- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello,
I'm trying calculate inference time of IR models, and I used "get_perf_counts()" to get some informations about inference time.
I wrote the code like that
----------------------------
infer_request_handle = exec_net.start_async(request_id=0, inputs={input_blob: resize_img}) infer_request_handle.wait() perf_counts = infer_request_handle.get_perf_counts() log.info("Performance counters:") print("{:<70} {:<15} {:<15} {:<15} {:<10}".format('name', 'layer_type', 'exet_type', 'status', 'real_time, us')) for layer, stats in perf_counts.items(): print("{:<70} {:<15} {:<15} {:<15} {:<10}".format(layer, stats['layer_type'], stats['exec_type'], stats['status'], stats['real_time']))
-----------------------------
but, I could not get result.
Next, I executed IntelSWTools\openvino_2019.1.087\deployment_tools\inference_engine\samples\python_samples\
classification_sample_async\classification_sample_async argument --perf_counts True.
Also in this source code "get_perf_counts()" did not return a result.
Why does it not return a results?
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Dear arakawa, yota,
According to the documentation (see below) on Image Classification Python Sample Async you only pass in one of these -pc or --perf_counts but you don't need to put 'True'. Also don't forget, you always have to add the -l switch for Python samples which points it to the cpu_extension.dll (or *.so) if you are running on the CPU.
Thanks,
Shubha
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
.

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page