[luci] Handle dynamic dimensions in Squeeze shape inference

[mbencer]

This commit skip verification of squeezed dimension if such dimension is dynamic.

ONE-DCO-1.0-Signed-off-by: Mateusz Bencer m.bencer@partner.samsung.com

Draft: #14882
Issue: #14791

[seanshpark]

Plz follow #14844 (comment) for this too

[mbencer]

Plz follow #14844 (comment) for this too

I'm trying with TF recipe like:

operand {
  name: "ifm"
  type: FLOAT32
  shape { dim: 3 dim: 4 dim: 5 dim: 1}
  shape_signature { dim: 3 dim: 4 dim: 5 dim: -1 }
}
operand {
  name: "ofm"
  type: FLOAT32
  shape { dim: 3 dim: 4 dim: 5 }
}
operation {
  type: "Squeeze"
  squeeze_options { squeeze_dim: 3 }
  input: "ifm"
  output: "ofm"
}
input: "ifm"
output: "ofm"

But it fails on asserts in luci-interpreter Squeeze kernel because of dynamic dimension in input shape. It looks like only shape_signature is propagated there.

[seanshpark]

I'm trying with TF recipe like:

this is tflite recipe, not TF

... on asserts in luci-interpreter Squeeze kernel ...

you may have to fix luci-interpreter too, as I know you are to support dynamic shapes.

[jinevening]

Code itself looks good to me.

[mbencer]

@seanshpark

this is tflite recipe, not TF

Right ;)

you may have to fix luci-interpreter too, as I know you are to support dynamic shapes.

I see but it looks like a bigger task. In the current state I'm specializing dynamic shape model to the static version via circle-resizer but still probably will be needed in the future. I'll think about it ;)

In the current moment I'm proposing introduce the Squeeze test based on tflite recipe in steps (the order is important):
#14864
#14865
#14866

But this PR should be merged at first.

[seanshpark]

as you've posted multiple PRs related to this PR, please add a link to the full draft PR.
I'd like to check all.

[mbencer]

as you've posted multiple PRs related to this PR, please add a link to the full draft PR. I'd like to check all.

sure - Draft: #14882

[mbencer]

@seanshpark In my opinion we should merge the PRs in order:

• this PR at first (after finishing review)
• [res] Add TFLiteRecipe for Squeeze with dynamic shape #14865 - in master version invalid dimension exception is still thrown
• [circle2circle-dredd-recipe-test] Add Inf_Squeeze_000 test #14866 - after introducing TFLiteRecipe for Squeeze

[seanshpark]

we should merge the PR

I'd like to but you didn't apply the changes from the draft.

[mbencer]

we should merge the PR

I'd like to but you didn't apply the changes from the draft.

ohh, I see, I've missed #14882 (comment)

[jinevening]

LGTM

[seanshpark]

LGTM