Hi
Earlier, I already tried changing image_size parameter fields as below.However unfortunately that did not work, and I get below error
line 38, in parse_detections
postprocess_nanodet_detection(outputs=np_outputs[0], conf=threshold, iou_thres=iou,
File "/usr/lib/python3/dist-packages/picamera2/devices/imx500/postprocess_nanodet.py", line 38, in postprocess_nanodet_detection
distances = x * anchors[..., 2, None]
~~^~~~~~~~~~~~~~~~~~~~~~~
ValueError: operands could not be broadcast together with shapes (1,0,4) (1,3598,1)
I think just changing input_size parameter did not work, since as we change input_size parameter, the strides and other parameter shall also change accordingly, but we don't know what should be the values for that?
Basically, at least logic in below must be changed with appropriately
# Extract feature map sizes
# Decode bboxes
Earlier, I already tried changing image_size parameter fields as below.
Code:
featmap_sizes = [(np.ceil(320 / stride), np.ceil(320 / stride)) for stride in strides]line 38, in parse_detections
postprocess_nanodet_detection(outputs=np_outputs[0], conf=threshold, iou_thres=iou,
File "/usr/lib/python3/dist-packages/picamera2/devices/imx500/postprocess_nanodet.py", line 38, in postprocess_nanodet_detection
distances = x * anchors[..., 2, None]
~~^~~~~~~~~~~~~~~~~~~~~~~
ValueError: operands could not be broadcast together with shapes (1,0,4) (1,3598,1)
I think just changing input_size parameter did not work, since as we change input_size parameter, the strides and other parameter shall also change accordingly, but we don't know what should be the values for that?
Basically, at least logic in below must be changed with appropriately
# Extract feature map sizes
# Decode bboxes
Statistics: Posted by Yogesh432b430pc — Thu Nov 07, 2024 7:40 am