Workflows with Ikomia API
You can create a workflow using our Python API.
Installation
As Ikomia API automatically installs algorithm dependencies, we strongly recommend using a virtual environment to avoid conflicts with your system packages.
- Windows
- bash/zsh
python -m venv .venv
.venv\Scripts\Activate.bat
python -m venv .venv
source .venv/bin/activate
Just install the Ikomia package and the CLI using pip:
pip install ikomia ikomia-cli
Make your own workflow
Here's a minimal code example demonstrating how to create a workflow that blurs faces in an image using the Ikomia API:
from ikomia.dataprocess.workflow import Workflow
from ikomia.utils.displayIO import display
from ikomia.utils import ik
wf = Workflow()
face = wf.add_task(ik.infer_face_detection_kornia(), auto_connect=True)
blur = wf.add_task(ik.ocv_blur(kSizeWidth="61", kSizeHeight="61"), auto_connect=True)
wf.run_on(url="https://raw.githubusercontent.com/Ikomia-dev/notebooks/main/examples/img/img_people.jpg")
display(blur.get_output(0).get_image())
For a step-by-step guide and more detailed examples, please refer to our Python API documentation.
Push a workflow to SCALE
To push your workflow, first export it to a JSON file using the Workflow.save method:
wf.save("path/to/your/workflow.json")
Once you have your workflow file, log in to your Ikomia account:
ikcli login
# Export generated access token to your environment variables:
export IKOMIA_TOKEN=<your_access_token>
If you have not defined a password on your account, you can generate an access token from your settings and export it to your environment variables directly.
Then, use the Ikomia CLI push command:
ikcli project push <ProjectName> <path/to/your/workflow.json>
Under the hood, the CLI will package your JSON workflow file alongside the algorithms it depends on and upload them to SCALE.
You will then be able to see your workflow in the project you specified from the SCALE dashboard. From there, you'll be able to deploy it on the infrastructure of your choice.