ConvBnReLU1d

class torch.nn.intrinsic.qat.ConvBnReLU1d(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 ConvBnReLU1d module is a module fused from Conv1d, BatchNorm1d and ReLU, attached with FakeQuantize modules for weight, used in quantization aware training.

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

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

Variables

~ConvBnReLU1d.weight_fake_quant – fake quant module for weight