- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I'm trying to queue multiple images for inferencing on NCS with NCSDK v2 APIs. Here, I'm assuming that multiple images are processed in a batch and returns output. Presently images are being sent for inferencing in a loop sequentially like this:
for img in range(list_img):
graph.queue_inference_with_fifo_elem(fifoIn, fifoOut, img, 'user object')
My concern is:
- Can you please confirm, is there a better way for using v2 APIs for batch processing?
- I'm assuming that, if a single image takes 500ms for inferencing and if we submit 5 images in a queue, the inferencing should still happen in ~500-600ms (since it is batch processing). Is my assumption correct?
Please provide any comments or suggestions on this regard.
Thanks
Madhusudhan S
Link Copied
2 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@madhusudhan_s It's a queue, so if you send in five images, it processes each image, one at a time. We don't support batch image processing at the moment. I don't know of any work-arounds with APi2 because one device can only process one inference at a time with the current NCSDK 2.04.00.06.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thanks for the clarification @Tome_at_Intel !!
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page