一、EfficientNet V1
1)Google2019发表的文章
2)论文中提出,EfficientNet-B7在Imagenet top-1上达到了当年最高准确率84.3%
3)与之前准确率最高的GPip相比,参数量仅仅为其1/8.4,推理速度提升了6.1倍
模型的大小与准确率对比如下(Top1)
同时探索输入分辨率,网络的深度,宽度的影响(图E)
宽度:特征矩阵的channel
增加网络的深度depth能够得到更加丰富、复杂的特征。但面临梯度消失,训练困难的问题。
增加网络的width能够获得更高细粒度的特征并且也更容易训练,但对于witdh很大而深度较浅的网络很难学习更深层次的特征
增加输入图片的分辨率能够潜在获得更高细粒度的特征模板,但对于非常高的输入分辨率,准确率的增益也会减小,并且分辨率图像会增加计算量
单独的宽度、深度、分辨率,在准确率达到80%基本饱和了,但同时改变则可以超过82%。
网络结构
EfficientNet-B0
Channel 输出特征矩阵个数
layers:重复MBConv多少次
MBConv
- 第一个升维的1x1卷积层,它的卷积核个数是输入特征矩阵channel的n倍(表格中的1 6)
- 当n=1时,不要第一个升维的1x1卷积层,即Stage2中的MBConv1结构都没有第一个升维1x1卷积层
- shortcut连接,仅当输入MBConv结构的特征矩阵与输入的特征矩阵shape相同时才存在。
SE模块
一个全局平均池化,两个全连接层
第一个全连接层
- 节点个数是输入该MBConv特征矩阵的1/4
- 激活函数:Swish。
第二个全连接层的
- 节点个数等于Depthwise Conv层输出的特征矩阵channels
- 激活函数:sigmoid
width_coefficient代表channel维度的倍率因子,如下
32*1.8=57.6 取到离它最近的8的证书倍即56
depth_coefficient代表depth维度上的倍率因子,从Stage2-Stage8
4*2.6=10.4 向上取证即11
性能对比
1)准确率高
2)参数个数少
3)占用GPU的内存,推理速度与FLOPS不是直接相关的
二、EfficientNet V2
1)2021.4 CVPR 上发表
2) 引入Fused-MBConv模块
3)引入渐进式学习策略(训练更快)
4)Top-1达到87.3%
训练速度提升11倍,参数量减少1/6.8
由上图得知,V2准确率高,速度快
EfficientNetV1中,关注的是准确率,参数数量以及FLOPs,在EfficientV2中作者关注模型的训练速度。
Efficientv1中存在的问题以及V2的解决方法
-
训练图像的尺寸很大时,训练速度慢
1)小尺寸的准确率反而高一些
2)batch=24的时候,出现内存溢出,而batch在训练时大一些好,所以降低训练图片尺寸 -
在网络浅层中使用Depthwise convolution 速度很慢
无法重复使用加速器,将MBConv 替换为FusedMBConv
Fused stage1-3浅层 最优
-
同等放大每个stage是次优的
深度和宽度是同等放大的,但每个stage对网络的训练速度以及参数数量的贡献并不相同,直接使用同等缩放策略不合理。作者使用了非均匀的缩放策略来缩放模型。
EfficientV2网络框架
Layers:重复的次数
Stride:步距 2(对第一层而言)
- 除了使用MBConv 模块,还使用Fused-MBConv模块
- 使用较小的expansion ratio
- 偏向使用更小的kernel_size(3x3)
- 移除了EfficientNetV1中最后一个步距为1的stage
Fused-MBConv模块
Progressive Learning 渐进式学习策略
在训练不同的图片尺寸时,使用不同的正则化方法的强度。
训练早期使用较小的训练尺寸以及较弱的正则化方法weak regularization。接着逐渐提升图像尺寸,同时增强正则化方法。regularization包括Dropout,RandAugment以及Mixup
渐进式策略使用在其它模型上,精度与速度均有所提升
三、源码
EfficientNetV2
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
训练
[valid epoch 29] loss: 0.163, acc: 0.956: 100%|
tensorboard