Parallel acceleration for detection models

Question

Parallel acceleration for detection models

Closed this issue a year ago · 6 comments

@LewisLiuPub is possible to get the functionality to have parallel execution for detection models as similar to this PR? - #143. Would be very useful to get faster speeds especially on the Movidius VPU

Answer 1 · 2021-03-24T05:42:29.000Z

Hi, @joelbudu
Do you need to input multiple data from several cameras? or only use one camera but want to execute the inference by several Movidius VPUs in parallel?

Answer 2 · 2021-03-24T05:44:25.000Z

@LewisLiuPub I would like to use one camera but execute the inference by several Movidius VPUs in parallel, please.

Answer 3 · 2021-03-24T05:47:39.000Z

@joelbudu Can you let me know more, which model(s) are you using in this case?

Answer 4 · 2021-03-24T06:00:10.000Z

Object Detection -> YOLOV2
Object Segmentation -> MaskRCNN

Answer 5 · 2023-04-26T07:43:35.000Z

To update the status for multiple pipeline supporting and yolo/maskrcnn supporting:

Yolov2 is deprecated. Instead, Yolov5 is supported.
instance segmentation (maskrcnn, deeplabv3) is supported on branch ros2 (enabled for ros2 foxy/galactic)

Answer 6 · 2023-04-26T08:45:37.000Z

Thank you for working on this @LewisLiuPub