Register Custom Operation - 3.5 English

Vitis AI User Guide (UG1414)

Document ID
UG1414
Release Date
2023-09-28
Version
3.5 English
To convert a quantized model to an XMODEL, vai_q_pytorch offers a decorator that allows you to register an operation or a group of operations as a custom operation that XIR does not recognize:
# Decorator API
def register_custom_op(op_type: str, attrs_list: Optional[List[str]] = None):
  """The decorator is used to register the function as a custom operation.
  Args:
  op_type(str) - the operator type registered into quantizer. 
  The type should not conflict with pytorch_nndct

  attrs_list(Optional[List[str]], optional) - 
  the name list of attributes that define operation flavor. 
  For example, Convolution operation has such attributes as padding, dilation, stride and groups. 
  The order of names in attrs_list should be consistent with that of the arguments list. 
  Default: None

  """

Perform the following steps:

  1. Aggregate some operations as a function. The first argument name of this function should be ctx, with the same meaning as in torch.autograd.Function
  2. Decorate this function with the decorator described previously.

from pytorch_nndct.utils import register_custom_op

@register_custom_op(op_type="MyOp", attrs_list=["scale_1", "scale_2"])
def custom_op(ctx, x: torch.Tensor, y:torch.Tensor, scale_1:float, scale_2:float) -> torch.Tensor:
  return scale_1 * x + scale_2 * y 

class MyModule(torch.nn.Module):
  def __init__(self):
  ...

  def forward(self, x, y):
          return custom_op(x, y, scale_1=2.0, scale_2=1.0)
Limitations:
  1. Loop operation is not allowed in a custom operation.
  2. A custom operation's number of return values can only be one.