[Bug]: convert layout to 'NCHW' (from 'NHWC' specified above at tensor layout) unable to infer normally about openvino HOT 5 OPEN

ppp.input().model().set_layout("NCHW"); doesn't modify your model. It sets the info for ppp about internal model layout so ppp.input().tensor().set_shape(input_shape).set_element_type(input_type).set_layout(tensor_layout); knows whether the transpose is required.

from openvino.

ppp.input().model().set_layout("NCHW");

Why does the model layout need to be set twice? What is the difference?

// First define layout for your tensor
ppp.input("input").tensor().set_layout("NHWC");

// Then define layout of model
ppp.input("input").model().set_layout("NCHW");

from openvino.

The first is the input layout. It's the layout you are going to follow while providing the input for inference. The second is the model layout. That's how the model weights are ordered, You can't influence weights layout and you are expected to know that when the model is trained.

from openvino.

I am having a related(?) problem with a NPU single-layer-test for MVN, below config passes vs OV reference:

void configure_model() override {
        ov::preprocess::PrePostProcessor p(function);
        p.input(0).tensor().set_layout(ov::Layout("NCHW"));
        p.input(0).model().set_layout(ov::Layout("NCHW"));
        p.output(0).model().set_layout(ov::Layout("NCHW"));
        p.output(0).tensor().set_layout(ov::Layout("NCHW"));
}

But NHWC config fails:

 void configure_model() override {
        ov::preprocess::PrePostProcessor p(function);
        p.input(0).tensor().set_layout(ov::Layout("NHWC"));
        p.input(0).model().set_layout(ov::Layout("NHWC"));
        p.output(0).model().set_layout(ov::Layout("NHWC"));
        p.output(0).tensor().set_layout(ov::Layout("NHWC"));
}

And the problem I see is that OV dumped .ref output is the same in both cases, but shouldn't be. This used to work fine in the past, not sure what changed recently.

from openvino.

It seems I'm not educated enough to understand the problem description. @Maxim-Doronin, can you take a look?

from openvino.