LinearTanh

class torch.ao.nn.intrinsic.quantized.modules.linear_relu.LinearTanh(in_features, out_features, bias=True, dtype=torch.qint8)

A LinearTanh module fused from Linear and Tanh modules

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

Variables:

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

Examples:

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