Layout conversion

[aag]

Does OpenVino provide means to convert input layout internally, or does input always need to be provided in the layout required by the model?

[SuryaPSC_Intel]

Hi Alex,

If the network assumes the RGB inputs, the Model Optimizer can swap the channels in the first convolution using the --reverse_input_channels command line option, so we do not need to convert the inputs to RGB every time we get the BGR image, for example, from OpenCV

Best Regards,

Surya

[aag]

Thanks, but this is not exactly what I'm looking for. The image comes interleaved (e.g. NHWC) from the decoder, but the network requires planar (e.g. NCHW). Does OpenVino have a conversion API (explicit or implicit), or does the conversion need to happen externally.

[SuryaPSC_Intel]

Hi Alex,

By default, Inference Engine accepts the planar and not interleaved inputs in NCHW, so the NHWC (which is exactly the interleaved layout) should be specified explicitly.

The InferenceEngine::NHWC layout is not supported natively by most InferenceEngine plugins, so internal conversion might happen.

Kindly refer to OpenCV* Interoperability Example

Best Regards,

Surya

[aag]

But that's just the point -- internal conversions do not seem to be happening. 

Providing NHWC blob to a network expecting NCHW input results in

`[PARAMETER_MISMATCH] Failed to set input Blob. Dimensions mismatch.`

exception being thrown. OpenCV samples you refer to, seem to use both approaches (matU8ToBlob performs external NHWC->NCHW conversion; wrapMat2Blob wraps a NHWC blob and passes it to input). However, the latter never seems to work for me.

[SuryaPSC_Intel]

HI Alex,

You may try doing the conversion within the decoder itself before feeding it into the inference engine.

You can also refer to the object_detection_demo_ssd_async.py to modify the layout.

Best Regards,

Surya