DingXiaoH / ACNet

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
MIT License
831 stars 133 forks source link

in the function BNReLUConv2d, is there no BN layer in the ACBlock? #24

Closed Yannis1995 closed 3 years ago

Yannis1995 commented 4 years ago

def BNReLUConv2d(self, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, padding_mode='zeros', use_original_conv=False): if use_original_conv or kernel_size == 1 or kernel_size == (1, 1): return super(ACNetBuilder, self).BNReLUConv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups=groups, padding_mode=padding_mode, use_original_conv=True) bn_layer = self.BatchNorm2d(num_features=in_channels) conv_layer = ACBlock(in_channels, out_channels, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups=groups, padding_mode=padding_mode, deploy=self.deploy) se = self.Sequential() se.add_module('bn', bn_layer) se.add_module('relu', self.ReLU()) se.add_module('acb', conv_layer) return se Is the bn layer in the acb?