Reputation: 7077
Just wondering if I choose a model from the Model Zoo which has bigger input size than the OPEN-CV OAK-D's resolution(FHD 1920x1080) it errors out.
To be more specific, I am trying to deploy a model which can be the fastseg-small or icent-camvid-ava-sparse-60-0001 or semantic-segmentation-adas-0001 onto the OpenCV OAK-D device.
when using python depthai_demo.py -cnn semantic-segmentation-adas-0001
to deploy the model to OAK-D, I received this error:
Using depthai module from: /media/winstonfan/Workspace/Learning/Github/depthai/myvenv/lib/python3.8/site-packages/depthai.cpython-38-x86_64-linux-gnu.so
Depthai version installed: 2.8.0.0
Available devices:
[0] 14442C10013762D700 [X_LINK_UNBOOTED]
Traceback (most recent call last):
File "depthai_demo.py", line 180, in <module>
device.startPipeline(pm.p)
RuntimeError: , LRT: 'ColorCamera(4) - 'preview' width or height (2048, 1024) bigger than sensor resolution (1920, 1080)'
So it seems that this model requires bigger input size.
How to use a model which requires input size larger than OAK-D's resolution?
Upvotes: 0
Views: 156
Reputation: 1413
The fastseg-small, icent-camvid-ava-sparse-60-0001 and semantic-segmentation-adas-0001 models are not listed in DepthAI Github repository, as such it might not be supported. You can post this question at the DepthAI Community forum, or Discussion forum. For your information, DepthAI and OpenCV OAK-D is not a part of OpenVINO Toolkit.
Upvotes: 0