-
-
Notifications
You must be signed in to change notification settings - Fork 60
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Created FAQ.md #131
Created FAQ.md #131
Changes from 1 commit
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,74 @@ | ||
# Frequently Asked Questions (FAQs) | ||
|
||
## Users | ||
**Q : What is fAIr?** | ||
|
||
A : fAIr is an open-source toolkit developed by the Humanitarian OpenStreetMap Team (HOT) that enables the integration of artificial intelligence (AI) into humanitarian mapping workflows. It provides AI models and tools to automate mapping tasks, improving efficiency and accuracy. | ||
|
||
<hr> | ||
|
||
**Q : How can I use fAIr in my mapping projects?** | ||
|
||
A : To use fAIr, you can follow the installation instructions provided in the documentation. Once installed, you can utilize the pre-trained AI models for tasks such as road network extraction, building footprint detection, or land use classification. The documentation offers examples and guidelines to help you get started. | ||
|
||
<hr> | ||
|
||
**Q : What types of data can I use with fAIr?** | ||
|
||
A : fAIr primarily works with satellite imagery and aerial photographs. You can use various types of imagery sources, including public satellite imagery datasets, to perform mapping tasks using the AI models provided. The documentation provides information on the compatible data formats and recommended data sources. | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Various source of imagery which compiles with opensource imagery license There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Done |
||
|
||
<hr> | ||
|
||
**Q : Can I customize the AI models in fAIr for my specific needs?** | ||
|
||
A : Yes, fAIr is designed to be customizable. The toolkit provides instructions and guidelines on how to train and fine-tune models with your own datasets. This allows you to adapt the models to suit your specific mapping requirements and improve their performance on your target areas or features of interest. | ||
|
||
<hr> | ||
|
||
**Q : Are there any limitations to using fAIr?** | ||
|
||
A : While fAIr offers powerful AI models, it's important to note that the accuracy of the results may vary depending on the quality and resolution of the input imagery and the complexity of the mapping task. Some tasks may require additional manual editing or validation. It's recommended to review the documentation and understand the limitations of each model before use. | ||
|
||
<hr> | ||
|
||
**Q : How can I contribute feedback or report issues with fAIr?** | ||
|
||
A : You can contribute to the improvement of fAIr by providing feedback, reporting issues, or suggesting new features through the project's GitHub repository. By creating an issue, you can share your observations or difficulties faced while using fAIr, allowing the developers to address them and enhance the toolkit. | ||
|
||
<hr> | ||
|
||
**Q : Can I integrate fAIr with other mapping tools or platforms?** | ||
|
||
A : Yes, fAIr is designed to be modular and can be integrated into existing mapping workflows and platforms. It provides interoperability with tools like OpenStreetMap, QGIS, and ArcGIS. You can leverage the AI models from fAIr within these tools or use the outputs of fAIr in combination with other mapping datasets and tools. | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. It provides modular pip packages/ API endpoints that can be used in other scripts and can be integrated as plugins on different platforms such as Qgis, Josm etc There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Done |
||
|
||
<hr> | ||
|
||
## Developers | ||
|
||
**Q : How can I contribute to the development of fAIr?** | ||
|
||
A : You can contribute to fAIr's development by following the guidelines provided in the project's GitHub repository. You can contribute code, suggest new features, or help improve documentation. By submitting pull requests, you can propose changes and collaborate with the project maintainers and the community. | ||
|
||
<hr> | ||
|
||
**Q : What programming languages and frameworks are used in fAIr?** | ||
|
||
A : fAIr frontend is made with React and backend with Django.fAIr is primarily developed using Python, which is widely used in machine learning and AI. It leverages popular frameworks such as PyTorch and TensorFlow for model development and training. Familiarity with Python and these frameworks will be beneficial if you plan to work on fAIr's development. | ||
omranlm marked this conversation as resolved.
Show resolved
Hide resolved
|
||
|
||
<hr> | ||
|
||
**Q : Are there any specific coding standards or guidelines for contributing to fAIr?** | ||
|
||
A : Yes, fAIr follows coding standards and guidelines outlined in the project's repository. These guidelines cover aspects such as code formatting, documentation, and testing. Adhering to these standards helps maintain code consistency and facilitates collaboration among contributors. | ||
|
||
<hr> | ||
|
||
**Q : Can I propose new AI models or enhancements to existing models?** | ||
|
||
A : Absolutely! The fAIr project welcomes contributions related to new AI models or enhancements to existing models. If you have developed a new model that aligns with the project's goals or if you have ideas to improve the current models, you can propose them through the GitHub repository and engage in discussions with the community or you can create them at [here](https://fair-dev.hotosm.org/ai-models) . | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Advised to Remove last or part , once approved community will be able go use it , link them to fAIr-utilities There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Removed the last or part . But I am unable to get the fAIr utilities. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. @neelimagoogly fAIr repo is the one handing backend and frontend components .. However, the backend is using s separate library we call it fAIr-utilities to handle:
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Thanks @omranlm . I have made the change and linked it to fAIr utilities. |
||
|
||
<hr> | ||
|
||
**Q : What kind of support can I expect as a developer contributing to fAIr?** | ||
|
||
A : As a developer contributing to fAIr, you can receive support and guidance from the project maintainers and the community. The maintainers can help address technical questions, review your contributions, and provide feedback. The community also offers a collaborative environment where you can interact with other contributors and share knowledge. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Add a clause here , Building for now
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done