本文为为🔗365天深度学习训练营内部文章
原作者：K同学啊
一 DenseNet算法结构
其基本思路与ResNet一致，但是它建立的是前面所有层和后面层的密集连接，它的另一大特色是通过特征在channel上的连接来实现特征重用。
二 设计理念
三 结构
四 算法代码
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,random
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
devicedata_dir = './data/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
classeNames
import matplotlib.pyplot as plt
from PIL import Image
# 指定图像文件夹路径
image_folder = './data/OSCC/'
# 获取文件夹中的所有图像文件
image_files = [f for f in os.listdir(image_folder) if f.endswith((".jpg", ".png", ".jpeg"))]
# 创建Matplotlib图像
fig, axes = plt.subplots(3, 8, figsize=(16, 6))
# 使用列表推导式加载和显示图像
for ax, img_file in zip(axes.flat, image_files):
img_path = os.path.join(image_folder, img_file)
img = Image.open(img_path)
ax.imshow(img)
ax.axis('off')
# 显示图像
plt.tight_layout()
plt.show()
total_datadir = './data/'
# 关于transforms.Compose的更多介绍可以参考：https://blog.csdn.net/qq_38251616/article/details/124878863
train_transforms = transforms.Compose([
transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
transforms.Normalize( # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])
total_data = datasets.ImageFolder(total_datadir,transform=train_transforms)
total_data
# 划分训练集
train_size = int(0.7 * len(total_data))
test_size = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
train_dataset, test_dataset
batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=1)for X, y in test_dl:
print("Shape of X [N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape, y.dtype)
breakShape of X [N, C, H, W]: torch.Size([32, 3, 224, 224]) Shape of y: torch.Size([32]) torch.int64
import torch.nn as nn
import torch.nn.functional as F
from collections import OrderedDict
import re
import torch
from torch.utils import model_zoo
from torchvision.models.video.resnet import model_urls
'''
_DenseLayer 类实现了 DenseNet 的关键机制：
通过使用批归一化、ReLU 激活和卷积层来提取特征，并通过密集连接促进特征的共享和再利用。
'''
class _DenseLayer(nn.Sequential):
def __init__(self, num_input_features, growth_rate, bn_size, drop_rate):
'''
:param num_input_features: 输入特征数
:param growth_rate: 每层增长的特征数
:param bn_size: 批归一化层的大小
:param drop_rate: 丢弃率
'''
super(_DenseLayer, self).__init__()
# 添加一个批归一化层（BatchNorm2d），用于对输入特征进行标准化
self.add_module("norm1", nn.BatchNorm2d(num_input_features))
# 添加一个 ReLU 激活函数
self.add_module("relu1", nn.ReLU(inplace=True))
# 添加第一个卷积层（Conv2d），其输入通道数为 num_input_features，输出通道数为 bn_size * growth_rate。
# 这里使用 1x1 卷积，主要用于减少特征图的维度，并引入更多特征
self.add_module("conv1", nn.Conv2d(num_input_features, bn_size * growth_rate,
kernel_size=1, stride=1, bias=False))
# 添加第二个批归一化层，应用于第一个卷积层的输出
self.add_module("norm2", nn.BatchNorm2d(bn_size * growth_rate))
# 添加第二个 ReLU 激活函数。与第一个激活函数相同，提供非线性变换
self.add_module("relu2", nn.ReLU(inplace=True))
# 添加第二个卷积层，输入通道数为 bn_size * growth_rate，输出通道数为 growth_rate。
# 这里使用 3x3 卷积，通常用于提取更复杂的特征
self.add_module("conv2", nn.Conv2d(bn_size * growth_rate, growth_rate,
kernel_size=3, stride=1, padding=1, bias=False))
# 保存丢弃率（drop rate），用于在前向传播中进行 dropout 操作，以防止过拟合
self.drop_rate = drop_rate
def forward(self, x):
# 调用父类 nn.Sequential 的 forward 方法，将输入 x 传递给之前添加的所有层。
# 输出 new_features 是经过所有层处理后的特征
new_features = super(_DenseLayer, self).forward(x)
# 检查丢弃率是否大于 0，如果是，则进行 dropout 操作
if self.drop_rate > 0:
# 对新特征应用 dropout，p 是丢弃概率，training 参数指示当前是否在训练模式。这将随机将一部分特征置为零，从而帮助减少过拟合
new_features = F.dropout(new_features, p=self.drop_rate, training=self.training)
# 将输入 x 和新特征 new_features 在通道维度（即维度 1）上连接。这样可以实现密集连接，允许模型利用前面层的所有特征
return torch.cat([x, new_features], 1)
'''
创建一个包含多个密集层的模块，每个层都会根据前面层的输出特征动态调整输入特征数量，形成一个密集连接的网络结构。
'''
class _DenseBlock(nn.Sequential):
def __init__(self, num_layers, num_input_features, bn_size, growth_rate, drop_rate):
'''
num_layers: 该密集块中层的数量。
num_input_features: 输入特征的数量。
bn_size: 批量归一化的大小。
growth_rate: 每层输出特征的增长率。
drop_rate: dropout 率，用于防止过拟合
'''
super(_DenseBlock, self).__init__()
# 开始一个循环，迭代 num_layers 次，为每一层创建一个密集层
for i in range(num_layers):
# 在每次迭代中，创建一个新的 _DenseLayer 实例。该层的输入特征数量为 num_input_features + i * growth_rate，即前面所有层的输出特征总和
layer = _DenseLayer(num_input_features + i * growth_rate, growth_rate, bn_size, drop_rate)
# 将创建的密集层添加到模块中，并命名为 denselayer1、denselayer2，依此类推。这样可以方便后续访问和调试
self.add_module("denselayer%d" % (i + 1,), layer)
'''
构建神经网络的一个过渡层,在神经网络中通常用于特征的转换和下采样
'''
class _Transition(nn.Sequential):
def __init__(self,num_input_feature,num_output_features):
super(_Transition,self).__init__()
# 添加一个批归一化层，标准化输入特征
self.add_module("norm",nn.BatchNorm2d(num_input_feature))
# 添加一个 ReLU 激活函数
self.add_module("relu",nn.ReLU(inplace=True))
# 添加一个卷积层，使用 1x1 的卷积核，连接输入特征和输出特征。
self.add_module("conv",nn.Conv2d(num_input_feature,num_output_features,kernel_size=1,
stride=1,bias=False))
# 添加一个 2x2 的平均池化层，步幅为 2，用于减少特征图的大小
self.add_module("pool",nn.AvgPool2d(2,stride=2))
class DenseNet(nn.Module):
def __init__(self,growth_rate=32,block_config=(6,12,24,16),num_init_features=64,
bn_size=4,compression_rate=0.5,drop_rate=0,num_classes=1000):
'''
growth_rate: 每个DenseBlock中每层输出特征图的增长率。
block_config: 一个元组，指定每个DenseBlock中的层数。
num_init_features: 第一层卷积的输出特征数量。
bn_size: Batch Normalization的大小
compression_rate: 每个Transition层中输出特征数量的压缩比例。
drop_rate: Dropout的概率
num_classes: 最终分类的类别数。
'''
super(DenseNet,self).__init__()
# 第一层卷积
self.features = nn.Sequential(OrderedDict([
("conv0",nn.Conv2d(3,num_init_features,kernel_size=7,stride=2,padding=3,bias=False)),
("norm0",nn.BatchNorm2d(num_init_features)),
("relu0",nn.ReLU(inplace=True)),
("pool0",nn.MaxPool2d(3,stride=2,padding=1))
]))
# DenseBlock
num_features = num_init_features
# 遍历block_config，为每个DenseBlock构建模型
for i,num_layers in enumerate(block_config):
block = _DenseBlock(num_layers,num_features,bn_size,growth_rate,drop_rate)
self.features.add_module("denseblock%d"%(i+1),block)
# 更新当前特征数量，每个DenseBlock后增加num_layers * growth_rate
num_features += num_layers*growth_rate
if i != len(block_config) - 1:
# 定义Transition层，连接DenseBlock，减小特征图尺寸（通过compression_rate
transition = _Transition(num_features,int(num_features*compression_rate))
# 将DenseBlock和Transition层添加到模型中
self.features.add_module("transition%d"%(i+1),transition)
num_features = int(num_features * compression_rate)
# final bn+relu
# 在所有DenseBlock和Transition层之后，添加一个Batch Normalization层和ReLU激活层
self.features.add_module("norm5",nn.BatchNorm2d(num_features))
self.features.add_module("relu5",nn.ReLU(inplace=True))
# classification layer
# 定义全连接层，将特征映射到类别数
self.classifier = nn.Linear(num_features,num_classes)
# 参数初始化
'''
遍历所有模块，初始化权重。
卷积层: 使用Kaiming正态分布初始化。
BatchNorm层: 将偏置初始化为0，权重初始化为1。
全连接层: 将偏置初始化为0。
'''
for m in self.modules():
if isinstance(m,nn.Conv2d):
nn.init.kaiming_normal_(m.weight)
elif isinstance(m,nn.BatchNorm2d):
nn.init.constant_(m.bias,0)
nn.init.constant_(m.weight,1)
elif isinstance(m,nn.Linear):
nn.init.constant_(m.bias,0)
def forward(self,x):
'''
self.features(x): 将输入x传递通过所有特征层。
F.avg_pool2d: 在特征图上进行全局平均池化。
view(features.size(0), -1): 将池化后的特征展平。
self.classifier(out): 通过分类层得到输出。
return out: 返回最终的分类结果。
'''
features = self.features(x)
out = F.avg_pool2d(features,7,stride=1).view(features.size(0),-1)
out = self.classifier(out)
return out
def densetnet121(pretrained=False, **kwargs):
model = DenseNet(num_init_features=64, growth_rate=32, block_config=(6, 12, 24, 16), num_classes=len(classeNames))
if pretrained:
pattern = re.compile(
r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$')
# 从指定的 URL 加载 DenseNet-121 的预训练权重，存储在 state_dict
state_dict = model_zoo.load_url(model_urls['densenet121'])
for key in list(state_dict.keys()):
res = pattern.match(key)
if res:
# 创建一个新键，组合匹配结果的前半部分和后半部分
new_key = res.group(1) + res.group(2)
state_dict[new_key] = state_dict[key]
del state_dict[key]
# 将处理后的权重加载到模型中
model.load_state_dict(state_dict)
return model
model = densetnet121()
modelimport torchsummary as summary
summary.summary(model,(3,224,224))----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 64, 112, 112] 9,408
BatchNorm2d-2 [-1, 64, 112, 112] 128
ReLU-3 [-1, 64, 112, 112] 0
MaxPool2d-4 [-1, 64, 56, 56] 0
BatchNorm2d-5 [-1, 64, 56, 56] 128
ReLU-6 [-1, 64, 56, 56] 0
Conv2d-7 [-1, 128, 56, 56] 8,192
BatchNorm2d-8 [-1, 128, 56, 56] 256
ReLU-9 [-1, 128, 56, 56] 0
Conv2d-10 [-1, 32, 56, 56] 36,864
BatchNorm2d-11 [-1, 96, 56, 56] 192
ReLU-12 [-1, 96, 56, 56] 0
Conv2d-13 [-1, 128, 56, 56] 12,288
BatchNorm2d-14 [-1, 128, 56, 56] 256
ReLU-15 [-1, 128, 56, 56] 0
Conv2d-16 [-1, 32, 56, 56] 36,864
BatchNorm2d-17 [-1, 128, 56, 56] 256
ReLU-18 [-1, 128, 56, 56] 0
Conv2d-19 [-1, 128, 56, 56] 16,384
BatchNorm2d-20 [-1, 128, 56, 56] 256
ReLU-21 [-1, 128, 56, 56] 0
Conv2d-22 [-1, 32, 56, 56] 36,864
BatchNorm2d-23 [-1, 160, 56, 56] 320
ReLU-24 [-1, 160, 56, 56] 0
Conv2d-25 [-1, 128, 56, 56] 20,480
BatchNorm2d-26 [-1, 128, 56, 56] 256
ReLU-27 [-1, 128, 56, 56] 0
Conv2d-28 [-1, 32, 56, 56] 36,864
BatchNorm2d-29 [-1, 192, 56, 56] 384
ReLU-30 [-1, 192, 56, 56] 0
Conv2d-31 [-1, 128, 56, 56] 24,576
BatchNorm2d-32 [-1, 128, 56, 56] 256
ReLU-33 [-1, 128, 56, 56] 0
Conv2d-34 [-1, 32, 56, 56] 36,864
BatchNorm2d-35 [-1, 224, 56, 56] 448
ReLU-36 [-1, 224, 56, 56] 0
Conv2d-37 [-1, 128, 56, 56] 28,672
BatchNorm2d-38 [-1, 128, 56, 56] 256
ReLU-39 [-1, 128, 56, 56] 0
Conv2d-40 [-1, 32, 56, 56] 36,864
BatchNorm2d-41 [-1, 256, 56, 56] 512
ReLU-42 [-1, 256, 56, 56] 0
Conv2d-43 [-1, 128, 56, 56] 32,768
AvgPool2d-44 [-1, 128, 28, 28] 0
BatchNorm2d-45 [-1, 128, 28, 28] 256
ReLU-46 [-1, 128, 28, 28] 0
Conv2d-47 [-1, 128, 28, 28] 16,384
BatchNorm2d-48 [-1, 128, 28, 28] 256
ReLU-49 [-1, 128, 28, 28] 0
Conv2d-50 [-1, 32, 28, 28] 36,864
BatchNorm2d-51 [-1, 160, 28, 28] 320
ReLU-52 [-1, 160, 28, 28] 0
Conv2d-53 [-1, 128, 28, 28] 20,480
BatchNorm2d-54 [-1, 128, 28, 28] 256
ReLU-55 [-1, 128, 28, 28] 0
Conv2d-56 [-1, 32, 28, 28] 36,864
BatchNorm2d-57 [-1, 192, 28, 28] 384
ReLU-58 [-1, 192, 28, 28] 0
Conv2d-59 [-1, 128, 28, 28] 24,576
BatchNorm2d-60 [-1, 128, 28, 28] 256
ReLU-61 [-1, 128, 28, 28] 0
Conv2d-62 [-1, 32, 28, 28] 36,864
BatchNorm2d-63 [-1, 224, 28, 28] 448
ReLU-64 [-1, 224, 28, 28] 0
Conv2d-65 [-1, 128, 28, 28] 28,672
BatchNorm2d-66 [-1, 128, 28, 28] 256
ReLU-67 [-1, 128, 28, 28] 0
Conv2d-68 [-1, 32, 28, 28] 36,864
BatchNorm2d-69 [-1, 256, 28, 28] 512
ReLU-70 [-1, 256, 28, 28] 0
Conv2d-71 [-1, 128, 28, 28] 32,768
BatchNorm2d-72 [-1, 128, 28, 28] 256
ReLU-73 [-1, 128, 28, 28] 0
Conv2d-74 [-1, 32, 28, 28] 36,864
BatchNorm2d-75 [-1, 288, 28, 28] 576
ReLU-76 [-1, 288, 28, 28] 0
Conv2d-77 [-1, 128, 28, 28] 36,864
BatchNorm2d-78 [-1, 128, 28, 28] 256
ReLU-79 [-1, 128, 28, 28] 0
Conv2d-80 [-1, 32, 28, 28] 36,864
BatchNorm2d-81 [-1, 320, 28, 28] 640
ReLU-82 [-1, 320, 28, 28] 0
Conv2d-83 [-1, 128, 28, 28] 40,960
BatchNorm2d-84 [-1, 128, 28, 28] 256
ReLU-85 [-1, 128, 28, 28] 0
Conv2d-86 [-1, 32, 28, 28] 36,864
BatchNorm2d-87 [-1, 352, 28, 28] 704
ReLU-88 [-1, 352, 28, 28] 0
Conv2d-89 [-1, 128, 28, 28] 45,056
BatchNorm2d-90 [-1, 128, 28, 28] 256
ReLU-91 [-1, 128, 28, 28] 0
Conv2d-92 [-1, 32, 28, 28] 36,864
BatchNorm2d-93 [-1, 384, 28, 28] 768
ReLU-94 [-1, 384, 28, 28] 0
Conv2d-95 [-1, 128, 28, 28] 49,152
BatchNorm2d-96 [-1, 128, 28, 28] 256
ReLU-97 [-1, 128, 28, 28] 0
Conv2d-98 [-1, 32, 28, 28] 36,864
BatchNorm2d-99 [-1, 416, 28, 28] 832
ReLU-100 [-1, 416, 28, 28] 0
Conv2d-101 [-1, 128, 28, 28] 53,248
BatchNorm2d-102 [-1, 128, 28, 28] 256
ReLU-103 [-1, 128, 28, 28] 0
Conv2d-104 [-1, 32, 28, 28] 36,864
BatchNorm2d-105 [-1, 448, 28, 28] 896
ReLU-106 [-1, 448, 28, 28] 0
Conv2d-107 [-1, 128, 28, 28] 57,344
BatchNorm2d-108 [-1, 128, 28, 28] 256
ReLU-109 [-1, 128, 28, 28] 0
Conv2d-110 [-1, 32, 28, 28] 36,864
BatchNorm2d-111 [-1, 480, 28, 28] 960
ReLU-112 [-1, 480, 28, 28] 0
Conv2d-113 [-1, 128, 28, 28] 61,440
BatchNorm2d-114 [-1, 128, 28, 28] 256
ReLU-115 [-1, 128, 28, 28] 0
Conv2d-116 [-1, 32, 28, 28] 36,864
BatchNorm2d-117 [-1, 512, 28, 28] 1,024
ReLU-118 [-1, 512, 28, 28] 0
Conv2d-119 [-1, 256, 28, 28] 131,072
AvgPool2d-120 [-1, 256, 14, 14] 0
BatchNorm2d-121 [-1, 256, 14, 14] 512
ReLU-122 [-1, 256, 14, 14] 0
Conv2d-123 [-1, 128, 14, 14] 32,768
BatchNorm2d-124 [-1, 128, 14, 14] 256
ReLU-125 [-1, 128, 14, 14] 0
Conv2d-126 [-1, 32, 14, 14] 36,864
BatchNorm2d-127 [-1, 288, 14, 14] 576
ReLU-128 [-1, 288, 14, 14] 0
Conv2d-129 [-1, 128, 14, 14] 36,864
BatchNorm2d-130 [-1, 128, 14, 14] 256
ReLU-131 [-1, 128, 14, 14] 0
Conv2d-132 [-1, 32, 14, 14] 36,864
BatchNorm2d-133 [-1, 320, 14, 14] 640
ReLU-134 [-1, 320, 14, 14] 0
Conv2d-135 [-1, 128, 14, 14] 40,960
BatchNorm2d-136 [-1, 128, 14, 14] 256
ReLU-137 [-1, 128, 14, 14] 0
Conv2d-138 [-1, 32, 14, 14] 36,864
BatchNorm2d-139 [-1, 352, 14, 14] 704
ReLU-140 [-1, 352, 14, 14] 0
Conv2d-141 [-1, 128, 14, 14] 45,056
BatchNorm2d-142 [-1, 128, 14, 14] 256
ReLU-143 [-1, 128, 14, 14] 0
Conv2d-144 [-1, 32, 14, 14] 36,864
BatchNorm2d-145 [-1, 384, 14, 14] 768
ReLU-146 [-1, 384, 14, 14] 0
Conv2d-147 [-1, 128, 14, 14] 49,152
BatchNorm2d-148 [-1, 128, 14, 14] 256
ReLU-149 [-1, 128, 14, 14] 0
Conv2d-150 [-1, 32, 14, 14] 36,864
BatchNorm2d-151 [-1, 416, 14, 14] 832
ReLU-152 [-1, 416, 14, 14] 0
Conv2d-153 [-1, 128, 14, 14] 53,248
BatchNorm2d-154 [-1, 128, 14, 14] 256
ReLU-155 [-1, 128, 14, 14] 0
Conv2d-156 [-1, 32, 14, 14] 36,864
BatchNorm2d-157 [-1, 448, 14, 14] 896
ReLU-158 [-1, 448, 14, 14] 0
Conv2d-159 [-1, 128, 14, 14] 57,344
BatchNorm2d-160 [-1, 128, 14, 14] 256
ReLU-161 [-1, 128, 14, 14] 0
Conv2d-162 [-1, 32, 14, 14] 36,864
BatchNorm2d-163 [-1, 480, 14, 14] 960
ReLU-164 [-1, 480, 14, 14] 0
Conv2d-165 [-1, 128, 14, 14] 61,440
BatchNorm2d-166 [-1, 128, 14, 14] 256
ReLU-167 [-1, 128, 14, 14] 0
Conv2d-168 [-1, 32, 14, 14] 36,864
BatchNorm2d-169 [-1, 512, 14, 14] 1,024
ReLU-170 [-1, 512, 14, 14] 0
Conv2d-171 [-1, 128, 14, 14] 65,536
BatchNorm2d-172 [-1, 128, 14, 14] 256
ReLU-173 [-1, 128, 14, 14] 0
Conv2d-174 [-1, 32, 14, 14] 36,864
BatchNorm2d-175 [-1, 544, 14, 14] 1,088
ReLU-176 [-1, 544, 14, 14] 0
Conv2d-177 [-1, 128, 14, 14] 69,632
BatchNorm2d-178 [-1, 128, 14, 14] 256
ReLU-179 [-1, 128, 14, 14] 0
Conv2d-180 [-1, 32, 14, 14] 36,864
BatchNorm2d-181 [-1, 576, 14, 14] 1,152
ReLU-182 [-1, 576, 14, 14] 0
Conv2d-183 [-1, 128, 14, 14] 73,728
BatchNorm2d-184 [-1, 128, 14, 14] 256
ReLU-185 [-1, 128, 14, 14] 0
Conv2d-186 [-1, 32, 14, 14] 36,864
BatchNorm2d-187 [-1, 608, 14, 14] 1,216
ReLU-188 [-1, 608, 14, 14] 0
Conv2d-189 [-1, 128, 14, 14] 77,824
BatchNorm2d-190 [-1, 128, 14, 14] 256
ReLU-191 [-1, 128, 14, 14] 0
Conv2d-192 [-1, 32, 14, 14] 36,864
BatchNorm2d-193 [-1, 640, 14, 14] 1,280
ReLU-194 [-1, 640, 14, 14] 0
Conv2d-195 [-1, 128, 14, 14] 81,920
BatchNorm2d-196 [-1, 128, 14, 14] 256
ReLU-197 [-1, 128, 14, 14] 0
Conv2d-198 [-1, 32, 14, 14] 36,864
BatchNorm2d-199 [-1, 672, 14, 14] 1,344
ReLU-200 [-1, 672, 14, 14] 0
Conv2d-201 [-1, 128, 14, 14] 86,016
BatchNorm2d-202 [-1, 128, 14, 14] 256
ReLU-203 [-1, 128, 14, 14] 0
Conv2d-204 [-1, 32, 14, 14] 36,864
BatchNorm2d-205 [-1, 704, 14, 14] 1,408
ReLU-206 [-1, 704, 14, 14] 0
Conv2d-207 [-1, 128, 14, 14] 90,112
BatchNorm2d-208 [-1, 128, 14, 14] 256
ReLU-209 [-1, 128, 14, 14] 0
Conv2d-210 [-1, 32, 14, 14] 36,864
BatchNorm2d-211 [-1, 736, 14, 14] 1,472
ReLU-212 [-1, 736, 14, 14] 0
Conv2d-213 [-1, 128, 14, 14] 94,208
BatchNorm2d-214 [-1, 128, 14, 14] 256
ReLU-215 [-1, 128, 14, 14] 0
Conv2d-216 [-1, 32, 14, 14] 36,864
BatchNorm2d-217 [-1, 768, 14, 14] 1,536
ReLU-218 [-1, 768, 14, 14] 0
Conv2d-219 [-1, 128, 14, 14] 98,304
BatchNorm2d-220 [-1, 128, 14, 14] 256
ReLU-221 [-1, 128, 14, 14] 0
Conv2d-222 [-1, 32, 14, 14] 36,864
BatchNorm2d-223 [-1, 800, 14, 14] 1,600
ReLU-224 [-1, 800, 14, 14] 0
Conv2d-225 [-1, 128, 14, 14] 102,400
BatchNorm2d-226 [-1, 128, 14, 14] 256
ReLU-227 [-1, 128, 14, 14] 0
Conv2d-228 [-1, 32, 14, 14] 36,864
BatchNorm2d-229 [-1, 832, 14, 14] 1,664
ReLU-230 [-1, 832, 14, 14] 0
Conv2d-231 [-1, 128, 14, 14] 106,496
BatchNorm2d-232 [-1, 128, 14, 14] 256
ReLU-233 [-1, 128, 14, 14] 0
Conv2d-234 [-1, 32, 14, 14] 36,864
BatchNorm2d-235 [-1, 864, 14, 14] 1,728
ReLU-236 [-1, 864, 14, 14] 0
Conv2d-237 [-1, 128, 14, 14] 110,592
BatchNorm2d-238 [-1, 128, 14, 14] 256
ReLU-239 [-1, 128, 14, 14] 0
Conv2d-240 [-1, 32, 14, 14] 36,864
BatchNorm2d-241 [-1, 896, 14, 14] 1,792
ReLU-242 [-1, 896, 14, 14] 0
Conv2d-243 [-1, 128, 14, 14] 114,688
BatchNorm2d-244 [-1, 128, 14, 14] 256
ReLU-245 [-1, 128, 14, 14] 0
Conv2d-246 [-1, 32, 14, 14] 36,864
BatchNorm2d-247 [-1, 928, 14, 14] 1,856
ReLU-248 [-1, 928, 14, 14] 0
Conv2d-249 [-1, 128, 14, 14] 118,784
BatchNorm2d-250 [-1, 128, 14, 14] 256
ReLU-251 [-1, 128, 14, 14] 0
Conv2d-252 [-1, 32, 14, 14] 36,864
BatchNorm2d-253 [-1, 960, 14, 14] 1,920
ReLU-254 [-1, 960, 14, 14] 0
Conv2d-255 [-1, 128, 14, 14] 122,880
BatchNorm2d-256 [-1, 128, 14, 14] 256
ReLU-257 [-1, 128, 14, 14] 0
Conv2d-258 [-1, 32, 14, 14] 36,864
BatchNorm2d-259 [-1, 992, 14, 14] 1,984
ReLU-260 [-1, 992, 14, 14] 0
Conv2d-261 [-1, 128, 14, 14] 126,976
BatchNorm2d-262 [-1, 128, 14, 14] 256
ReLU-263 [-1, 128, 14, 14] 0
Conv2d-264 [-1, 32, 14, 14] 36,864
BatchNorm2d-265 [-1, 1024, 14, 14] 2,048
ReLU-266 [-1, 1024, 14, 14] 0
Conv2d-267 [-1, 512, 14, 14] 524,288
AvgPool2d-268 [-1, 512, 7, 7] 0
BatchNorm2d-269 [-1, 512, 7, 7] 1,024
ReLU-270 [-1, 512, 7, 7] 0
Conv2d-271 [-1, 128, 7, 7] 65,536
BatchNorm2d-272 [-1, 128, 7, 7] 256
ReLU-273 [-1, 128, 7, 7] 0
Conv2d-274 [-1, 32, 7, 7] 36,864
BatchNorm2d-275 [-1, 544, 7, 7] 1,088
ReLU-276 [-1, 544, 7, 7] 0
Conv2d-277 [-1, 128, 7, 7] 69,632
BatchNorm2d-278 [-1, 128, 7, 7] 256
ReLU-279 [-1, 128, 7, 7] 0
Conv2d-280 [-1, 32, 7, 7] 36,864
BatchNorm2d-281 [-1, 576, 7, 7] 1,152
ReLU-282 [-1, 576, 7, 7] 0
Conv2d-283 [-1, 128, 7, 7] 73,728
BatchNorm2d-284 [-1, 128, 7, 7] 256
ReLU-285 [-1, 128, 7, 7] 0
Conv2d-286 [-1, 32, 7, 7] 36,864
BatchNorm2d-287 [-1, 608, 7, 7] 1,216
ReLU-288 [-1, 608, 7, 7] 0
Conv2d-289 [-1, 128, 7, 7] 77,824
BatchNorm2d-290 [-1, 128, 7, 7] 256
ReLU-291 [-1, 128, 7, 7] 0
Conv2d-292 [-1, 32, 7, 7] 36,864
BatchNorm2d-293 [-1, 640, 7, 7] 1,280
ReLU-294 [-1, 640, 7, 7] 0
Conv2d-295 [-1, 128, 7, 7] 81,920
BatchNorm2d-296 [-1, 128, 7, 7] 256
ReLU-297 [-1, 128, 7, 7] 0
Conv2d-298 [-1, 32, 7, 7] 36,864
BatchNorm2d-299 [-1, 672, 7, 7] 1,344
ReLU-300 [-1, 672, 7, 7] 0
Conv2d-301 [-1, 128, 7, 7] 86,016
BatchNorm2d-302 [-1, 128, 7, 7] 256
ReLU-303 [-1, 128, 7, 7] 0
Conv2d-304 [-1, 32, 7, 7] 36,864
BatchNorm2d-305 [-1, 704, 7, 7] 1,408
ReLU-306 [-1, 704, 7, 7] 0
Conv2d-307 [-1, 128, 7, 7] 90,112
BatchNorm2d-308 [-1, 128, 7, 7] 256
ReLU-309 [-1, 128, 7, 7] 0
Conv2d-310 [-1, 32, 7, 7] 36,864
BatchNorm2d-311 [-1, 736, 7, 7] 1,472
ReLU-312 [-1, 736, 7, 7] 0
Conv2d-313 [-1, 128, 7, 7] 94,208
BatchNorm2d-314 [-1, 128, 7, 7] 256
ReLU-315 [-1, 128, 7, 7] 0
Conv2d-316 [-1, 32, 7, 7] 36,864
BatchNorm2d-317 [-1, 768, 7, 7] 1,536
ReLU-318 [-1, 768, 7, 7] 0
Conv2d-319 [-1, 128, 7, 7] 98,304
BatchNorm2d-320 [-1, 128, 7, 7] 256
ReLU-321 [-1, 128, 7, 7] 0
Conv2d-322 [-1, 32, 7, 7] 36,864
BatchNorm2d-323 [-1, 800, 7, 7] 1,600
ReLU-324 [-1, 800, 7, 7] 0
Conv2d-325 [-1, 128, 7, 7] 102,400
BatchNorm2d-326 [-1, 128, 7, 7] 256
ReLU-327 [-1, 128, 7, 7] 0
Conv2d-328 [-1, 32, 7, 7] 36,864
BatchNorm2d-329 [-1, 832, 7, 7] 1,664
ReLU-330 [-1, 832, 7, 7] 0
Conv2d-331 [-1, 128, 7, 7] 106,496
BatchNorm2d-332 [-1, 128, 7, 7] 256
ReLU-333 [-1, 128, 7, 7] 0
Conv2d-334 [-1, 32, 7, 7] 36,864
BatchNorm2d-335 [-1, 864, 7, 7] 1,728
ReLU-336 [-1, 864, 7, 7] 0
Conv2d-337 [-1, 128, 7, 7] 110,592
BatchNorm2d-338 [-1, 128, 7, 7] 256
ReLU-339 [-1, 128, 7, 7] 0
Conv2d-340 [-1, 32, 7, 7] 36,864
BatchNorm2d-341 [-1, 896, 7, 7] 1,792
ReLU-342 [-1, 896, 7, 7] 0
Conv2d-343 [-1, 128, 7, 7] 114,688
BatchNorm2d-344 [-1, 128, 7, 7] 256
ReLU-345 [-1, 128, 7, 7] 0
Conv2d-346 [-1, 32, 7, 7] 36,864
BatchNorm2d-347 [-1, 928, 7, 7] 1,856
ReLU-348 [-1, 928, 7, 7] 0
Conv2d-349 [-1, 128, 7, 7] 118,784
BatchNorm2d-350 [-1, 128, 7, 7] 256
ReLU-351 [-1, 128, 7, 7] 0
Conv2d-352 [-1, 32, 7, 7] 36,864
BatchNorm2d-353 [-1, 960, 7, 7] 1,920
ReLU-354 [-1, 960, 7, 7] 0
Conv2d-355 [-1, 128, 7, 7] 122,880
BatchNorm2d-356 [-1, 128, 7, 7] 256
ReLU-357 [-1, 128, 7, 7] 0
Conv2d-358 [-1, 32, 7, 7] 36,864
BatchNorm2d-359 [-1, 992, 7, 7] 1,984
ReLU-360 [-1, 992, 7, 7] 0
Conv2d-361 [-1, 128, 7, 7] 126,976
BatchNorm2d-362 [-1, 128, 7, 7] 256
ReLU-363 [-1, 128, 7, 7] 0
Conv2d-364 [-1, 32, 7, 7] 36,864
BatchNorm2d-365 [-1, 1024, 7, 7] 2,048
ReLU-366 [-1, 1024, 7, 7] 0
Linear-367 [-1, 2] 2,050
================================================================
Total params: 6,955,906
Trainable params: 6,955,906
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 294.57
Params size (MB): 26.53
Estimated Total Size (MB): 321.68
----------------------------------------------------------------
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-4 # 学习率
opt = torch.optim.SGD(model.parameters(),lr=learn_rate)
# 训练循环
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset) # 训练集的大小，一共60000张图片
num_batches = len(dataloader) # 批次数目，1875（60000/32）
train_loss, train_acc = 0, 0 # 初始化训练损失和正确率
for X, y in dataloader: # 获取图片及其标签
X, y = X.to(device), y.to(device)
# 计算预测误差
pred = model(X) # 网络输出
loss = loss_fn(pred, y) # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失
# 反向传播
optimizer.zero_grad() # grad属性归零
loss.backward() # 反向传播
optimizer.step() # 每一步自动更新
# 记录acc与loss
train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
train_loss += loss.item()
train_acc /= size
train_loss /= num_batches
return train_acc, train_loss
def test (dataloader, model, loss_fn):
size = len(dataloader.dataset) # 测试集的大小，一共10000张图片
num_batches = len(dataloader) # 批次数目，313（10000/32=312.5，向上取整）
test_loss, test_acc = 0, 0
# 当不进行训练时，停止梯度更新，节省计算内存消耗
with torch.no_grad():
for imgs, target in dataloader:
imgs, target = imgs.to(device), target.to(device)
# 计算loss
target_pred = model(imgs)
loss = loss_fn(target_pred, target)
test_loss += loss.item()
test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()
test_acc /= size
test_loss /= num_batches
return test_acc, test_loss
epochs = 20
train_loss = []
train_acc = []
test_loss = []
test_acc = []
for epoch in range(epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
train_acc.append(epoch_train_acc)
train_loss.append(epoch_train_loss)
test_acc.append(epoch_test_acc)
test_loss.append(epoch_test_loss)
template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%，Test_loss:{:.3f}')
print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')Epoch: 1, Train_acc:47.7%, Train_loss:0.725, Test_acc:47.4%，Test_loss:0.708 Epoch: 2, Train_acc:50.2%, Train_loss:0.697, Test_acc:52.7%，Test_loss:0.690 Epoch: 3, Train_acc:56.1%, Train_loss:0.686, Test_acc:59.9%，Test_loss:0.681 Epoch: 4, Train_acc:58.5%, Train_loss:0.679, Test_acc:60.7%，Test_loss:0.675 Epoch: 5, Train_acc:60.9%, Train_loss:0.673, Test_acc:60.1%，Test_loss:0.671 Epoch: 6, Train_acc:61.7%, Train_loss:0.670, Test_acc:62.6%，Test_loss:0.664 Epoch: 7, Train_acc:62.4%, Train_loss:0.665, Test_acc:63.5%，Test_loss:0.659 Epoch: 8, Train_acc:63.0%, Train_loss:0.660, Test_acc:64.8%，Test_loss:0.653 Epoch: 9, Train_acc:64.2%, Train_loss:0.656, Test_acc:65.5%，Test_loss:0.649 Epoch:10, Train_acc:64.9%, Train_loss:0.652, Test_acc:65.6%，Test_loss:0.644 Epoch:11, Train_acc:65.4%, Train_loss:0.649, Test_acc:66.6%，Test_loss:0.641 Epoch:12, Train_acc:65.0%, Train_loss:0.646, Test_acc:66.6%，Test_loss:0.638 Epoch:13, Train_acc:64.8%, Train_loss:0.643, Test_acc:67.5%，Test_loss:0.634 Epoch:14, Train_acc:65.7%, Train_loss:0.641, Test_acc:67.3%，Test_loss:0.633 Epoch:15, Train_acc:65.9%, Train_loss:0.638, Test_acc:67.8%，Test_loss:0.629 Epoch:16, Train_acc:66.3%, Train_loss:0.635, Test_acc:67.6%，Test_loss:0.626 Epoch:17, Train_acc:67.3%, Train_loss:0.632, Test_acc:67.8%，Test_loss:0.624 Epoch:18, Train_acc:67.1%, Train_loss:0.628, Test_acc:68.2%，Test_loss:0.618 Epoch:19, Train_acc:67.3%, Train_loss:0.628, Test_acc:68.9%，Test_loss:0.618 Epoch:20, Train_acc:67.9%, Train_loss:0.624, Test_acc:68.4%，Test_loss:0.614 Done
import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings("ignore") #忽略警告信息
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号
plt.rcParams['figure.dpi'] = 100 #分辨率
epochs_range = range(epochs)
plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
