ConvBnReLU2d — PyTorch 2.7 documentation (original) (raw)

class torch.ao.nn.intrinsic.qat.ConvBnReLU2d(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][source]¶

A ConvBnReLU2d module is a module fused from Conv2d, BatchNorm2d and ReLU, attached with FakeQuantize modules for weight, used in quantization aware training.

We combined the interface of torch.nn.Conv2d andtorch.nn.BatchNorm2d and torch.nn.ReLU.

Similar to torch.nn.Conv2d, with FakeQuantize modules initialized to default.

Variables

weight_fake_quant – fake quant module for weight