ConvBn1d

class torch.nn.intrinsic.qat.ConvBn1d(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)

A ConvBn1d module is a module fused from Conv1d and BatchNorm1d, attached with FakeQuantize modules for weight, used in quantization aware training.

We combined the interface of torch.nn.Conv1d and torch.nn.BatchNorm1d.

Similar to torch.nn.Conv1d, with FakeQuantize modules initialized to default.

Variables

• ~ConvBn1d.freeze_bn –

• ~ConvBn1d.weight_fake_quant – fake quant module for weight