- 🍨 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
""" python =3.12.4 编译器：jupyter notebook 深度学习环境： pytorch == 2.5.1 pytorchvision == 0.20.1 显卡: NVIDIA GeForce RTX3050 laptop 数据：提供数据 """
import torch
import torchvision
import torch.nn as nn
import torchvision.transforms as transforms
from torchvision import transforms,datasets
import warnings,random,PIL,os,pathlib
warnings.filterwarnings("ignore")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device
device(type='cpu')
data_dir = './8-data/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classNames = [str(path).split("\\")[1] for path in data_paths]
classNames
['cloudy', 'rain', 'shine', 'sunrise']
train_transforms = transforms.Compose([
transforms.Resize([224,224]),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(
mean=[0.485,0.456,0.406],
std =[0.229,0.224,0.225]
)
])
test_transforms = transforms.Compose([
transforms.Resize([224,224]),
transforms.ToTensor(),
transforms.Normalize(
mean=[0.485,0.456,0.406],
std =[0.229,0.224,0.225]
)
])
total_data = datasets.ImageFolder("./8-data/",transform=train_transforms)
total_data
Dataset ImageFolder
Number of datapoints: 1125
Root location: ./8-data/
StandardTransform
Transform: Compose(
Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=True)
RandomHorizontalFlip(p=0.5)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)
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])
train_dataset,test_dataset
(<torch.utils.data.dataset.Subset at 0x1f3448383b0>,
<torch.utils.data.dataset.Subset at 0x1f3448390d0>)
batch_size = 4
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 train_dl:
print("Shape of X [N,C,H,W]:",X.shape)
print("Shape of y:",y.shape,y.dtype)
break
Shape of X [N,C,H,W]: torch.Size([4, 3, 224, 224])
Shape of y: torch.Size([4]) torch.int64
import torch.nn.functional as F
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
model = model_K().to(device)
model
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)
)
)
import torchsummary as summary
summary.summary(model,(3,224,224))
----------------------------------------------------------------
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
----------------------------------------------------------------
def train(dataloader,model,loss_fn,optimizer):
size = len(dataloader.dataset)
num_batches = len(dataloader)
train_loss, train_acc = 0,0
for X,y in dataloader:
X,y = X.to(device),y.to(device)
pred = model(X)
loss = loss_fn(pred,y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
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)
num_batches = len(dataloader)
test_loss,test_acc = 0,0
with torch.no_grad():
for imgs,target in dataloader:
imgs,target = imgs.to(device),target.to(device)
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
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(best_model.state_dict(), PATH)
print('Done')
Epoch: 1, Train_acc:73.8%, Train_loss:1.259, Test_acc:84.4%, Test_loss:0.755, Lr:1.00E-04
Epoch: 2, Train_acc:84.4%, Train_loss:0.445, Test_acc:92.0%, Test_loss:0.384, Lr:1.00E-04
Epoch: 3, Train_acc:88.8%, Train_loss:0.327, Test_acc:89.8%, Test_loss:0.616, Lr:1.00E-04
Epoch: 4, Train_acc:93.4%, Train_loss:0.174, Test_acc:89.3%, Test_loss:0.621, Lr:1.00E-04
Epoch: 5, Train_acc:93.1%, Train_loss:0.231, Test_acc:88.4%, Test_loss:0.659, Lr:1.00E-04
Epoch: 6, Train_acc:93.3%, Train_loss:0.189, Test_acc:86.7%, Test_loss:0.791, Lr:1.00E-04
Epoch: 7, Train_acc:95.0%, Train_loss:0.150, Test_acc:91.1%, Test_loss:0.569, Lr:1.00E-04
Epoch: 8, Train_acc:97.8%, Train_loss:0.062, Test_acc:90.2%, Test_loss:0.614, Lr:1.00E-04
Epoch: 9, Train_acc:99.0%, Train_loss:0.040, Test_acc:90.2%, Test_loss:0.603, Lr:1.00E-04
Epoch:10, Train_acc:98.8%, Train_loss:0.045, Test_acc:90.2%, Test_loss:0.629, Lr:1.00E-04
Epoch:11, Train_acc:96.8%, Train_loss:0.112, Test_acc:88.0%, Test_loss:0.786, Lr:1.00E-04
Epoch:12, Train_acc:98.1%, Train_loss:0.052, Test_acc:88.4%, Test_loss:0.794, Lr:1.00E-04
Epoch:13, Train_acc:97.0%, Train_loss:0.114, Test_acc:88.4%, Test_loss:0.659, Lr:1.00E-04
Epoch:14, Train_acc:97.1%, Train_loss:0.093, Test_acc:91.6%, Test_loss:0.459, Lr:1.00E-04
Epoch:15, Train_acc:98.9%, Train_loss:0.037, Test_acc:89.8%, Test_loss:0.846, Lr:1.00E-04
Epoch:16, Train_acc:98.8%, Train_loss:0.048, Test_acc:91.6%, Test_loss:0.603, Lr:1.00E-04
Epoch:17, Train_acc:100.0%, Train_loss:0.005, Test_acc:92.4%, Test_loss:0.610, Lr:1.00E-04
Epoch:18, Train_acc:99.8%, Train_loss:0.005, Test_acc:92.0%, Test_loss:0.650, Lr:1.00E-04
Epoch:19, Train_acc:99.9%, Train_loss:0.006, Test_acc:92.9%, Test_loss:0.622, Lr:1.00E-04
Epoch:20, Train_acc:99.6%, Train_loss:0.013, Test_acc:92.0%, Test_loss:0.642, Lr:1.00E-04
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
from datetime import datetime
current_time = datetime.now() # 获取当前时间
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.xlabel(current_time) # 打卡请带上时间戳，否则代码截图无效
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()
best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)
epoch_test_acc, epoch_test_loss
(0.9333333333333333, 0.609610618604611)
# 查看是否与我们记录的最高准确率一致
epoch_test_acc
0.9333333333333333
总结
- 了解YOLO的基本知识
- 学习了用YOLOv5中的C3模块搭建网络
- 从时间上直观的和之前的VGG16进行对比，感觉比VGG训练更快且准确率更高
