Computer Vision Platform, Open Ecosystem of Apps, SDK for Python
Table of contents
- Introduction
- Supervisely Platform
- Supervisely Ecosystem
- Development
- What developers can do
- Principles
- Main features
- Community
- Contribution
- Partnership
Introduction
Every company wants to ensure that its current and future AI tasks are solvable. The main issue with most solutions on the market is that they behave like products designed as a black box, where the owner holds the reins. When your needs outgrow basic features and require customization, you’re often left in the lurch. This is why Supervisely is building a platform instead of a product.
Supervisely Platform
Imagine a vibrant city inhabited by tools, apps, and services, all working in unison—this is what Supervisely embodies! Just like an operating system, Supervisely unites various tools within a Ecosystem designed for the smooth development of AI.
- Data labeling across diverse formats including images, videos, and 3D point clouds.
- Interactive tools for deep learning model performance analysis, enabling a hands-on experience.
- AI-assisted labeling tools to speed up data processing.
Supervisely Ecosystem
Just like an app store filled with diverse applications ready to cater to user needs, the Supervisely ecosystem consists of numerous applications that perform tasks at the click of a button—be it labeling data or running neural networks. It’s the one-stop-shop for your computer vision needs.
Development
Similar to how a home requires a solid foundation, Supervisely provides the framework necessary for developing, customizing, and operating computer vision applications. The platform ensures you can pick the level of customization and integration that suits your tasks.
What developers can do
Developers can leverage Supervisely’s power through multiple levels of integration:
- HTTP REST API
- Python scripts for automation and integration
- Headless apps (without UI)
- Apps with interactive UIs
- Apps integrated into labeling tools
Level 1. HTTP REST API
The HTTP REST API is the **web’s equivalent of a toolbox**—instead of physical tools, you’re provided with a rich set of functions that enable you to manipulate and access your data. Using any programming language, you can craft requests to interface with Supervisely, taking control of various operations.
curl -H "x-api-key: your-token-here" https://app.supervise.ly/public/api/v3/projects.listLevel 2. Python scripts for automation and integration
The Supervisely SDK for Python acts like a smart assistant in your computer vision project. Just a few lines of Python code can perform complicated tasks such as managing data and invoking labels, enhancing development speed and efficiency.
import supervisely as sly
api = sly.Api.from_env() # authenticate
# create project and dataset
project = api.project.create(workspace_id=123, name="demo project")
dataset = api.dataset.create(project.id, "dataset-01")Level 3. Headless apps (without UI)
Headless apps are akin to a background operations crew—working tirelessly to perform tasks without needing visual interfaces. Developers can create scripts to automate routine activities easily and efficiently.
Level 4. Apps with interactive UIs
The importance of an engaging UI is similar to a storefront for a business—it’s what attracts users and encourages interaction. Supervisely allows developers to craft interactive user interfaces and visual tools, enhancing user engagement.
Level 5. Apps with UI integrated into labeling tools
This level provides the ability to smoothly blend applications into existing workflows—essentially merging two different worlds (the app and the tool) to create a singular, seamless experience for users.
Principles
Development at Supervisely is built upon several foundational principles:
- All applications are born from pure Python.
- No front-end experience is necessary to build interactive apps.
- Easy learning curve with everything customizable.
Main features
Community
Join a growing community with over 65,000 users. Your insights or questions can significantly contribute to the fabric of the ecosystem.
Contribution
Thinking about contributing? You can help propel computer vision R&D forward by collaborating with the Supervisely Ecosystem.
Partnership
Looking to expand your reach and offer solutions together? Supervisely welcomes partnerships that align with our goals to enhance the ecosystem.
Troubleshooting
If you face any issues while navigating your way through the Supervisely platform or its features, here are some troubleshooting ideas:
- Ensure your API key is valid and active for successful requests.
- Check if the required dependencies are correctly installed.
- Utilize the extensive documentation available at Supervisely Developer Documentation.
For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.
At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.