🍨 本文为：[🔗365天深度学习训练营] 中的学习记录博客
🍖 原作者：[K同学啊 | 接辅导、项目定制]
要求：
- 了解并学习图2中的卷积层运算量的计算过程（🏐储备知识->卷积层运算量的计算，有我的推导过程，建议先自己手动推导，然后再看）
- 了解并学习卷积层的并行结构与1x1卷积核部分内容（重点
- 尝试根据模型框架图写入相应的pytorch代码，并使用Inception v1完成猴痘病识别
一、 基础配置
- 语言环境：Python3.8
- 编译器选择：Pycharm
- 深度学习环境：
-
- torch==1.12.1+cu113
- torchvision==0.13.1+cu113
二、 前期准备
1.设置GPU
import pathlib
import torch
import torch.nn as nn
import torch.nn.functional as F
from torchvision import transforms, datasets
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)2. 导入数据
本项目所采用的数据集未收录于公开数据中，故需要自己在文件目录中导入相应数据集合，并设置对应文件目录，以供后续学习过程中使用。
运行下述代码：
data_dir = './data/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
print(classeNames)
image_count = len(list(data_dir.glob('*/*')))
print("图片总数为：", image_count)得到如下输出：
['Monkeypox', 'Others']
图片总数为： 2142接下来，我们通过transforms.Compose对整个数据集进行预处理：
train_transforms = transforms.Compose([
transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
# transforms.RandomHorizontalFlip(), # 随机水平翻转
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。
])
test_transform = 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("./data/", transform=train_transforms)
print(total_data.class_to_idx)得到如下输出：
{'Monkeypox': 0, 'Others': 1}3. 划分数据集
此处数据集需要做按比例划分的操作：
train_size = int(0.8 * 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])
接下来，根据划分得到的训练集和验证集对数据集进行包装：
batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0)并通过：
for X, y in test_dl:
print("Shape of X [N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape, y.dtype)
break
输出测试数据集的数据分布情况：
Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y: torch.Size([32]) torch.int644.搭建模型
1.模型搭建
class inception_block(nn.Module):
def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
super().__init__()
# 1x1 conv branch
self.branch1 = nn.Sequential(
nn.Conv2d(in_channels, ch1x1, kernel_size=1),
nn.BatchNorm2d(ch1x1),
nn.ReLU(inplace=True)
)
# 1x1 conv -> 3x3 conv branch
self.branch2 = nn.Sequential(
nn.Conv2d(in_channels, ch3x3red, kernel_size=1),
nn.BatchNorm2d(ch3x3red),
nn.ReLU(inplace=True),
nn.Conv2d(ch3x3red, ch3x3, kernel_size=3, padding=1),
nn.BatchNorm2d(ch3x3),
nn.ReLU(inplace=True)
)
# 1x1 conv -> 5x5 conv branch
self.branch3 = nn.Sequential(
nn.Conv2d(in_channels, ch5x5red, kernel_size=1),
nn.BatchNorm2d(ch5x5red),
nn.ReLU(inplace=True),
nn.Conv2d(ch5x5red, ch5x5, kernel_size=3, padding=1),
nn.BatchNorm2d(ch5x5),
nn.ReLU(inplace=True)
)
self.branch4 = nn.Sequential(
nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
nn.Conv2d(in_channels, pool_proj, kernel_size=1),
nn.BatchNorm2d(pool_proj),
nn.ReLU(inplace=True)
)
def forward(self, x):
branch1_output = self.branch1(x)
branch2_output = self.branch2(x)
branch3_output = self.branch3(x)
branch4_output = self.branch4(x)
outputs = [branch1_output, branch2_output, branch3_output, branch4_output]
return torch.cat(outputs, 1)
class InceptionV1(nn.Module):
def __init__(self, num_classes=1000):
super(InceptionV1, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
self.maxpool1 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.conv2 = nn.Conv2d(64, 64, kernel_size=1, stride=1, padding=1)
self.conv3 = nn.Conv2d(64, 192, kernel_size=3, stride=1, padding=1)
self.maxpool2 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.inception3a = inception_block(192, 64, 96, 128, 16, 32, 32)
self.inception3b = inception_block(256, 128, 128, 192, 32, 96, 64)
self.maxpool3 = nn.MaxPool2d(3, stride=2)
self.inception4a = inception_block(480, 192, 96, 208, 16, 48, 64)
self.inception4b = inception_block(512, 160, 112, 224, 24, 64, 64)
self.inception4c = inception_block(512, 128, 128, 256, 24, 64, 64)
self.inception4d = inception_block(512, 112, 144, 288, 32, 64, 64)
self.inception4e = inception_block(528, 256, 160, 320, 32, 128, 128)
self.maxpool4 = nn.MaxPool2d(2, stride=2)
self.inception5a = inception_block(832, 256, 160, 320, 32, 128, 128)
self.inception5b = nn.Sequential(
inception_block(832, 384, 192, 384, 48, 128, 128),
nn.AvgPool2d(kernel_size=7, stride=1, padding=0),
nn.Dropout(0.4)
)
# 全连接网络层，用于分类
self.classifier = nn.Sequential(
nn.Linear(in_features=1024, out_features=1024),
nn.ReLU(),
nn.Linear(in_features=1024, out_features=num_classes),
nn.Softmax(dim=1)
)
def forward(self, x):
x = self.conv1(x)
x = F.relu(x)
x = self.maxpool1(x)
x = self.conv2(x)
x = F.relu(x)
x = self.conv3(x)
x = F.relu(x)
x = self.maxpool2(x)
x = self.inception3a(x)
x = self.inception3b(x)
x = self.maxpool3(x)
x = self.inception4a(x)
x = self.inception4b(x)
x = self.inception4c(x)
x = self.inception4d(x)
x = self.inception4e(x)
x = self.maxpool4(x)
x = self.inception5a(x)
x = self.inception5b(x)
x = torch.flatten(x, start_dim=1)
x = self.classifier(x)
return x;2.查看模型信息
model = InceptionV1(4)
model.to(device)
# 统计模型参数量以及其他指标
import torchsummary as summary
summary.summary(model, (3, 224, 224))得到如下输出：
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 64, 112, 112] 9,472
MaxPool2d-2 [-1, 64, 56, 56] 0
Conv2d-3 [-1, 64, 58, 58] 4,160
Conv2d-4 [-1, 192, 58, 58] 110,784
MaxPool2d-5 [-1, 192, 29, 29] 0
Conv2d-6 [-1, 64, 29, 29] 12,352
BatchNorm2d-7 [-1, 64, 29, 29] 128
ReLU-8 [-1, 64, 29, 29] 0
Conv2d-9 [-1, 96, 29, 29] 18,528
BatchNorm2d-10 [-1, 96, 29, 29] 192
ReLU-11 [-1, 96, 29, 29] 0
Conv2d-12 [-1, 128, 29, 29] 110,720
BatchNorm2d-13 [-1, 128, 29, 29] 256
ReLU-14 [-1, 128, 29, 29] 0
Conv2d-15 [-1, 16, 29, 29] 3,088
BatchNorm2d-16 [-1, 16, 29, 29] 32
ReLU-17 [-1, 16, 29, 29] 0
Conv2d-18 [-1, 32, 29, 29] 4,640
BatchNorm2d-19 [-1, 32, 29, 29] 64
ReLU-20 [-1, 32, 29, 29] 0
MaxPool2d-21 [-1, 192, 29, 29] 0
Conv2d-22 [-1, 32, 29, 29] 6,176
BatchNorm2d-23 [-1, 32, 29, 29] 64
ReLU-24 [-1, 32, 29, 29] 0
inception_block-25 [-1, 256, 29, 29] 0
Conv2d-26 [-1, 128, 29, 29] 32,896
BatchNorm2d-27 [-1, 128, 29, 29] 256
ReLU-28 [-1, 128, 29, 29] 0
Conv2d-29 [-1, 128, 29, 29] 32,896
BatchNorm2d-30 [-1, 128, 29, 29] 256
ReLU-31 [-1, 128, 29, 29] 0
Conv2d-32 [-1, 192, 29, 29] 221,376
BatchNorm2d-33 [-1, 192, 29, 29] 384
ReLU-34 [-1, 192, 29, 29] 0
Conv2d-35 [-1, 32, 29, 29] 8,224
BatchNorm2d-36 [-1, 32, 29, 29] 64
ReLU-37 [-1, 32, 29, 29] 0
Conv2d-38 [-1, 96, 29, 29] 27,744
BatchNorm2d-39 [-1, 96, 29, 29] 192
ReLU-40 [-1, 96, 29, 29] 0
MaxPool2d-41 [-1, 256, 29, 29] 0
Conv2d-42 [-1, 64, 29, 29] 16,448
BatchNorm2d-43 [-1, 64, 29, 29] 128
ReLU-44 [-1, 64, 29, 29] 0
inception_block-45 [-1, 480, 29, 29] 0
MaxPool2d-46 [-1, 480, 14, 14] 0
Conv2d-47 [-1, 192, 14, 14] 92,352
BatchNorm2d-48 [-1, 192, 14, 14] 384
ReLU-49 [-1, 192, 14, 14] 0
Conv2d-50 [-1, 96, 14, 14] 46,176
BatchNorm2d-51 [-1, 96, 14, 14] 192
ReLU-52 [-1, 96, 14, 14] 0
Conv2d-53 [-1, 208, 14, 14] 179,920
BatchNorm2d-54 [-1, 208, 14, 14] 416
ReLU-55 [-1, 208, 14, 14] 0
Conv2d-56 [-1, 16, 14, 14] 7,696
BatchNorm2d-57 [-1, 16, 14, 14] 32
ReLU-58 [-1, 16, 14, 14] 0
Conv2d-59 [-1, 48, 14, 14] 6,960
BatchNorm2d-60 [-1, 48, 14, 14] 96
ReLU-61 [-1, 48, 14, 14] 0
MaxPool2d-62 [-1, 480, 14, 14] 0
Conv2d-63 [-1, 64, 14, 14] 30,784
BatchNorm2d-64 [-1, 64, 14, 14] 128
ReLU-65 [-1, 64, 14, 14] 0
inception_block-66 [-1, 512, 14, 14] 0
Conv2d-67 [-1, 160, 14, 14] 82,080
BatchNorm2d-68 [-1, 160, 14, 14] 320
ReLU-69 [-1, 160, 14, 14] 0
Conv2d-70 [-1, 112, 14, 14] 57,456
BatchNorm2d-71 [-1, 112, 14, 14] 224
ReLU-72 [-1, 112, 14, 14] 0
Conv2d-73 [-1, 224, 14, 14] 226,016
BatchNorm2d-74 [-1, 224, 14, 14] 448
ReLU-75 [-1, 224, 14, 14] 0
Conv2d-76 [-1, 24, 14, 14] 12,312
BatchNorm2d-77 [-1, 24, 14, 14] 48
ReLU-78 [-1, 24, 14, 14] 0
Conv2d-79 [-1, 64, 14, 14] 13,888
BatchNorm2d-80 [-1, 64, 14, 14] 128
ReLU-81 [-1, 64, 14, 14] 0
MaxPool2d-82 [-1, 512, 14, 14] 0
Conv2d-83 [-1, 64, 14, 14] 32,832
BatchNorm2d-84 [-1, 64, 14, 14] 128
ReLU-85 [-1, 64, 14, 14] 0
inception_block-86 [-1, 512, 14, 14] 0
Conv2d-87 [-1, 128, 14, 14] 65,664
BatchNorm2d-88 [-1, 128, 14, 14] 256
ReLU-89 [-1, 128, 14, 14] 0
Conv2d-90 [-1, 128, 14, 14] 65,664
BatchNorm2d-91 [-1, 128, 14, 14] 256
ReLU-92 [-1, 128, 14, 14] 0
Conv2d-93 [-1, 256, 14, 14] 295,168
BatchNorm2d-94 [-1, 256, 14, 14] 512
ReLU-95 [-1, 256, 14, 14] 0
Conv2d-96 [-1, 24, 14, 14] 12,312
BatchNorm2d-97 [-1, 24, 14, 14] 48
ReLU-98 [-1, 24, 14, 14] 0
Conv2d-99 [-1, 64, 14, 14] 13,888
BatchNorm2d-100 [-1, 64, 14, 14] 128
ReLU-101 [-1, 64, 14, 14] 0
MaxPool2d-102 [-1, 512, 14, 14] 0
Conv2d-103 [-1, 64, 14, 14] 32,832
BatchNorm2d-104 [-1, 64, 14, 14] 128
ReLU-105 [-1, 64, 14, 14] 0
inception_block-106 [-1, 512, 14, 14] 0
Conv2d-107 [-1, 112, 14, 14] 57,456
BatchNorm2d-108 [-1, 112, 14, 14] 224
ReLU-109 [-1, 112, 14, 14] 0
Conv2d-110 [-1, 144, 14, 14] 73,872
BatchNorm2d-111 [-1, 144, 14, 14] 288
ReLU-112 [-1, 144, 14, 14] 0
Conv2d-113 [-1, 288, 14, 14] 373,536
BatchNorm2d-114 [-1, 288, 14, 14] 576
ReLU-115 [-1, 288, 14, 14] 0
Conv2d-116 [-1, 32, 14, 14] 16,416
BatchNorm2d-117 [-1, 32, 14, 14] 64
ReLU-118 [-1, 32, 14, 14] 0
Conv2d-119 [-1, 64, 14, 14] 18,496
BatchNorm2d-120 [-1, 64, 14, 14] 128
ReLU-121 [-1, 64, 14, 14] 0
MaxPool2d-122 [-1, 512, 14, 14] 0
Conv2d-123 [-1, 64, 14, 14] 32,832
BatchNorm2d-124 [-1, 64, 14, 14] 128
ReLU-125 [-1, 64, 14, 14] 0
inception_block-126 [-1, 528, 14, 14] 0
Conv2d-127 [-1, 256, 14, 14] 135,424
BatchNorm2d-128 [-1, 256, 14, 14] 512
ReLU-129 [-1, 256, 14, 14] 0
Conv2d-130 [-1, 160, 14, 14] 84,640
BatchNorm2d-131 [-1, 160, 14, 14] 320
ReLU-132 [-1, 160, 14, 14] 0
Conv2d-133 [-1, 320, 14, 14] 461,120
BatchNorm2d-134 [-1, 320, 14, 14] 640
ReLU-135 [-1, 320, 14, 14] 0
Conv2d-136 [-1, 32, 14, 14] 16,928
BatchNorm2d-137 [-1, 32, 14, 14] 64
ReLU-138 [-1, 32, 14, 14] 0
Conv2d-139 [-1, 128, 14, 14] 36,992
BatchNorm2d-140 [-1, 128, 14, 14] 256
ReLU-141 [-1, 128, 14, 14] 0
MaxPool2d-142 [-1, 528, 14, 14] 0
Conv2d-143 [-1, 128, 14, 14] 67,712
BatchNorm2d-144 [-1, 128, 14, 14] 256
ReLU-145 [-1, 128, 14, 14] 0
inception_block-146 [-1, 832, 14, 14] 0
MaxPool2d-147 [-1, 832, 7, 7] 0
Conv2d-148 [-1, 256, 7, 7] 213,248
BatchNorm2d-149 [-1, 256, 7, 7] 512
ReLU-150 [-1, 256, 7, 7] 0
Conv2d-151 [-1, 160, 7, 7] 133,280
BatchNorm2d-152 [-1, 160, 7, 7] 320
ReLU-153 [-1, 160, 7, 7] 0
Conv2d-154 [-1, 320, 7, 7] 461,120
BatchNorm2d-155 [-1, 320, 7, 7] 640
ReLU-156 [-1, 320, 7, 7] 0
Conv2d-157 [-1, 32, 7, 7] 26,656
BatchNorm2d-158 [-1, 32, 7, 7] 64
ReLU-159 [-1, 32, 7, 7] 0
Conv2d-160 [-1, 128, 7, 7] 36,992
BatchNorm2d-161 [-1, 128, 7, 7] 256
ReLU-162 [-1, 128, 7, 7] 0
MaxPool2d-163 [-1, 832, 7, 7] 0
Conv2d-164 [-1, 128, 7, 7] 106,624
BatchNorm2d-165 [-1, 128, 7, 7] 256
ReLU-166 [-1, 128, 7, 7] 0
inception_block-167 [-1, 832, 7, 7] 0
Conv2d-168 [-1, 384, 7, 7] 319,872
BatchNorm2d-169 [-1, 384, 7, 7] 768
ReLU-170 [-1, 384, 7, 7] 0
Conv2d-171 [-1, 192, 7, 7] 159,936
BatchNorm2d-172 [-1, 192, 7, 7] 384
ReLU-173 [-1, 192, 7, 7] 0
Conv2d-174 [-1, 384, 7, 7] 663,936
BatchNorm2d-175 [-1, 384, 7, 7] 768
ReLU-176 [-1, 384, 7, 7] 0
Conv2d-177 [-1, 48, 7, 7] 39,984
BatchNorm2d-178 [-1, 48, 7, 7] 96
ReLU-179 [-1, 48, 7, 7] 0
Conv2d-180 [-1, 128, 7, 7] 55,424
BatchNorm2d-181 [-1, 128, 7, 7] 256
ReLU-182 [-1, 128, 7, 7] 0
MaxPool2d-183 [-1, 832, 7, 7] 0
Conv2d-184 [-1, 128, 7, 7] 106,624
BatchNorm2d-185 [-1, 128, 7, 7] 256
ReLU-186 [-1, 128, 7, 7] 0
inception_block-187 [-1, 1024, 7, 7] 0
AvgPool2d-188 [-1, 1024, 1, 1] 0
Dropout-189 [-1, 1024, 1, 1] 0
Linear-190 [-1, 1024] 1,049,600
ReLU-191 [-1, 1024] 0
Linear-192 [-1, 4] 4,100
Softmax-193 [-1, 4] 0
================================================================
Total params: 6,660,244
Trainable params: 6,660,244
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 71.97
Params size (MB): 25.41
Estimated Total Size (MB): 97.95
----------------------------------------------------------------三、 训练模型
1. 编写训练函数
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset) # 训练集的大小
num_batches = len(dataloader) # 批次数目, (size/batch_size，向上取整)
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_loss2. 编写测试函数
测试函数和训练函数大致相同，但是由于不进行梯度下降对网络权重进行更新，所以不需要传入优化器
def test(dataloader, model, loss_fn):
size = len(dataloader.dataset) # 测试集的大小
num_batches = len(dataloader) # 批次数目
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_loss3.正式训练
import copy
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
epochs = 10
train_loss = []
train_acc = []
test_loss = []
test_acc = []
best_acc = 0 # 设置一个最佳准确率，作为最佳模型的判别指标
for epoch in range(epochs):
# 更新学习率（使用自定义学习率时使用）
# adjust_learning_rate(optimizer, epoch, learn_rate)
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
# scheduler.step() # 更新学习率（调用官方动态学习率接口时使用）
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
# 保存最佳模型到 best_model
if epoch_test_acc > best_acc:
best_acc = epoch_test_acc
best_model = copy.deepcopy(model)
train_acc.append(epoch_train_acc)
train_loss.append(epoch_train_loss)
test_acc.append(epoch_test_acc)
test_loss.append(epoch_test_loss)
# 获取当前的学习率
lr = optimizer.state_dict()['param_groups'][0]['lr']
template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')
print(template.format(epoch + 1, epoch_train_acc * 100, epoch_train_loss,
epoch_test_acc * 100, epoch_test_loss, lr))
# 保存最佳模型到文件中
PATH = './best_model.pth' # 保存的参数文件名
torch.save(model.state_dict(), PATH)
print('Done')得到如下输出：
Epoch: 1, Train_acc:63.6%, Train_loss:1.117, Test_acc:64.6%, Test_loss:1.101, Lr:1.00E-04
Epoch: 2, Train_acc:67.8%, Train_loss:1.053, Test_acc:70.2%, Test_loss:1.046, Lr:1.00E-04
Epoch: 3, Train_acc:74.7%, Train_loss:0.998, Test_acc:69.7%, Test_loss:1.042, Lr:1.00E-04
Epoch: 4, Train_acc:72.6%, Train_loss:1.015, Test_acc:69.9%, Test_loss:1.046, Lr:1.00E-04
Epoch: 5, Train_acc:74.7%, Train_loss:0.986, Test_acc:75.3%, Test_loss:0.990, Lr:1.00E-04
Epoch: 6, Train_acc:79.5%, Train_loss:0.949, Test_acc:75.3%, Test_loss:0.988, Lr:1.00E-04
Epoch: 7, Train_acc:80.3%, Train_loss:0.938, Test_acc:83.0%, Test_loss:0.907, Lr:1.00E-04
Epoch: 8, Train_acc:85.2%, Train_loss:0.889, Test_acc:83.2%, Test_loss:0.915, Lr:1.00E-04
Epoch: 9, Train_acc:85.8%, Train_loss:0.884, Test_acc:85.8%, Test_loss:0.887, Lr:1.00E-04
Epoch:10, Train_acc:87.9%, Train_loss:0.861, Test_acc:88.6%, Test_loss:0.859, Lr:1.00E-04
Done四、 结果可视化
1. Loss&Accuracy
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()得到的可视化结果：
2. 指定图片进行预测
首先，先定义出一个用于预测的函数：
from PIL import Image
classes = list(total_data.class_to_idx)
def predict_one_image(image_path, model, transform, classes):
test_img = Image.open(image_path).convert('RGB')
plt.imshow(test_img) # 展示预测的图片
test_img = transform(test_img)
img = test_img.to(device).unsqueeze(0)
model.eval()
output = model(img)
_, pred = torch.max(output, 1)
pred_class = classes[pred]
print(f'预测结果是：{pred_class}')接着调用函数对指定图片进行预测：
# 预测训练集中的某张照片
predict_one_image(image_path='./data/Others/NM01_01_01.jpg',
model=model,
transform=train_transforms,
classes=classes)
得到如下结果：
预测结果是：Others五、网络介绍
1.简介
Inception v1是一种深度卷积神经网络，该网络的最大特点是使用了Inception模块，该模块通过多种不同的卷积核来提取不同大小的特征图，并将这些特征图拼接在一起，从而同时考虑了不同尺度下的特征信息，提高了网络的准确性和泛化能力。
在Inception v1中，Inception模块一般由1x1、3x3和5x5的卷积层以及一个最大池化层组成，同时还会在最后加上一个1x1的卷积层来减少通道数，从而避免参数过多的问题。
2.结构
另外增加了两个辅助分支，作用有两点，一是为了避免梯度消失，用于向前传导梯度。反向传播时如果有一层求导为0，链式求导结果则为0。二是将中间某一层输出用作分类，起到模型融合作用，实际测试时，这两个辅助softmax分支会被去掉，在后续模型的发展中，该方法被采用较少，可以直接绕过，重点学习卷积层的并行结构与1x1卷积核部分的内容即可。
用PyTorch复现Inception v1，可以首先定义Inception模块，包括四个分支，每个分支使用不同的卷积核进行卷积操作。然后，将四个分支的输出在深度维度上拼接起来得到最终输出。可以使用PyTorch中的nn.Module来实现Inception模块。接下来，将多个Inception模块按照一定的顺序进行组合，形成完整的Inception v1网络结构。可以使用PyTorch中的nn.Sequential或nn.ModuleList来实现网络的组合。最后，通过反向传播优化网络参数，以达到训练的目的。
