Getting Started with Ikomia: Simplifying Computer Vision Deployment

Welcome to the world of Ikomia, where we aim to transform intricate computer vision algorithms into simplified, deployable solutions for both enthusiasts and professionals alike!

Why Choose Ikomia?

• Research Meets Reality: Ikomia bridges the gap between cutting-edge research and practical applications. Access algorithms from trusted sources like OpenCV, Detectron2, OpenMMLab, and Hugging Face.
• Unified Framework: Forget about cumbersome integration issues. Create workflows and integrate algorithms effortlessly.
• Empowerment: We’re dedicated to building a community around AI and computer vision, encouraging collaboration and innovation at every step.

Getting Started

Installation

Begin your journey with Ikomia by installing it using pip:

pip install ikomia

Quick Examples

Object Detection

Let’s dive into some code. To detect objects in an image, you can use the following:

python
from ikomia.dataprocess.workflow import Workflow
from ikomia.utils.displayIO import display

wf = Workflow()
yolov7 = wf.add_task(name=infer_yolo_v7, auto_connect=True)
wf.run_on(url=https://raw.githubusercontent.com/Ikomia-dev/notebooks/main/examples/img/img_fireman.jpg)
display(yolov7.get_image_with_graphics())

In this analogy, think of the code as a recipe for a delicious cake. The from ikomia.dataprocess.workflow import Workflow line is like gathering your ingredients. The wf = Workflow() is mixing them together, and the wf.run_on(url=...) is pouring the batter into a pre-heated oven. Finally, display(yolov7.get_image_with_graphics()) is like taking the freshly baked cake out and showcasing it at a party!

Pose Estimation

You can also estimate poses with a similar structure:

python
wf = Workflow()
pose_estimation = wf.add_task(name=infer_mmlab_pose_estimation, auto_connect=True)
wf.run_on(url=https://raw.githubusercontent.com/Ikomia-dev/notebooks/main/examples/img/img_fireman.jpg)
display(pose_estimation.get_image_with_graphics())

Exporting Your Workflow

Sharing your workflows is as easy as pie! Use the code below to export your project:

python
wf = Workflow(Instance Segmentation with YOLOv7)
yolov7 = wf.add_task(ik.infer_yolo_v7_instance_segmentation(), auto_connect=True)
filter_task = wf.add_task(ik.ik_instance_segmentation_filter(categories='dog', confidence=0.90), auto_connect=True)
wf.save(path='your_workflow.json')

Troubleshooting

If you encounter issues during installation or while executing your code, consider the following troubleshooting steps:

• Ensure that you have the correct version of Python installed (3.8, 3.9, 3.10, or 3.11).
• Make sure all image URLs are valid and accessible.
• Check for typos in your code; they can lead to frustrating errors.

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

Comprehensive Documentation

For those who love to dive deeper, our comprehensive documentation is a goldmine containing detailed information from basic setups to advanced configurations.

Contributing

We believe in the power of community. If you have suggestions or improvements, we’d love to hear from you!

License

Ikomia is licensed under the Apache-2.0 License, promoting open-source development and collaboration.

Support & Feedback

Your feedback is essential in our journey. Drop us an email at team@ikomia.com or join our discord channel to connect!

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.