Hi i got a code to study but when i look at the code it doesnt make sense special for out
this is code for the module
class Bottleneck(nn.Module):
def __init__(self, inp, oup, stride, expansion):
super(Bottleneck, self).__init__()
self.connect = stride == 1 and inp == oup
#
self.conv = nn.Sequential(
# pw
nn.Conv2d(inp, inp * expansion, 1, 1, 0, bias=False),
nn.BatchNorm2d(inp * expansion),
nn.PReLU(inp * expansion),
# nn.ReLU(inplace=True),
# dw
nn.Conv2d(inp * expansion, inp * expansion, 3, stride, 1, groups=inp * expansion, bias=False),
nn.BatchNorm2d(inp * expansion),
nn.PReLU(inp * expansion),
# nn.ReLU(inplace=True),
# pw-linear
nn.Conv2d(inp * expansion, oup, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup),
)
def forward(self, x):
if self.connect:
return x + self.conv(x)
else:
return self.conv(x)
MobiFace_bottleneck_setting = [
# t, c , n, s
[2, 64, 1, 2],
[2, 64, 2, 1],
[4, 128, 1, 2],
[2, 128, 3, 1],
[4, 256, 1, 2],
[2, 256, 6, 1]
]
this is when i run this code
class MobiFace(nn.Module):
def __init__(self, bottleneck_setting=MobiFace_bottleneck_setting, final_linear=False):
super(MobiFace, self).__init__()
self.final_linear = final_linear
self.conv1 = ConvBlock(3, 64, 3, 2, 1)
self.dw_conv1 = ConvBlock(64, 64, 3, 1, 1, dw=True)
self.inplanes = 64
block = Bottleneck
#set_trace()
self.blocks = self._make_layer(block, bottleneck_setting)
self.conv2 = ConvBlock(256, 512, 1, 1, 0, linear=True)
self.linear1 = nn.Linear(7*7*512, 512)
self.prelu1 = nn.PReLU()
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def _make_layer(self, block, setting):
layers = []
for t, c, n, s in setting:
for i in range(n):
if i == 0:
layers.append(block(self.inplanes, c, s, t))
else:
layers.append(block(self.inplanes, c, 1, t))
self.inplanes = c
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.dw_conv1(x)
x = self.blocks(x)
x = self.conv2(x)
x = x.view(x.size(0), -1)
x = self.linear1(x)
if self.final_linear is False:
x = self.prelu1(x)
return x
so print the layer
if __name__ == "__main__":
input = Variable(torch.FloatTensor(2, 3, 112, 96))
net = MobiFace()
print(net)
MobiFace(
(conv1): ConvBlock(
(conv): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(prelu): PReLU(num_parameters=64)
)
(dw_conv1): ConvBlock(
(conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=64, bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(prelu): PReLU(num_parameters=64)
)
(blocks): Sequential(
(0): Bottleneck(
(conv): Sequential(
(0): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): PReLU(num_parameters=128)
(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=128, bias=False)
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): PReLU(num_parameters=128)
(6): **Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)**
(7): **BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)**
can anyone explain to me how does the conv2d input is 128 in (6) it reduce to 64 at the end how is this happen?