Stride=1 cfg Kernel Sizes Never Used?

[glenn-jocher]

The first column of the cfg are k kernel sizes:

ghostnet.pytorch/ghost_net.py

Lines 175 to 194 in 8c601df

	cfgs = [
	# k, t, c, SE, s
	[3, 16, 16, 0, 1],
	[3, 48, 24, 0, 2],
	[3, 72, 24, 0, 1],
	[5, 72, 40, 1, 2],
	[5, 120, 40, 1, 1],
	[3, 240, 80, 0, 2],
	[3, 200, 80, 0, 1],
	[3, 184, 80, 0, 1],
	[3, 184, 80, 0, 1],
	[3, 480, 112, 1, 1],
	[3, 672, 112, 1, 1],
	[5, 672, 160, 1, 2],
	[5, 960, 160, 0, 1],
	[5, 960, 160, 1, 1],
	[5, 960, 160, 0, 1],
	[5, 960, 160, 1, 1]
	]
	return GhostNet(cfgs, **kwargs)

But unless stride=2, it appears GhostBottleneck() module does not use the cfg kernel size. Is this correct? If so setting these to 1 in the cfg may be more clear?

ghostnet.pytorch/ghost_net.py

Lines 81 to 108 in 8c601df

	class GhostBottleneck(nn.Module):
	def __init__(self, inp, hidden_dim, oup, kernel_size, stride, use_se):
	super(GhostBottleneck, self).__init__()
	assert stride in [1, 2]
	self.conv = nn.Sequential(
	# pw
	GhostModule(inp, hidden_dim, kernel_size=1, relu=True),
	# dw
	depthwise_conv(hidden_dim, hidden_dim, kernel_size, stride, relu=False) if stride==2 else nn.Sequential(),
	# Squeeze-and-Excite
	SELayer(hidden_dim) if use_se else nn.Sequential(),
	# pw-linear
	GhostModule(hidden_dim, oup, kernel_size=1, relu=False),
	)
	if stride == 1 and inp == oup:
	self.shortcut = nn.Sequential()
	else:
	self.shortcut = nn.Sequential(
	depthwise_conv(inp, inp, kernet_size, stride, relu=False),
	nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
	nn.BatchNorm2d(oup),
	)
	def forward(self, x):
	return self.conv(x) + self.shortcut(x)

[iamhankai]

You are right. The code is not clean... As said in huawei-noah/Efficient-AI-Backbones#12

[glenn-jocher]

@iamhankai ok got it, thank you! Was just checking to make sure I wasn't missing something.