- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello,
On increasing the Batchsize of the model in OpenVINO the fps drops to half.
On increasing the Async inference requests the fps increases to a threshold point.
Is this nature of batch size normal? What is the reason behind it.
Can be replicated using Multi-Channel Object Detection Yolov3 C++ Demo -
./multi_channel_object_detection_demo_yolov3 -bs 5 -nireq 1
observed fps - 5
./multi_channel_object_detection_demo_yolov3 -bs 1 -nireq 5
observed fps - 63
./multi_channel_object_detection_demo_yolov3 -bs 5 -nireq 5
observed fps - 12
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@Patel I'd refer you to Introduction to Performance Topics article of OpenVINO online documentation, which says:
One way to increase computational efficiency is batching, which combines many (potentially tens) of input images to achieve optimal throughput. However, high batch size also comes with a latency penalty
Basically, batching can provide some performance benefits on GPU device, for CPU playing streams and number of threads is more beneficial.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@Patel I'd refer you to Introduction to Performance Topics article of OpenVINO online documentation, which says:
One way to increase computational efficiency is batching, which combines many (potentially tens) of input images to achieve optimal throughput. However, high batch size also comes with a latency penalty
Basically, batching can provide some performance benefits on GPU device, for CPU playing streams and number of threads is more beneficial.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Prince Patel`,
Thank you for reaching out to us.
This thread will no longer be monitored since this issue has been resolved.
If you need any additional information from Intel, please submit a new question.
Regards,
Wan
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page