Inferencing on Image rather than Videos

Hi!
I currently have both the Hailo8 and Hailo8L modules. I would like to ask if it’s possible to run inferencing on static images rather than videos. All the examples that I could find thus far only demonstrates how detection can be run on .mp4 files.

Would great appreciate any help.

Thank you!

Yes, you can run inference on single images. The Hailo-8 does not need to know the source of the data. The application handles the preprocessing of the source data, converting it into an array of numbers in the format expected by the model, and sends this data to the Hailo-8 to run through the model.

Here is an example that supports both video and single images.

GitHub - Hailo Application Code Examples - General Detection Inference

Hi
Are there any such examples in Python?

@fabrice.auzanneau
You can take a look at our PySDK User Guide to see how to do this: User Guide 1 Hailo World: Running Your First Inference on a Hailo Device Using DeGirum PySDK

Thanks a lot @shashi I’ll have a look !