[NeuralNetwork(0)] [warning] Input image (224x224) does not match NN (3x224)

Nadi

[BUG!!] - OPENVINO / LUXONIS OAKD
Hello everyone,
I am experiencing this problem with running DeeLabV3+ on oak-d lite with blob format.
I converted ONNX-> XML/BINOpenVino format and then compiled xml to blob format with openvino-2022.2 compiler.
when i run my application i got this problem and i didnt manage to get my input layer.

erik

Hi Nadi ,
You have incorrect input layout - please see docs here on how to specify this.
Thanks, Erik

SebastianH

Hello erik
I have the same issue as @Nadi I looked at the docs you send and I could not understand how to solve this issue, could you explain in further detail?

SebastianH

SebastianH Mine is more specificly [DetectionNetwork(1)] [warning] Input image (512x512) does not match NN (3x512)

erik

Hi SebastianH ,
2 options:

Preferred: Specify correct layout using openvino's model optimizer, using --layout, docs here.
Change frame layout with depthai, using colorCamera.setInterleaved(bool)

I hope this helps!
Thanks, Erik

SebastianH

erik
I tryed using colorCamera.setInterleaved(True) but i didnt help i will try your first recommendation and let you know 🙂

SebastianH

erik What layout should the model have?

erik

Hi SebastianH , Per docs, model should be Planar / CHW layout.

SebastianH

Hi erik
Will there be any performance issue using colorCamera.setInterleaved(True) instead of chaning the model?

Nadi

@erik Hi Erik, I have setinterleaved(True) (HWC) and I set the model input and outpuat layout to NHWC and looks like the openvino compiler changed it to NCHW alone and i get this message now:

[NeuralNetwork(0)] [warning] Input image is interleaved (HWC), NN specifies planar (CHW) data order

any fix?

erik

Nadi This means you need to set setinterleaved(False), so it's planar, which is what NN specifies.
@SebastianH no performance issues on the model (or minimal, simple conversion layer), but some nodes that process frames (eg ImageManip) are slower if they process interleaved frames (see docs here)
Thanks, Erik

Nadi

@erik I fixed it but now i got only output layer when i call getalllayers() , do you have a clue?

erik

@Nadi what else are you expecting to get returned from the output of the NN inference?

Nadi

erik did you understand?

Nadi

I am not talking about the output layer, i am talking about getalllayers -> i expect it to return input and output layers
and now it returns only the output

erik

@Nadi Why would you need input layer? If you want to overlay the semantic seg. result with the rgb image, you can use neuralNetworkNode.passthrough output to get the input image. Thoughts?