Where can we report bugs?

[rosslote]

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:

@user67

Hi,
As explained in tappas/docs/write_your_own_application/write-your-own-python-postprocess.rst at master · hailo-ai/tappas · GitHub , calling my_array = np.array(my_tensor, copy=False), should automatically dequantize the tensor from integer format to float.

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.