EfficientNetV2
與EfficientNet相比，V2進行了精簡。方便理解搭建的過程。
1、drop_path方法
與之前的相同。
def drop_path(x, drop_prob: float = 0., training: bool = False):
if drop_prob == 0. or not training:
return x
keep_prob = 1 - drop_prob
shape = (x.shape[0],) + (1,) * (x.ndim - 1) # work with diff dim tensors, not just 2D ConvNets
random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
random_tensor.floor_() # binarize
output = x.div(keep_prob) * random_tensor
return output
2、DropPath類
在DropPath類中，正向傳遞過程，輸出直接調用drop_path方法。
class DropPath(nn.Module):
def __init__(self, drop_prob=None):
super(DropPath, self).__init__()
self.drop_prob = drop_prob
def forward(self, x):
return drop_path(x, self.drop_prob, self.training)
3、ConvBNAct類
卷積+BN+激活放在一起，groups判斷是卷積還是DW卷積。
class ConvBNAct(nn.Module):
def __init__(self,
in_planes: int,
out_planes: int,
kernel_size: int = 3,
stride: int = 1,
groups: int = 1,
norm_layer: Optional[Callable[..., nn.Module]] = None,
activation_layer: Optional[Callable[..., nn.Module]] = None):
super(ConvBNAct, self).__init__()
padding = (kernel_size - 1) // 2
if norm_layer is None:
norm_layer = nn.BatchNorm2d
if activation_layer is None:
activation_layer = nn.SiLU # alias Swish (torch>=1.7)
self.conv = nn.Conv2d(in_channels=in_planes,
out_channels=out_planes,
kernel_size=kernel_size,
stride=stride,
padding=padding,
groups=groups,
bias=False)
self.bn = norm_layer(out_planes)
self.act = activation_layer()
def forward(self, x):
result = self.conv(x)
result = self.bn(result)
result = self.act(result)
return result
4、SE類
SE模塊：首先，全局平均池化，將每一個channel求一個均值；再一次通過兩個全連接層，得到輸出。
注意：第一個全連接層節點個數等於輸入MBConv矩陣channel的1/4，第二個全連接層節點個數等於輸入SE模塊的channel。
class SqueezeExcite(nn.Module):
def __init__(self,
input_c: int, # block input channel
expand_c: int, # block expand channel
se_ratio: float = 0.25):
super(SqueezeExcite, self).__init__()
squeeze_c = int(input_c * se_ratio)
self.conv_reduce = nn.Conv2d(expand_c, squeeze_c, 1)
self.act1 = nn.SiLU() # alias Swish
self.conv_expand = nn.Conv2d(squeeze_c, expand_c, 1)
self.act2 = nn.Sigmoid()
def forward(self, x: Tensor) -> Tensor:
scale = x.mean((2, 3), keepdim=True)
scale = self.conv_reduce(scale)
scale = self.act1(scale)
scale = self.conv_expand(scale)
scale = self.act2(scale)
return scale * x
5、MBConv類
首先，進行一個判斷，如果stride不在1，2中，報錯。然后，判斷是否有捷徑分支。各種參數的設置，類似於EfficientNet。搭建各個模塊，1*1卷積。DW卷積，SE模塊，最后一個1*1無激活函數的卷積層，最后Dropout。
class MBConv(nn.Module):
def __init__(self,
kernel_size: int,
input_c: int,
out_c: int,
expand_ratio: int,
stride: int,
se_ratio: float,
drop_rate: float,
norm_layer: Callable[..., nn.Module]):
super(MBConv, self).__init__()
if stride not in [1, 2]:
raise ValueError("illegal stride value.")
self.has_shortcut = (stride == 1 and input_c == out_c)
activation_layer = nn.SiLU # alias Swish
expanded_c = input_c * expand_ratio
# 在EfficientNetV2中，MBConv中不存在expansion=1的情況所以conv_pw肯定存在
assert expand_ratio != 1
# Point-wise expansion
self.expand_conv = ConvBNAct(input_c,
expanded_c,
kernel_size=1,
norm_layer=norm_layer,
activation_layer=activation_layer)
# Depth-wise convolution
self.dwconv = ConvBNAct(expanded_c,
expanded_c,
kernel_size=kernel_size,
stride=stride,
groups=expanded_c,
norm_layer=norm_layer,
activation_layer=activation_layer)
self.se = SqueezeExcite(input_c, expanded_c, se_ratio) if se_ratio > 0 else nn.Identity()
# Point-wise linear projection
self.project_conv = ConvBNAct(expanded_c,
out_planes=out_c,
kernel_size=1,
norm_layer=norm_layer,
activation_layer=nn.Identity) # 注意這里沒有激活函數，所有傳入Identity
self.out_channels = out_c
# 只有在使用shortcut連接時才使用dropout層
self.drop_rate = drop_rate
if self.has_shortcut and drop_rate > 0:
self.dropout = DropPath(drop_rate)
def forward(self, x: Tensor) -> Tensor:
result = self.expand_conv(x)
result = self.dwconv(result)
result = self.se(result)
result = self.project_conv(result)
if self.has_shortcut:
if self.drop_rate > 0:
result = self.dropout(result)
result += x
return result
6、FusedMBConv模塊
分兩種情況expansion=1和不等1。
等於1，只有3*3卷積+BN+SiLU+Dropout。不等於1的話，3*3的卷積+BN+SiLU,1*1的卷積+BN，Dropout。在代碼中，先判斷
class FusedMBConv(nn.Module):
def __init__(self,
kernel_size: int,
input_c: int,
out_c: int,
expand_ratio: int,
stride: int,
se_ratio: float,
drop_rate: float,
norm_layer: Callable[..., nn.Module]):
super(FusedMBConv, self).__init__()
assert stride in [1, 2]
assert se_ratio == 0
self.has_shortcut = stride == 1 and input_c == out_c
self.drop_rate = drop_rate
self.has_expansion = expand_ratio != 1
activation_layer = nn.SiLU # alias Swish
expanded_c = input_c * expand_ratio
# 只有當expand ratio不等於1時才有expand conv
if self.has_expansion:
# Expansion convolution
self.expand_conv = ConvBNAct(input_c,
expanded_c,
kernel_size=kernel_size,
stride=stride,
norm_layer=norm_layer,
activation_layer=activation_layer)
self.project_conv = ConvBNAct(expanded_c,
out_c,
kernel_size=1,
norm_layer=norm_layer,
activation_layer=nn.Identity) # 注意沒有激活函數
else:
# 當只有project_conv時的情況
self.project_conv = ConvBNAct(input_c,
out_c,
kernel_size=kernel_size,
stride=stride,
norm_layer=norm_layer,
activation_layer=activation_layer) # 注意有激活函數
self.out_channels = out_c
# 只有在使用shortcut連接時才使用dropout層
self.drop_rate = drop_rate
if self.has_shortcut and drop_rate > 0:
self.dropout = DropPath(drop_rate)
def forward(self, x: Tensor) -> Tensor:
if self.has_expansion:
result = self.expand_conv(x)
result = self.project_conv(result)
else:
result = self.project_conv(x)
if self.has_shortcut:
if self.drop_rate > 0:
result = self.dropout(result)
result += x
return result
7、EfficientNetV2
class EfficientNetV2(nn.Module):
def __init__(self,
model_cnf: list,
num_classes: int = 1000,
num_features: int = 1280,
dropout_rate: float = 0.2,
drop_connect_rate: float = 0.2):
super(EfficientNetV2, self).__init__()
for cnf in model_cnf:
assert len(cnf) == 8
norm_layer = partial(nn.BatchNorm2d, eps=1e-3, momentum=0.1)
stem_filter_num = model_cnf[0][4]
self.stem = ConvBNAct(3,
stem_filter_num,
kernel_size=3,
stride=2,
norm_layer=norm_layer) # 激活函數默認是SiLU
total_blocks = sum([i[0] for i in model_cnf])
block_id = 0
blocks = []
for cnf in model_cnf:
repeats = cnf[0]
op = FusedMBConv if cnf[-2] == 0 else MBConv
for i in range(repeats):
blocks.append(op(kernel_size=cnf[1],
input_c=cnf[4] if i == 0 else cnf[5],
out_c=cnf[5],
expand_ratio=cnf[3],
stride=cnf[2] if i == 0 else 1,
se_ratio=cnf[-1],
drop_rate=drop_connect_rate * block_id / total_blocks,
norm_layer=norm_layer))
block_id += 1
self.blocks = nn.Sequential(*blocks)
head_input_c = model_cnf[-1][-3]
head = OrderedDict()
head.update({"project_conv": ConvBNAct(head_input_c,
num_features,
kernel_size=1,
norm_layer=norm_layer)}) # 激活函數默認是SiLU
head.update({"avgpool": nn.AdaptiveAvgPool2d(1)})
head.update({"flatten": nn.Flatten()})
if dropout_rate > 0:
head.update({"dropout": nn.Dropout(p=dropout_rate, inplace=True)})
head.update({"classifier": nn.Linear(num_features, num_classes)})
self.head = nn.Sequential(head)
# initial weights
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode="fan_out")
if m.bias is not None:
nn.init.zeros_(m.bias)
elif isinstance(m, nn.BatchNorm2d):
nn.init.ones_(m.weight)
nn.init.zeros_(m.bias)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.zeros_(m.bias)
def forward(self, x: Tensor) -> Tensor:
x = self.stem(x)
x = self.blocks(x)
x = self.head(x)
return x