Not quantize AdaptiveMaxPool

[AlexanderDokuchaev]

Changes

According to https://docs.openvino.ai/2023.1/openvino_docs_OV_UG_lpt.html
Placement FQ nodes like in OV backend.

Related tickets

124839

[codecov]

Codecov Report

Merging #2284 (09188a9) into develop (077d361) will decrease coverage by 4.79%.
Report is 7 commits behind head on develop.
The diff coverage is 100.00%.

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #2284      +/-   ##
===========================================
- Coverage    90.75%   85.96%   -4.79%     
===========================================
  Files          485      486       +1     
  Lines        43744    43783      +39     
===========================================
- Hits         39700    37639    -2061     
- Misses        4044     6144    +2100     

Flag	Coverage Δ
COMMON	15.86% <0.00%> (+0.04%)	⬆️
ONNX	?
OPENVINO	38.71% <100.00%> (+0.05%)	⬆️
TENSORFLOW	30.02% <0.00%> (-0.02%)	⬇️
TORCH	62.68% <100.00%> (-0.03%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files	Coverage Δ
nncf/experimental/torch/pruning/operations.py	100.00% <100.00%> (ø)
nncf/torch/graph/operator_metatypes.py	99.13% <100.00%> (+0.01%)	⬆️
nncf/torch/pruning/operations.py	75.90% <100.00%> (+0.10%)	⬆️

... and 40 files with indirect coverage changes

[daniil-lyakhov]

Great contribution!
One comment: do you considering implementing a syntenic example with both MaxPool and AdaptiveMaxPool to check quantizers are inserting as expected?

[alexsu52]

LGTM

[daniil-lyakhov]

👍