ConvBnReLU3d¶
-
class
torch.nn.intrinsic.qat.ConvBnReLU3d(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 ConvBnReLU3d module is a module fused from Conv3d, BatchNorm3d and ReLU, attached with FakeQuantize modules for weight, used in quantization aware training.
We combined the interface of
torch.nn.Conv3dandtorch.nn.BatchNorm3dandtorch.nn.ReLU.Similar to torch.nn.Conv3d, with FakeQuantize modules initialized to default.
- Variables
~ConvBnReLU3d.weight_fake_quant – fake quant module for weight
