I’ve noticed that a lot of the issues raise here in the community can got left unresolved for a long time. I don’t necessarily mean that people don’t get help I mean that if there is a bug preventing things from working and this is noticed that moths later the bug still exists with now way to know if someone is even working on a solution.
I see that there are 3 repos available for raising issues but the issues might not be related to those repos.
Are we supposed to just mention them here and hope they get picked up at some point?
Thank you for reporting this issue. Please include the details in the question , and we’ll forward this to our R&D team for review. Once we have assessed the timeline for addressing this, we’ll provide you with an update.
Just to set expectations - while we have successfully resolved many reported issues, we prioritize fixes based on impact and overall product roadmap. We’ll evaluate this issue within that framework.
Please let us know if you have any additional information to share that could help us better understand the severity and impact of this issue.
for tensor in video_frame.roi.get_tensors()
try:
info = tensor.vstream_info()
except Exception as e:
print(e)
Unable to convert function return value to a Python type! The signature was
(self: hailo.HailoTensor) -> hailo_vstream_info_t
Also, this entire thread was mostly caused by not being able to extract the tensor data as 16bit. Calling np.array(tensor) always give 8bit results which results in truncation causing the entire app to break.
Finally, this quote:
Firstly, the doc doesn’t say anything about dequantizing. Secondly, if it is supposed to then it doesn’t work. I have had to manually dequantize all of the data from my model.