🍨 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]
一、 基础配置
- 语言环境:Python3.8
- 编译器选择:Pycharm
- 数据集:参考深度学习Day-03(天气识别数据集)
- 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 torch
import torch.nn as nn
from torchvision import transforms, datasets
import warnings
warnings.filterwarnings("ignore") #忽略警告信息
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
根据个人设备情况,选择使用GPU/CPU进行训练,在Pycharm中需要添加print命令来查看是否使用了GPU ,若GPU可用则输出
cuda
该代码片段中加入了 warnings.filterwarnings("ignore")用于忽略代码运行中不必要的警告信息。
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。
*考虑到Day-08及Day-09均为YOLOv5的实现,故这里对文件夹做了一定的调整,需使用到os库中的API完成对data数据中的文件提取。
运行下述代码:
import os,pathlib
data_dir = '../data'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
class_names = [str(path).split(os.path.sep)[-1] for path in data_paths]
print(class_names)
得到如下输出:
['cloudy', 'rain', 'shine', 'sunrise']
接下来,我们通过transforms.Compose对整个数据集进行预处理:
- 第一步:将输入图片resize成统一尺寸,即[224, 224]
- 第二步:转换为tensor,并归一化到[0,1]之间
- 第三步:转换为标准正态分布(高斯分布),使模型更容易收敛
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)
得到如下输出:
Dataset ImageFolder
Number of datapoints: 1125
Root location: ../data
StandardTransform
Transform: Compose(
Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=None)
RandomHorizontalFlip(p=0.5)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)
接下来,为了方便模型进行训练和推理,映射关系可以将类别标签转换为模型可以理解的数字格式:
total_data.class_to_idx
得到如下输出:
{'cloudy': 0, 'rain': 1, 'shine': 2, 'sunrise': 3}
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])
根据代码所示,本文将原数据集按照8:2的比例进行了划分,接着根据划分得到的训练集和验证集对数据集进行包装:
batch_size = 4
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([4, 3, 224, 224])
Shape of y: torch.Size([4]) torch.int64
Tips:win需要采用num_workers=0的模式。
二、手动搭建包含C3模块的模型
1.模型搭建
def autopad(k, p=None): # kernel, padding
# Pad to 'same'
if p is None:
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
return p
class Conv(nn.Module):
# Standard convolution
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
super().__init__()
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
self.bn = nn.BatchNorm2d(c2)
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
def forward(self, x):
return self.act(self.bn(self.conv(x)))
class Bottleneck(nn.Module):
# Standard bottleneck
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_, c2, 3, 1, g=g)
self.add = shortcut and c1 == c2
def forward(self, x):
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class C3(nn.Module):
# CSP Bottleneck with 3 convolutions
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c1, c_, 1, 1)
self.cv3 = Conv(2 * c_, c2, 1) # act=FReLU(c2)
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
def forward(self, x):
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
class model_K(nn.Module):
def __init__(self):
super(model_K, self).__init__()
# 卷积模块
self.Conv = Conv(3, 32, 3, 2)
# C3模块1
self.C3_1 = C3(32, 64, 3, 2)
# 全连接网络层,用于分类
self.classifier = nn.Sequential(
nn.Linear(in_features=802816, out_features=100),
nn.ReLU(),
nn.Linear(in_features=100, out_features=4)
)
def forward(self, x):
x = self.Conv(x)
x = self.C3_1(x)
x = torch.flatten(x, start_dim=1)
x = self.classifier(x)
return x
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
model = model_K().to(device)
print(model)
可以得到如下输出:
Using cuda device
model_K(
(Conv): Conv(
(conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(C3_1): C3(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv3): Conv(
(conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(m): Sequential(
(0): Bottleneck(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
(1): Bottleneck(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
(2): Bottleneck(
(cv1): Conv(
(conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
(cv2): Conv(
(conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): SiLU()
)
)
)
)
(classifier): Sequential(
(0): Linear(in_features=802816, out_features=100, bias=True)
(1): ReLU()
(2): Linear(in_features=100, out_features=4, bias=True)
)
)
2.查看模型信息
# 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, 32, 112, 112] 864
BatchNorm2d-2 [-1, 32, 112, 112] 64
SiLU-3 [-1, 32, 112, 112] 0
Conv-4 [-1, 32, 112, 112] 0
Conv2d-5 [-1, 32, 112, 112] 1,024
BatchNorm2d-6 [-1, 32, 112, 112] 64
SiLU-7 [-1, 32, 112, 112] 0
Conv-8 [-1, 32, 112, 112] 0
Conv2d-9 [-1, 32, 112, 112] 1,024
BatchNorm2d-10 [-1, 32, 112, 112] 64
SiLU-11 [-1, 32, 112, 112] 0
Conv-12 [-1, 32, 112, 112] 0
Conv2d-13 [-1, 32, 112, 112] 9,216
BatchNorm2d-14 [-1, 32, 112, 112] 64
SiLU-15 [-1, 32, 112, 112] 0
Conv-16 [-1, 32, 112, 112] 0
Bottleneck-17 [-1, 32, 112, 112] 0
Conv2d-18 [-1, 32, 112, 112] 1,024
BatchNorm2d-19 [-1, 32, 112, 112] 64
SiLU-20 [-1, 32, 112, 112] 0
Conv-21 [-1, 32, 112, 112] 0
Conv2d-22 [-1, 32, 112, 112] 9,216
BatchNorm2d-23 [-1, 32, 112, 112] 64
SiLU-24 [-1, 32, 112, 112] 0
Conv-25 [-1, 32, 112, 112] 0
Bottleneck-26 [-1, 32, 112, 112] 0
Conv2d-27 [-1, 32, 112, 112] 1,024
BatchNorm2d-28 [-1, 32, 112, 112] 64
SiLU-29 [-1, 32, 112, 112] 0
Conv-30 [-1, 32, 112, 112] 0
Conv2d-31 [-1, 32, 112, 112] 9,216
BatchNorm2d-32 [-1, 32, 112, 112] 64
SiLU-33 [-1, 32, 112, 112] 0
Conv-34 [-1, 32, 112, 112] 0
Bottleneck-35 [-1, 32, 112, 112] 0
Conv2d-36 [-1, 32, 112, 112] 1,024
BatchNorm2d-37 [-1, 32, 112, 112] 64
SiLU-38 [-1, 32, 112, 112] 0
Conv-39 [-1, 32, 112, 112] 0
Conv2d-40 [-1, 64, 112, 112] 4,096
BatchNorm2d-41 [-1, 64, 112, 112] 128
SiLU-42 [-1, 64, 112, 112] 0
Conv-43 [-1, 64, 112, 112] 0
C3-44 [-1, 64, 112, 112] 0
Linear-45 [-1, 100] 80,281,700
ReLU-46 [-1, 100] 0
Linear-47 [-1, 4] 404
================================================================
Total params: 80,320,536
Trainable params: 80,320,536
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 150.06
Params size (MB): 306.40
Estimated Total Size (MB): 457.04
----------------------------------------------------------------
参数量为:80,320,536
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_loss
2. 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, (size/batch_size,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
3.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 = 20
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):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
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:68.8%, Train_loss:1.591, Test_acc:83.6%, Test_loss:0.419, Lr:1.00E-04
Epoch: 2, Train_acc:80.0%, Train_loss:0.581, Test_acc:86.2%, Test_loss:0.386, Lr:1.00E-04
Epoch: 3, Train_acc:87.8%, Train_loss:0.318, Test_acc:87.1%, Test_loss:0.390, Lr:1.00E-04
Epoch: 4, Train_acc:92.3%, Train_loss:0.267, Test_acc:90.2%, Test_loss:0.324, Lr:1.00E-04
Epoch: 5, Train_acc:93.1%, Train_loss:0.225, Test_acc:89.3%, Test_loss:0.309, Lr:1.00E-04
Epoch: 6, Train_acc:94.1%, Train_loss:0.198, Test_acc:90.2%, Test_loss:0.319, Lr:1.00E-04
Epoch: 7, Train_acc:95.4%, Train_loss:0.140, Test_acc:90.7%, Test_loss:0.321, Lr:1.00E-04
Epoch: 8, Train_acc:97.2%, Train_loss:0.080, Test_acc:89.8%, Test_loss:0.283, Lr:1.00E-04
Epoch: 9, Train_acc:98.3%, Train_loss:0.051, Test_acc:89.3%, Test_loss:0.317, Lr:1.00E-04
Epoch:10, Train_acc:98.6%, Train_loss:0.052, Test_acc:89.3%, Test_loss:0.318, Lr:1.00E-04
Epoch:11, Train_acc:98.0%, Train_loss:0.055, Test_acc:90.2%, Test_loss:0.408, Lr:1.00E-04
Epoch:12, Train_acc:98.8%, Train_loss:0.034, Test_acc:92.0%, Test_loss:0.348, Lr:1.00E-04
Epoch:13, Train_acc:99.0%, Train_loss:0.042, Test_acc:89.3%, Test_loss:0.252, Lr:1.00E-04
Epoch:14, Train_acc:97.8%, Train_loss:0.075, Test_acc:88.0%, Test_loss:0.523, Lr:1.00E-04
Epoch:15, Train_acc:97.8%, Train_loss:0.066, Test_acc:90.2%, Test_loss:0.499, Lr:1.00E-04
Epoch:16, Train_acc:98.4%, Train_loss:0.072, Test_acc:90.7%, Test_loss:0.496, Lr:1.00E-04
Epoch:17, Train_acc:97.8%, Train_loss:0.079, Test_acc:90.2%, Test_loss:0.382, Lr:1.00E-04
Epoch:18, Train_acc:99.1%, Train_loss:0.021, Test_acc:89.8%, Test_loss:0.366, Lr:1.00E-04
Epoch:19, Train_acc:99.8%, Train_loss:0.008, Test_acc:92.0%, Test_loss:0.321, Lr:1.00E-04
Epoch:20, Train_acc:98.8%, Train_loss:0.042, Test_acc:91.1%, Test_loss:0.389, 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()
得到可视化的结果为:
2. 模型评估
将模型调至评估模式:
best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)
print(epoch_test_acc, epoch_test_loss,epoch_test_acc)
得到如下输出:
0.9066666666666666 0.29367532026190657 0.9066666666666666
观察得到和前文中一致。
五、个人理解
本项目要求为实现YOLOv5-C3模块的搭建过程,现在根据原文中搭建模型的代码及问题进行对应的解释说明:
1.回答问题
Q:是否可以尝试通过增加/调整C3模块与Conv模块来提高准确率?
A:首先,调整C3模块和Conv模块是一种常见提高准确率的方法,通过调整Conv模块的参数、卷积核大小等,可以使网络更好地捕捉输入数据的特征;然而,需要注意的是,调整模型结构并不总是能够带来准确率的显著提升。在进行调整时,需要进行充分的实验和评估,以确保调整后的模型在验证集或测试集上获得更好的性能。
2.代码说明
def autopad(k, p=None):
if p is None:
p = k // 2 if isinstance(k, int) else [x // 2 for x in k]
return p
定义了一个名为autopad的函数,用于自动计算卷积操作的padding参数,使得输入和输出的尺寸相同。其中,k代表卷积核的大小,p表示padding的大小,如果没有给出p参数,则自动计算k的一半作为p。
class Conv(nn.Module):
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):
super().__init__()
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
self.bn = nn.BatchNorm2d(c2)
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
def forward(self, x):
return self.act(self.bn(self.conv(x)))
定义了一个名为Conv的类,用于构建卷积层。在初始化方法中,参数c1表示输入通道数,c2表示输出通道数,k表示卷积核大小,s表示步长大小,p表示 padding大小,g表示分组卷积的组数,act表示是否使用激活函数。在forward方法中,先执行卷积操作、BatchNorm,最后再使用激活函数。
class Bottleneck(nn.Module):
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):
super().__init__()
c_ = int(c2 * e)
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_, c2, 3, 1, g=g)
self.add = shortcut and c1 == c2
def forward(self, x):
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
定义了一个名为Bottleneck的类,用于构建标准的瓶颈块。在初始化方法中,参数c1表示输入通道数,c2表示输出通道数,shortcut表示是否使用跳跃连接,g表示分组卷积的组数,e表示瓶颈块中间层的扩张因子。在forward方法中,先执行两次卷积运算,然后进行跳跃连接或者直接返回结果。
class C3(nn.Module):
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
super().__init__()
c_ = int(c2 * e)
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c1, c_, 1, 1)
self.cv3 = Conv(2 * c_, c2, 1)
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
def forward(self, x):
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
定义了一个名为C3的类,用于构建Bottleneck模块。在初始化方法中,参数c1表示输入通道数,c2表示输出通道数,n表示模块中使用的瓶颈块数量,shortcut表示是否使用跳跃连接,g表示分组卷积的组数,e表示瓶颈块中间层的扩张因子。在forward方法中,先执行卷积操作,然后进行两次不同的卷积运算,最后使用跳跃连接。
class model_K(nn.Module):
def __init__(self):
super(model_K, self).__init__()
self.Conv = Conv(3, 32, 3, 2)
self.C3_1 = C3(32, 64, 3, 2)
self.classifier = nn.Sequential(
nn.Linear(in_features=802816, out_features=100),
nn.ReLU(),
nn.Linear(in_features=100, out_features=4)
)
def forward(self, x):
x = self.Conv(x)
x = self.C3_1(x)
x = torch.flatten(x, start_dim=1)
x = self.classifier(x)
return x
定义了一个名为model_K的类,用于构建整个模型。在初始化方法中,分别创建了卷积层、C3模块和全连接层,并在forward方法中按照顺序执行。将输入数据传入卷积层得到卷积结果,然后再将其传入C3模块得到特征提取结果,最后通过flatten操作将特征结果变成一维向量,传入全连接层进行分类。