Linear#

classtorch.ao.nn.quantized.dynamic.Linear(in_features,out_features,bias_=True,dtype=torch.qint8)[source]#

A dynamic quantized linear module with floating point tensor as inputs and outputs.We adopt the same interface astorch.nn.Linear, please seehttps://pytorch.org/docs/stable/nn.html#torch.nn.Linear for documentation.

Similar totorch.nn.Linear, attributes will be randomlyinitialized at module creation time and will be overwritten later

Variables

• weight (Tensor) – the non-learnable quantized weights of the module which are ofshape$(\text{out\_features},\text{in\_features})$(out_features,in_features).

• bias (Tensor) – the non-learnable floating point bias of the module of shape$(\text{out\_features})$(out_features). Ifbias isTrue,the values are initialized to zero.

Examples:

>>>m=nn.quantized.dynamic.Linear(20,30)>>>input=torch.randn(128,20)>>>output=m(input)>>>print(output.size())torch.Size([128, 30])

classmethodfrom_float(mod,use_precomputed_fake_quant=False)[source]#

Create a dynamic quantized module from a float module or qparams_dict

Parameters

mod (Module) – a float module, either produced by torch.ao.quantizationutilities or provided by the user

classmethodfrom_reference(ref_qlinear)[source]#

Create a (fbgemm/qnnpack) dynamic quantized module from a reference quantizedmodule:param ref_qlinear: a reference quantized module, either produced by:type ref_qlinear: Module:param torch.ao.quantization functions or provided by the user: