BNReLU3d

class torch.ao.nn.intrinsic.quantized.modules.bn_relu.BNReLU3d(num_features, eps=1e-05, momentum=0.1, device=None, dtype=None)

A BNReLU3d module is a fused module of BatchNorm3d and ReLU

We adopt the same interface as torch.ao.nn.quantized.BatchNorm3d.

Variables:

torch.ao.nn.quantized.BatchNorm3d (Same as) –

forward(input)

Applies fused BatchNorm3d and ReLU.

classmethod from_float(mod, use_precomputed_fake_quant=False)

Creates a quantized module from a float module.

classmethod from_reference(bn_relu, output_scale, output_zero_point)

Creates a quantized module from a reference module.