ConvBn2d

class torch.ao.nn.intrinsic.qat.ConvBn2d(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 ConvBn2d module is a module fused from Conv2d and BatchNorm2d, attached with FakeQuantize modules for weight, used in quantization aware training.

我们结合了 torch.nn.Conv2d 和 torch.nn.BatchNorm2d 的接口。

与 torch.nn.Conv2d 类似，FakeQuantize 模块初始化为默认值。

变量

• freeze_bn –

• weight_fake_quant – 权重的 fake quant 模块