EfficientNet中存在的问题
- 训练图像尺寸大时，训练速度非常慢。train size = 512, batch = 24时，V100 out of memory
- 在网络浅层中使用Depthwise convolutions速度会很慢。因此将原本EfficientNet中的
conv1x1 and depthwise conv3x3 (MBConv)替换成conv3x3 (Fused-MBCon v)。但如果将所有的conv1x1 and depthwise conv3x3都替换成conv3x3后，会明显增加参数数量，降低训练速度，因此使用NAS技术去搜索两者的最佳组合。
- 同等放大每个stage是次优的，因为每个stage对网络的训练速度以及参数量贡献不同。
NAS 搜索
与EfficientNet相同，但这次的NAS搜索采用了联合优化策略，联合了accuracy, parameter efficiency, training efficiency三个标准。设计空间包括
- convolutional operation types {MBConv, Fused-MBConv}
- number of layers
- kernel size {3x3, 5x5}
- expansion ration {1,4,6}
同时随机采样1000个models，并且对每个models进行了10个epochs的训练。搜索奖励结合了模型准确率A，标准训练一个step所需要的时间S，和参数量P， A ⋅ S − 0.07 ⋅ P − 0.05 A \cdot S^{-0.07} \cdot P^{-0.05} A⋅S−0.07⋅P−0.05
EfficientNetV2 网络结构
与EfficientNet相比，EfficientNetV2有以下区别：
- 在浅层网络中大量运用了
MBConv和新加入的fused-MBConv - 使用了较小的expansion ratio，可以达到较小的内存访问开销
- 偏向于
kernel3x3，但这需要增加层数来弥补小kernel感受野的不足 - 移除了last stride-1 stage，但是这是由于NAS搜索出来的，所以是作者的猜测可能是在参数量和访存开销的优化。
code
# 使用的是https://github.com/WZMIAOMIAO/deep-learning-for-image-processing/blob/master/pytorch_classification/Test11_efficientnetV2/model.py 中的代码！
from collections import OrderedDict
from functools import partial
from typing import Callable, Optional
import torch.nn as nn
import torch
from torch import Tensor
def drop_path(x, drop_prob: float = 0., training: bool = False):
"""
Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
"Deep Networks with Stochastic Depth", https://arxiv.org/pdf/1603.09382.pdf
This function is taken from the rwightman.
It can be seen here:
https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/layers/drop.py#L140
"""
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
class DropPath(nn.Module):
"""
Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
"Deep Networks with Stochastic Depth", https://arxiv.org/pdf/1603.09382.pdf
"""
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)
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
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
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的情况所以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) # 注意这里没有激活函数，所有传入Identity
self.out_channels = out_c
# 只有在使用shortcut连接时才使用dropout层
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
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
# 只有当expand ratio不等于1时才有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) # 注意没有激活函数
else:
# 当只有project_conv时的情况
self.project_conv = ConvBNAct(input_c,
out_c,
kernel_size=kernel_size,
stride=stride,
norm_layer=norm_layer,
activation_layer=activation_layer) # 注意有激活函数
self.out_channels = out_c
# 只有在使用shortcut连接时才使用dropout层
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
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) # 激活函数默认是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)}) # 激活函数默认是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
def efficientnetv2_s(num_classes: int = 1000):
"""
EfficientNetV2
https://arxiv.org/abs/2104.00298
"""
# train_size: 300, eval_size: 384
# repeat, kernel, stride, expansion, in_c, out_c, operator, se_ratio
model_config = [[2, 3, 1, 1, 24, 24, 0, 0],
[4, 3, 2, 4, 24, 48, 0, 0],
[4, 3, 2, 4, 48, 64, 0, 0],
[6, 3, 2, 4, 64, 128, 1, 0.25],
[9, 3, 1, 6, 128, 160, 1, 0.25],
[15, 3, 2, 6, 160, 256, 1, 0.25]]
model = EfficientNetV2(model_cnf=model_config,
num_classes=num_classes,
dropout_rate=0.2)
return model
def efficientnetv2_m(num_classes: int = 1000):
"""
EfficientNetV2
https://arxiv.org/abs/2104.00298
"""
# train_size: 384, eval_size: 480
# repeat, kernel, stride, expansion, in_c, out_c, operator, se_ratio
model_config = [[3, 3, 1, 1, 24, 24, 0, 0],
[5, 3, 2, 4, 24, 48, 0, 0],
[5, 3, 2, 4, 48, 80, 0, 0],
[7, 3, 2, 4, 80, 160, 1, 0.25],
[14, 3, 1, 6, 160, 176, 1, 0.25],
[18, 3, 2, 6, 176, 304, 1, 0.25],
[5, 3, 1, 6, 304, 512, 1, 0.25]]
model = EfficientNetV2(model_cnf=model_config,
num_classes=num_classes,
dropout_rate=0.3)
return model
def efficientnetv2_l(num_classes: int = 1000):
"""
EfficientNetV2
https://arxiv.org/abs/2104.00298
"""
# train_size: 384, eval_size: 480
# repeat, kernel, stride, expansion, in_c, out_c, operator, se_ratio
model_config = [[4, 3, 1, 1, 32, 32, 0, 0],
[7, 3, 2, 4, 32, 64, 0, 0],
[7, 3, 2, 4, 64, 96, 0, 0],
[10, 3, 2, 4, 96, 192, 1, 0.25],
[19, 3, 1, 6, 192, 224, 1, 0.25],
[25, 3, 2, 6, 224, 384, 1, 0.25],
[7, 3, 1, 6, 384, 640, 1, 0.25]]
model = EfficientNetV2(model_cnf=model_config,
num_classes=num_classes,
dropout_rate=0.4)
return model
from torchsummary import summary
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = efficientnetv2_l()
model = model.to(device)
summary(model, (3,256,256))
使用torchsummary输出结果:
================================================================
Total params: 118,515,272
Trainable params: 118,515,272
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.75
Forward/backward pass size (MB): 1576.33
Params size (MB): 452.10
Estimated Total Size (MB): 2029.18
----------------------------------------------------------------