This includes HWCustomOp and HLSBackend specializations of the operators aiming for full ONNX compliance. Adds infrastructure for converting the standard ONNX version of the operators to the FINN dialect, which mostly means transplanting the node into the FINN domain and setting a few type and shape attributes. Adds unit tests in Python, C++ and RTL simulation as well as a simple integration test starting from PyTorch model export.

Proposes a new scheme for registering and importing custom operators into their corresponding module namespace, i.e., the 'custom_op' dictionary used to lookup operators by ONNX domain. This is the same as already proposed in#1040.

Support for these operators might seem unnecessary as they have no real effect on the stream/dataflow. However, they can be useful as a workaround for adapting between datalayouts, for example when combining convolutions (assuming 4-dimensional layouts) and attention operations (working on 3-dimensional, or rather 2-dimensional layouts). I will link some example presenting this later...