Linear — PyTorch 2.7 documentation (original) (raw)

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

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

Similar to torch.nn.Linear, attributes will be randomly initialized at module creation time and will be overwritten later

Variables

• weight (Tensor) – the non-learnable quantized weights of the module which are of shape (out_features,in_features)(\text{out\_features}, \text{in\_features}).
• bias (Tensor) – the non-learnable floating point bias of the module of shape(out_features)(\text{out\_features}). If bias is True, 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])

classmethod from_float(mod, use_precomputed_fake_quant=False)[source][source]¶

Create a dynamic quantized module from a float module or qparams_dict

Parameters

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

classmethod from_reference(ref_qlinear)[source][source]¶

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