pytorch / 2 / generated / torch.ao.nn.intrinsic.quantized.dynamic.linearrelu.html

LinearReLU

class torch.ao.nn.intrinsic.quantized.dynamic.LinearReLU(in_features, out_features, bias=True, dtype=torch.qint8) [source]

A LinearReLU module fused from Linear and ReLU modules that can be used for dynamic quantization. Supports both, FP16 and INT8 quantization.

We adopt the same interface as torch.ao.nn.quantized.dynamic.Linear.

Variables

torch.ao.nn.quantized.dynamic.Linear (Same as) –

Examples:

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

© 2024, PyTorch Contributors
PyTorch has a BSD-style license, as found in the LICENSE file.
https://pytorch.org/docs/2.1/generated/torch.ao.nn.intrinsic.quantized.dynamic.LinearReLU.html