Summary
Reference to create a custom asynchronous inference demo from OpenVINO™ toolkit.
Description
- Ran custom Face Recognition demo.
- Snippet code:
if self.max_requests <= self.active_requests: log.warning('Processing request rejected - too many requests') return False
self.infer_queue.start_async(input,self.active_requests) #Error getting line
self.active_requests += 1
return True
except Exception as ex:
print(ex) -
Received Runtime Error: [REQUEST_BUSY]
Resolution
REQUEST_BUSY error arises when a request is not being processed and then asking for another infer/request.
Refer to the face_recognition_demo.py for the example of inferencing using Asynchronous Inference request.