the conflict, leading to installation errors or missing functionalities.
3. Dependency Issues: Other dependencies in the project might have specific requirements for either opencv-python or opencv-contrib-python. Having both listed could lead to unexpected dependency conflicts for those libraries.

Solutions:

There are a couple of ways to address this redundancy and potential conflict:

• Use opencv-contrib-python only: Since it includes all functionalities of opencv-python, using only opencv-contrib-python is sufficient. This simplifies the dependency list and avoids potential conflicts.
• Specify version compatibility: If there are specific reasons for needing both packages, ensure their versions are compatible and explicitly specify them in the requirements.txt using version specifiers (e.g., opencv-python==4.5.5, opencv-contrib-python==4.5.5).
• Consider alternatives: Depending on your specific needs, there might be alternative libraries or functionalities within PaddleOCR that can replace the need for both opencv-python and opencv-contrib-python.

It's generally recommended to avoid having both packages listed unless absolutely necessary. Choosing the appropriate approach depends on your specific requirements and the functionalities you need in your project.

I hope this explanation clarifies the potential conflict and provides helpful solutions!