[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.

Hi @"Nadi"#p6578 , You have incorrect input layout - please [see docs](https://docs.luxonis.com/en/latest/pages/model_conversion/#model-layout-parameter) here on how to specify this. Thanks, Erik

Hi @"SebastianH"#p6596 , 2 options: - Preferred: Specify correct layout using openvino's model optimizer, using `--layout`, [docs here](https://docs.openvino.ai/2022.1/openvino_docs_MO_DG_Additional_Optimization_Use_Cases.html#when-to-specify-layout). - Change frame layout with depthai, using `colorCamera.setInterleaved(bool)` I hope this helps! Thanks, Erik

@"erik"#p6597 What layout should the model have?

Hi @"SebastianH"#p6599 , [Per docs](https://docs.luxonis.com/en/latest/pages/model_conversion/#model-layout-parameter), model should be Planar / CHW layout.

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

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?

heebahsaleem

[184430107165680F00] [3.3] [89.777] [NeuralNetwork(0)] [warning] Input image (300x300) does not match NN (3x300)

Model: MobileNetV2

I am getting the same error and I tried the above two options which you have mentioned, but no luck.
I am assuming that it is just a warning, will it affect in any way.

jakaskerl

heebahsaleem
It will not work.
You need to change:

either the Openvino version you are using (trial and error), they seem to change their default shapes between versions.
when compiling the blob with blobconverter, use these https://docs.openvino.ai/2022.3/openvino_inference_engine_tools_compile_tool_README.html parameters (primarily -il) to set the desired shape.

Thanks,
Jaka

heebahsaleem

jakaskerl
thank you for your reply.

what is trial and error Openvino version? I am using openvino 2022.2 version.
I am using blobconverter app to convert [https://blobconverter.luxonis.com/]. How to use the one you have mentioned?
FYI I am using TF model

Your help will be highly appreciated. TIA

userOfCamera

I'm having a similiar issue

[18443010D18F411300] [2.2] [9.560] [DetectionNetwork(1)] [warning] Input image (244x244) does not match NN (3x244)

My blob conversion:
blob_path = blobconverter.from_tf(

frozen_pb="./frozen_graph.pb",

data_type="FP16",

shaves=6,

optimizer_params=[

f"--input_shape=[1,{SHAPE},{SHAPE},3]"

]

)

I'm confused about how I should modify this blob_path to make sure it outputs the desired shape/right convention @jakaskerl

jakaskerl

Hi heebahsaleem

Trial and error is referring to the process of finding the right Openvino version for your model to work. Basically you would have to compile the model with each Openvino version, untill you find the right one (perhaps 2021.4 could work right away), hence the "trial and error".
Inside blobconverter, you have "advanced" tab which allows you to select the number of shaves you are using, and pass in additional parameters. Under "Compile parameters:" you should be able to pass in the -il parameter and the shape you want.

userOfCamera
According to README I sent above the shapes should be defined as either "NCHW" or "NHWC". So the compiler knows how to reshape the input.

Thanks,
Jaka

userOfCamera

@jakaskerl
I set --layout to both nchw and nhwc but the same issue persists

blob_path = blobconverter.from_tf(

frozen_pb="./frozen_graph.pb",

data_type="FP16",

shaves=6,

optimizer_params=[

f"--input_shape=[1,{SHAPE},{SHAPE},3]",

"--layout=nhwc"

]

)

Am I supposed to set this using the -il flag? Can you show me an example