New feature, bug fixes, code modifications to create a CPP export of Resnet18 (quantified model)

Context

Summary

This MR is or adapt, fix error and add new features to this module for support the ResNet18 quandfied model

Detailed major modifications

Work on operators:

• Pooling
  • [Feat] integration of rounding for an integer data type (pooling.hpp)
• Rescaling
  • [Feat] Add rescaling function (rescaling.hpp)
  • [Feat] Add registrar file (CppRescaling.py)
  • [Feat] Add config and forward jinja for rescaling operator (rescaling_config.jinja & rescaling_forward.jinja)
• Elemwise
  • [Refactor] Change "elemwise_op" attribute resolution (elemwise_config.py)
  • [Refactor] Use rescaling.jinja file to collect rescaling attribute

Work on export object:

• [Fix] Modify cpp_recipes: renaming operator to fix error (export_utils.py)
• [Feat] Add normalize function necessary to format data before PTQ (export_utils.py)
• [Feat] Add external input_tensor option. Can be use with main cpp generation fucntion (export.py)
• [Fix] Replacing a hard CAST with a CAST based on the output data type (_aidge_cmp.jinja)
• [Feat] create a new template for aidge_cmp function (for integer datatype)

Work to fix error for openmp option:

• [Fix] Add "#ifdef _OPENMP" to enable or disable the OpenMP option of the compilation
  • convolution.hpp
  • fullyconnected.hpp
  • leakyrelu.hpp
  • pooling.hpp

assigned to @mick94

requested review from @axelfarr

changed milestone to %aidge v0.6.0

added Enhancement ⭐ Feature 🚀 StatusReview Ready TopicExport labels

changed the description

changed the description

requested changes

added 1 commit

• 7330a819 - [Fix] Suppress constexpr and simplified the choice of rounding

Compare with previous version

added 1 commit

• 5de6bc4e - [Refactor] Simplify aidge_cmp function to one function for float or interger

Compare with previous version

added 37 commits

• 5de6bc4e...ba2b04cc - 19 commits from branch eclipse/aidge:feat_add_quantized_export
• ba2b04cc...2479c67c - 8 earlier commits
• f01fb846 - [Refactor] Change rescaling resolution using rescaling.jinja
• 2f44c203 - [Fix] Replacing a hard cast with a cast based on the output typ
• 9986dca6 - [Feat] Adaptation of the Aidge_cmp function for an integer datatype
• 927f7f34 - [Refactor] Change formatting
• 6e21d6f0 - [Feat] Add jinja file for forward build
• aa614f33 - [Fix] Add #define to enable or disable the OpenMP option for compilation
• 11260789 - [Feature] Add Python script for ResNet18 export (cpp)
• 9e88dece - [Git] Add gitignores
• 0c8a131d - [Fix] Suppress constexpr and simplified the choice of rounding
• 28d60307 - [Refactor] Simplify aidge_cmp function to one function for float or interger

Compare with previous version

added StatusChanges required label and removed StatusReview Ready label

changed milestone to %aidge v0.7.0

added 20 commits

• aad912c8 - 1 commit from branch eclipse/aidge:feat_add_quantized_export
• aad912c8...76e61374 - 9 earlier commits
• e4317fd7 - [Fix] Replacing a hard cast with a cast based on the output typ
• 7801dc6f - [Feat] Adaptation of the Aidge_cmp function for an integer datatype
• b063bd16 - [Refactor] Change formatting
• 56ecbd41 - [Feat] Add jinja file for forward build
• cea36246 - [Fix] Add #define to enable or disable the OpenMP option for compilation
• cf3509dd - [Feature] Add Python script for ResNet18 export (cpp)
• 1057b2e0 - [Git] Add gitignores
• 55b4d096 - [Fix] Suppress constexpr and simplified the choice of rounding
• 3f58cc01 - [Refactor] Simplify aidge_cmp function to one function for float or interger
• c2cfa8d1 - Fix Add ignore attribute to False by default

Compare with previous version

requested review from @axelfarr

resolved all threads

added StatusReview Ready label and removed StatusChanges required label