Added QARepVGGBlock

[spsancti]

QARepVGG (S4) block from 'Make RepVGG Greater Again: A Quantization-aware Approach' (https://arxiv.org/pdf/2212.01593.pdf)
It consists of three branches:

3x3: a branch of a 3x3 Convolution + BatchNorm
1x1: a branch of a 1x1 Convolution with bias
identity: a Residual branch
BatchNorm is applied after summation of all three branches.

In contrast to our implementation of RepVGGBlock, SE is applied AFTER NONLINEARITY in order to fuse Conv+Act in inference frameworks.

This module converts to Conv+Act in a PTQ-friendly way by calling QARepVGGBlock.fuse_block_residual_branches().
Has the same API as RepVGGBlock and is designed to be a plug-and-play replacement but is not compatible parameter-wise.
Has less trainable parameters than RepVGGBlock because it has only 2 BatchNorms instead of 3.

[dagshub]

Join the discussion on DagsHub!

[ofrimasad]

This PR breaks the logic we have built for quantization.
instead of having a block and registering a quantized block, we define here a block that knows how to be quantized. I don't like this and I am not sure exactly how that will work with the rest of the quantization code.
Instead, lets define a block without the quantization part and (no if qat_mode) and override some logics in a second block that is registered as his Quantized version

[ofrimasad]

waiting for fixes

[ofrimasad]

only one minor comment

[ofrimasad]

LGTM