网络发表的论文：EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
论文下载：论文下载地址论文相关代码：论文提供github代码访问地址
这就是可能为什么EfficientNet会有不同的版本模型，网络的深度和宽度不同，效果也就不同.
EfficientNet 模型从 B0 到 B7 对于电脑的显存要求越来越高的。
论文中不同 EfficientNet 模型的性能对比
解释：
MBConv1 ， MBConv6 …MBConv 后的数字就是channel 的 n 值（倍率因子）
11 卷积 升维
se 为注意力机制
se 后的 11 卷积 降维
SE 注意力机制模块
requirement
numpy==1.19.5
matplotlib==3.2.1
tqdm==4.56.0
torch >=1.7.1
torchvision>=0.8.2
声明：
这里以 EfficientNet_B0 模型为例，实现网络的搭建训练与预测，但是实际代码包含了实现从 B0 到 B7 的功能，只要更改相应的参数，就可改变使用不同的模型进行训练，所以看起来比较复杂，如果熟悉以后，可以单独拿出来自己需要的代码块，组成单一模型的网络架构，会对网络的搭建与功能实现理解的更加清晰！
model.py 文件
依据上述的 EfficientNet-B0 baseline network 网络结构实现（卷积层、池化层、全连接层）
代码关键地方参考注释
import math
import copy
from functools import partial
from collections import OrderedDict
from typing import Optional, Callable
import torch
import torch.nn as nn
from torch import Tensor
from torch.nn import functional as F
def _make_divisible(ch, divisor=8, min_ch=None): # 将传入的channel个数调整到离它最近的8的整数倍，这样对于我们的硬件更加的友好
"""
This function is taken from the original tf repo.
It ensures that all layers have a channel number that is divisible by 8
It can be seen here:
https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
"""
if min_ch is None:
min_ch = divisor
new_ch = max(min_ch, int(ch + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_ch < 0.9 * ch:
new_ch += divisor
return new_ch
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 ConvBNActivation(nn.Sequential):
def __init__(self,
in_planes: int,
out_planes: int,
kernel_size: int = 3,
stride: int = 1,
groups: int = 1, # 作用：控制当前的卷积结构是使用普通的卷积还是使用 Dw 卷积
norm_layer: Optional[Callable[..., nn.Module]] = None, # (BN结构)
activation_layer: Optional[Callable[..., nn.Module]] = None): #（激活函数）
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)
# 定义卷积层
super(ConvBNActivation, self).__init__(nn.Conv2d(in_channels=in_planes,
out_channels=out_planes,
kernel_size=kernel_size,
stride=stride,
padding=padding,
groups=groups,
bias=False), # 使用了 BN 结构，bias 设置为 false
norm_layer(out_planes),
activation_layer())
# SE 模块（注意力机制）
class SqueezeExcitation(nn.Module):
def __init__(self,
input_c: int, # block input channel
expand_c: int, # block expand channel
squeeze_factor: int = 4):
super(SqueezeExcitation, self).__init__()
squeeze_c = input_c // squeeze_factor
self.fc1 = nn.Conv2d(expand_c, squeeze_c, 1) # 全连接层
self.ac1 = nn.SiLU() # alias Swish
self.fc2 = nn.Conv2d(squeeze_c, expand_c, 1)
self.ac2 = nn.Sigmoid()
def forward(self, x: Tensor) -> Tensor:
scale = F.adaptive_avg_pool2d(x, output_size=(1, 1)) # 全局平均池化
scale = self.fc1(scale)
scale = self.ac1(scale)
scale = self.fc2(scale)
scale = self.ac2(scale)
return scale * x
class InvertedResidualConfig:
# kernel_size, in_channel, out_channel, exp_ratio, strides, use_SE, drop_connect_rate
def __init__(self,
kernel: int, # 3 or 5
input_c: int,
out_c: int,
expanded_ratio: int, # 1 or 6
stride: int, # 1 or 2
use_se: bool, # True
drop_rate: float,
index: str, # 1a, 2a, 2b, ...
width_coefficient: float): # 倍率因子
self.input_c = self.adjust_channels(input_c, width_coefficient)
self.kernel = kernel
self.expanded_c = self.input_c * expanded_ratio
self.out_c = self.adjust_channels(out_c, width_coefficient)
self.use_se = use_se
self.stride = stride
self.drop_rate = drop_rate
self.index = index
@staticmethod
def adjust_channels(channels: int, width_coefficient: float):
return _make_divisible(channels * width_coefficient, 8)
class InvertedResidual(nn.Module):
def __init__(self,
cnf: InvertedResidualConfig,
norm_layer: Callable[..., nn.Module]):
super(InvertedResidual, self).__init__()
if cnf.stride not in [1, 2]:
raise ValueError("illegal stride value.")
self.use_res_connect = (cnf.stride == 1 and cnf.input_c == cnf.out_c)
layers = OrderedDict()
activation_layer = nn.SiLU # alias Swish
# expand
if cnf.expanded_c != cnf.input_c:
layers.update({"expand_conv": ConvBNActivation(cnf.input_c,
cnf.expanded_c,
kernel_size=1,
norm_layer=norm_layer,
activation_layer=activation_layer)})
# depthwise
layers.update({"dwconv": ConvBNActivation(cnf.expanded_c,
cnf.expanded_c,
kernel_size=cnf.kernel,
stride=cnf.stride,
groups=cnf.expanded_c,
norm_layer=norm_layer,
activation_layer=activation_layer)})
if cnf.use_se:
layers.update({"se": SqueezeExcitation(cnf.input_c,
cnf.expanded_c)})
# project
layers.update({"project_conv": ConvBNActivation(cnf.expanded_c,
cnf.out_c,
kernel_size=1,
norm_layer=norm_layer,
activation_layer=nn.Identity)})
self.block = nn.Sequential(layers)
self.out_channels = cnf.out_c
self.is_strided = cnf.stride > 1
# 只有在使用shortcut连接时才使用dropout层
if self.use_res_connect and cnf.drop_rate > 0:
self.dropout = DropPath(cnf.drop_rate)
else:
self.dropout = nn.Identity()
def forward(self, x: Tensor) -> Tensor:
result = self.block(x)
result = self.dropout(result)
if self.use_res_connect:
result += x
return result
class EfficientNet(nn.Module):
def __init__(self,
width_coefficient: float,
depth_coefficient: float,
num_classes: int = 1000,
dropout_rate: float = 0.2,
drop_connect_rate: float = 0.2,
block: Optional[Callable[..., nn.Module]] = None,
norm_layer: Optional[Callable[..., nn.Module]] = None
):
super(EfficientNet, self).__init__()
# kernel_size, in_channel, out_channel, exp_ratio, strides, use_SE, drop_connect_rate, repeats
default_cnf = [[3, 32, 16, 1, 1, True, drop_connect_rate, 1],
[3, 16, 24, 6, 2, True, drop_connect_rate, 2],
[5, 24, 40, 6, 2, True, drop_connect_rate, 2],
[3, 40, 80, 6, 2, True, drop_connect_rate, 3],
[5, 80, 112, 6, 1, True, drop_connect_rate, 3],
[5, 112, 192, 6, 2, True, drop_connect_rate, 4],
[3, 192, 320, 6, 1, True, drop_connect_rate, 1]]
def round_repeats(repeats):
"""Round number of repeats based on depth multiplier."""
return int(math.ceil(depth_coefficient * repeats))
if block is None:
block = InvertedResidual
if norm_layer is None:
norm_layer = partial(nn.BatchNorm2d, eps=1e-3, momentum=0.1)
adjust_channels = partial(InvertedResidualConfig.adjust_channels,
width_coefficient=width_coefficient)
# build inverted_residual_setting
bneck_conf = partial(InvertedResidualConfig,
width_coefficient=width_coefficient)
b = 0
num_blocks = float(sum(round_repeats(i[-1]) for i in default_cnf))
inverted_residual_setting = []
for stage, args in enumerate(default_cnf):
cnf = copy.copy(args)
for i in range(round_repeats(cnf.pop(-1))):
if i > 0:
# strides equal 1 except first cnf
cnf[-3] = 1 # strides
cnf[1] = cnf[2] # input_channel equal output_channel
cnf[-1] = args[-2] * b / num_blocks # update dropout ratio
index = str(stage + 1) + chr(i + 97) # 1a, 2a, 2b, ... 可以记录当前MBConv结构是属于第几个stage中的第几个MBConv结构
inverted_residual_setting.append(bneck_conf(*cnf, index))
b += 1
# create layers
layers = OrderedDict()
# first conv
layers.update({"stem_conv": ConvBNActivation(in_planes=3,
out_planes=adjust_channels(32),
kernel_size=3,
stride=2,
norm_layer=norm_layer)})
# building inverted residual blocks
for cnf in inverted_residual_setting:
layers.update({cnf.index: block(cnf, norm_layer)})
# build top
last_conv_input_c = inverted_residual_setting[-1].out_c
last_conv_output_c = adjust_channels(1280)
layers.update({"top": ConvBNActivation(in_planes=last_conv_input_c,
out_planes=last_conv_output_c,
kernel_size=1,
norm_layer=norm_layer)})
# 池化层结构搭建
self.features = nn.Sequential(layers)
self.avgpool = nn.AdaptiveAvgPool2d(1)
# 分类器
classifier = []
if dropout_rate > 0:
classifier.append(nn.Dropout(p=dropout_rate, inplace=True))
classifier.append(nn.Linear(last_conv_output_c, num_classes))
self.classifier = nn.Sequential(*classifier)
# 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_impl(self, x: Tensor) -> Tensor:
x = self.features(x)
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.classifier(x)
return x
def forward(self, x: Tensor) -> Tensor:
return self._forward_impl(x)
# 不同版本的 efficient 参数传入设置实现
def efficientnet_b0(num_classes=1000):
# input image size 224x224
return EfficientNet(width_coefficient=1.0,
depth_coefficient=1.0,
dropout_rate=0.2,
num_classes=num_classes)
def efficientnet_b1(num_classes=1000):
# input image size 240x240
return EfficientNet(width_coefficient=1.0,
depth_coefficient=1.1,
dropout_rate=0.2,
num_classes=num_classes)
def efficientnet_b2(num_classes=1000):
# input image size 260x260
return EfficientNet(width_coefficient=1.1,
depth_coefficient=1.2,
dropout_rate=0.3,
num_classes=num_classes)
def efficientnet_b3(num_classes=1000):
# input image size 300x300
return EfficientNet(width_coefficient=1.2,
depth_coefficient=1.4,
dropout_rate=0.3,
num_classes=num_classes)
def efficientnet_b4(num_classes=1000):
# input image size 380x380
return EfficientNet(width_coefficient=1.4,
depth_coefficient=1.8,
dropout_rate=0.4,
num_classes=num_classes)
def efficientnet_b5(num_classes=1000):
# input image size 456x456
return EfficientNet(width_coefficient=1.6,
depth_coefficient=2.2,
dropout_rate=0.4,
num_classes=num_classes)
def efficientnet_b6(num_classes=1000):
# input image size 528x528
return EfficientNet(width_coefficient=1.8,
depth_coefficient=2.6,
dropout_rate=0.5,
num_classes=num_classes)
def efficientnet_b7(num_classes=1000):
# input image size 600x600
return EfficientNet(width_coefficient=2.0,
depth_coefficient=3.1,
dropout_rate=0.5,
num_classes=num_classes)
train.py
代码关键地方参考注释
import os
import math
import argparse
import torch
import torch.optim as optim
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
import torch.optim.lr_scheduler as lr_scheduler
from model import efficientnet_b0 as create_model # 使用 b0 版本 与35行 num_model = "B0" 保持一致（控制传入的图片尺寸大小，不同版本传入的图片尺寸大小不一样）
from my_dataset import MyDataSet
from utils import read_split_data, train_one_epoch, evaluate
def main(args):
device = torch.device(args.device if torch.cuda.is_available() else "cpu")
print(args)
print('Start Tensorboard with "tensorboard --logdir=runs", view at http://localhost:6006/')
tb_writer = SummaryWriter()
if os.path.exists("./weights") is False:
os.makedirs("./weights")
train_images_path, train_images_label, val_images_path, val_images_label = read_split_data(args.data_path)
img_size = {"B0": 224,
"B1": 240,
"B2": 260,
"B3": 300,
"B4": 380,
"B5": 456,
"B6": 528,
"B7": 600}
num_model = "B0"
data_transform = {
"train": transforms.Compose([transforms.RandomResizedCrop(img_size[num_model]),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
"val": transforms.Compose([transforms.Resize(img_size[num_model]),
transforms.CenterCrop(img_size[num_model]),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])}
# 实例化训练数据集
train_dataset = MyDataSet(images_path=train_images_path,
images_class=train_images_label,
transform=data_transform["train"])
# 实例化验证数据集
val_dataset = MyDataSet(images_path=val_images_path,
images_class=val_images_label,
transform=data_transform["val"])
batch_size = args.batch_size
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8]) # number of workers
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
pin_memory=True,
num_workers=nw,
collate_fn=train_dataset.collate_fn)
val_loader = torch.utils.data.DataLoader(val_dataset,
batch_size=batch_size,
shuffle=False,
pin_memory=True,
num_workers=nw,
collate_fn=val_dataset.collate_fn)
# 如果存在预训练权重则载入
model = create_model(num_classes=args.num_classes).to(device)
if os.path.exists(args.weights):
weights_dict = torch.load(args.weights, map_location=device)
load_weights_dict = {k: v for k, v in weights_dict.items()
if model.state_dict()[k].numel() == v.numel()}
print(model.load_state_dict(load_weights_dict, strict=False))
# 是否冻结权重
if args.freeze_layers:
for name, para in model.named_parameters():
# 除最后一个卷积层和全连接层外，其他权重全部冻结
if ("features.top" not in name) and ("classifier" not in name):
para.requires_grad_(False)
else:
print("training {}".format(name))
pg = [p for p in model.parameters() if p.requires_grad]
optimizer = optim.SGD(pg, lr=args.lr, momentum=0.9, weight_decay=1E-4)
# Scheduler https://arxiv.org/pdf/1812.01187.pdf
lf = lambda x: ((1 + math.cos(x * math.pi / args.epochs)) / 2) * (1 - args.lrf) + args.lrf # cosine
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
for epoch in range(args.epochs):
# train
mean_loss = train_one_epoch(model=model,
optimizer=optimizer,
data_loader=train_loader,
device=device,
epoch=epoch)
scheduler.step()
# validate
acc = evaluate(model=model,
data_loader=val_loader,
device=device)
print("[epoch {}] accuracy: {}".format(epoch, round(acc, 3)))
tags = ["loss", "accuracy", "learning_rate"]
tb_writer.add_scalar(tags[0], mean_loss, epoch)
tb_writer.add_scalar(tags[1], acc, epoch)
tb_writer.add_scalar(tags[2], optimizer.param_groups[0]["lr"], epoch)
torch.save(model.state_dict(), "./weights/model-{}.pth".format(epoch))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--num_classes', type=int, default=5) # 训练时候的类别个数依据需要修改
parser.add_argument('--epochs', type=int, default=30)
parser.add_argument('--batch-size', type=int, default=16)
parser.add_argument('--lr', type=float, default=0.01)
parser.add_argument('--lrf', type=float, default=0.01)
# 数据集所在根目录
# http://download.tensorflow.org/example_images/flower_photos.tgz
parser.add_argument('--data-path', type=str,
default="/data/flower_photos")
# download model weights（B0-->B7）
# 此预训练权重非pytorch官网提供的权重，而是通过tensorflow官方转化过来的权重
# 链接: https://pan.baidu.com/s/1ouX0UmjCsmSx3ZrqXbowjw 密码: 090i
parser.add_argument('--weights', type=str, default='./efficientnetb0.pth', # 选用的预训练权重要和使用的版本一致
help='initial weights path')
parser.add_argument('--freeze-layers', type=bool, default=False)
# freeze-layers默认为false（调整所有的权重，），如果只想微调最后一个1*1的卷积层，以及全连接层，改为True 即可
parser.add_argument('--device', default='cuda:0', help='device id (i.e. 0 or 0,1 or cpu)')
opt = parser.parse_args()
main(opt)
更改数据集训练自己的模型
依据给出的代码，更改参数后运行
更改数据的地方
① 数据集路径
② 训练的参数（num_classes，epochs，batch-size等等）
③ 预训练的权重，这里使用了预训练模型_b0 (网盘链接中的预训练权重)
训练结果：
训练数据集的文件夹方式（文件夹里直接是.jpg 图片）
predict.py
import os
import json
import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
from model import efficientnet_b0 as create_model # 训练哪个模型就导入哪个模型
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
img_size = {"B0": 224,
"B1": 240,
"B2": 260,
"B3": 300,
"B4": 380,
"B5": 456,
"B6": 528,
"B7": 600}
num_model = "B0" # 注意不同模型之间输入图像大小的问题，模型参数保持一致
data_transform = transforms.Compose(
[transforms.Resize(img_size[num_model]),
transforms.CenterCrop(img_size[num_model]),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
# load image
img_path = "../tulip.jpg"
assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
img = Image.open(img_path)
plt.imshow(img)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
# read class_indict （）
json_path = './class_indices.json'
assert os.path.exists(json_path), "file: '{}' dose not exist.".format(json_path)
json_file = open(json_path, "r")
class_indict = json.load(json_file)
# create model（创建模型）
model = create_model(num_classes=5).to(device) # 训练时候的类别个数依据需要修改（训练脚本同样）
# load model weights
model_weight_path = "./weights/model-29.pth" # 导入训练好的权重
model.load_state_dict(torch.load(model_weight_path, map_location=device))
model.eval()
with torch.no_grad():
# predict class
output = torch.squeeze(model(img.to(device))).cpu()
predict = torch.softmax(output, dim=0)
predict_cla = torch.argmax(predict).numpy()
print_res = "class: {} prob: {:.3}".format(class_indict[str(predict_cla)],
predict[predict_cla].numpy())
plt.title(print_res)
print(print_res)
plt.show()
if __name__ == '__main__':
main()
数据集问题
如果使用自己的数据集，与此保持结构，创建不同类别的子文件夹
本文复现时候数据划分：
实操预测的效果：
依据上面给的预测文件中的代码，更改参数后运行
① 直接使用代码训练自己的数据集时候，对于model.py 不用修改
② 对于 train.py文件 ， 选定要使用的训练模板b0-b7中的哪一个，从连接中网盘下对应的载预训练权重，放在代码根目录下，并在代码中修改路径导入，然后把数据集划分并将路径导入代码，之后再修改训练超参数，就可以进行训练。
③ 使用predict.py预测，只需要更改导入训练好的模型权重，指定要预测的图片与路径即可，代码其他部分不用动。
使用集成好的模型，直接调用库训练自己的数据集，简化代码量
from efficientnet_pytorch import EfficientNet
后续更新。。。。。。
视频链接：https://www.bilibili.com/video/BV1XK4y1U7PX