Daniil Lyakhov

It's look like `tf.keras.Model` subclassing isn't possible in the way introduced here. As the solution I can suggest to use target model and teacher model composition with attribute proxying by...

@evgeniya-egupova, could you please update PR?

Guys, looks like we were removed from nncf developers group. Please add me as an reviewer and don't merge this without our review! Please run precommit tests before merge cc:...

@sooahleex, please provide an example of network with concat layer as a leaf. Looks like a problem in graph building part.

@sooahleex, we already have mechanism for ignoring layers, it's implemented here: https://github.com/openvinotoolkit/nncf/blob/160990cba0473452955c494b2087c4f4160241c7/nncf/common/pruning/node_selector.py#L279-L305 it used at the last step of node selection here: https://github.com/openvinotoolkit/nncf/blob/160990cba0473452955c494b2087c4f4160241c7/nncf/common/pruning/node_selector.py#L218 It's essential to generate masks for each...

@sooahleex, thank you for your contribution! Please don't forget to update correspondent nncf tensorflow part as well

Please add tests to torch/pruning/filter_pruning/test_algo.py

General comment: Masks matching by input shapes is implicit method of matching, I suggest you to 1) Explicitly have SymbolicMask (in case op has one ouput edge) or {Nodename: SymbolicMask}...

@sooahleex, to test this please update `test_model_pruning_analysis.py` with model/models which have split operations described in previous comment

> We will cover the reshape check in the different pr related to 90584 ticket. For that ticket and pr, some tests in this pr will be updated for `_is_not_mixing_dim`....