TensorRT  7.2.1.6
NVIDIA TensorRT
Looking for a C++ dev who knows TensorRT?
I'm looking for work. Hire me!
pytorch_quantization.nn.modules._utils Namespace Reference

Classes

class  QuantInputMixin
 
class  QuantMixin
 

Functions

def pop_quant_desc_in_kwargs (quant_cls, input_only=False, **kwargs)
 

Function Documentation

◆ pop_quant_desc_in_kwargs()

def pytorch_quantization.nn.modules._utils.pop_quant_desc_in_kwargs (   quant_cls,
  input_only = False,
**  kwargs 
)
Pop quant descriptors in kwargs

If there is no descriptor in kwargs, the default one in quant_cls will be used

Arguments:
   quant_cls: A class that has default quantization descriptors
   input_only: A boolean. If True, pop quant_desc_input only, not quant_desc_weight. Default false.

Keyword Arguments:
   quant_desc_input: An instance of :class:`QuantDescriptor <pytorch_quantization.tensor_quant.QuantDescriptor>`.
       Quantization descriptor of input.
   quant_desc_weight: An instance of :class:`QuantDescriptor <pytorch_quantization.tensor_quant.QuantDescriptor>`.
       Quantization descriptor of weight.