ConvBn3d¶
-
class
torch.nn.intrinsic.qat.
ConvBn3d
(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=None, padding_mode='zeros', eps=1e-05, momentum=0.1, freeze_bn=False, qconfig=None)[source]¶ A ConvBn3d module is a module fused from Conv3d and BatchNorm3d, attached with FakeQuantize modules for weight, used in quantization aware training.
We combined the interface of
torch.nn.Conv3d
andtorch.nn.BatchNorm3d
.Similar to
torch.nn.Conv3d
, with FakeQuantize modules initialized to default.- Variables
~ConvBn3d.freeze_bn –
~ConvBn3d.weight_fake_quant – fake quant module for weight