Hello,
I have a problem trying to use the inference engine in an async mode (with a ssd mobilenet v1).
My code worked with previous release. I compared with samples/python/object_detection_demo_ssd_async.py and my code looks very similar.
# Run inference
if self.is_async_mode:
self.exec_net.start_async(request_id=self.next_request_id,
inputs={self.input_blob: in_frame})
else:
self.exec_net.start_async(request_id=self.cur_request_id,
inputs={self.input_blob: in_frame})
if self.exec_net.requests[self.cur_request_id].wait(-1) == 0:
# Parse detection results of the current request
res = self.exec_net.requests[self.cur_request_id].outputs[self.out_blob]
When 'self.is_async_mode' is set to false, it works, but when 'self.is_async_mode' is set to true, it doesn't.
I get the following error :
....
File "/media/tameimpala/Data/Logos/src/OV_utils.py", line 63, in detect_objects
inputs={self.input_blob: in_frame})
File "ie_api.pyx", line 138, in inference_engine.ie_api.ExecutableNetwork.start_async
File "ie_api.pyx", line 166, in inference_engine.ie_api.InferRequest.async_infer
File "ie_api.pyx", line 170, in inference_engine.ie_api.InferRequest.async_infer
RuntimeError: [REQUEST_BUSY]
/teamcity/work/scoring_engine_build/releases_openvino-2018-r4/ie_bridges/python/inference_engine/ie_api_impl.cpp:334
I didn't found anything on the internet, is it a known issue ?
Thank you.
