Hi Darshan,

I am looking to extend this to real-time inference by feeding frames directly from a camera. From the documentation I have reviewed, it seems that ACL supports input files in formats like npy, jpg, and ppm.Could you please let me know if there is a recommended approach or any existing functionality in ACL to achieve this? Arm Compute Library does not support other higher level file formats like onnx or tflite. If you need to run a tflite model the best option would be ArmNNhttps://github.com/ARM-software/armnn , ArmNN has a tflite parser and uses ACL to accelerate each layer. There is a tool in ArmNN called ExecuteNetwork which can run tflite models directly, for more information about this please see the documentationhttps://github.com/ARM-software/armnn/blob/branches/armnn_24_11/docs/FAQ.md#how-can-i-run-a-pretrained-model-using-arm-nn.

ACL goal is to accelerate ML workloads, the library does not have any functionality to capture and preprocess frames. I'd suggest you look into OpenCV examples on how to implement this component of your solution.

If you have any further questions or you need help with ACL please open an issue on github.https://github.com/ARM-software/ComputeLibrary/issues

Hope this helps.

________________________________ From: Darshan B Y darshanvvce@gmail.com Sent: 23 December 2024 14:24 To: acl-dev@lists.linaro.org acl-dev@lists.linaro.org Subject: [Acl-dev] REAL-TIME INFERENCE WITH ARM COMPUTE LIBRARY

Dear ACL Development Team,

I hope this email finds you well. I am following up on my previous email regarding the implementation of real-time inference using Arm Compute Library.

To recap, I have successfully implemented inference for single images with the object detection model on ARM devices, but I am looking to extend this to real-time inference by feeding frames directly from a camera. From the documentation I have reviewed, it seems that ACL supports input files in formats like npy, jpg, and ppm.Could you please let me know if there is a recommended approach or any existing functionality in ACL to achieve this?

In case there is no built-in support, I am currently exploring the ACL source code to understand how this might be implemented. If possible, I would appreciate any advice or suggestions on how to approach this, or any resources that could assist in my efforts.

Thank you for your time and support. I look forward to hearing from you.

Best regards, Darshan B Y _______________________________________________ Acl-dev mailing list -- acl-dev@lists.linaro.org To unsubscribe send an email to acl-dev-leave@lists.linaro.org IMPORTANT NOTICE: The contents of this email and any attachments are confidential and may also be privileged. If you are not the intended recipient, please notify the sender immediately and do not disclose the contents to any other person, use it for any purpose, or store or copy the information in any medium. Thank you.