- 🍨 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
我的环境:
- 语言环境:Python3.11.2
- 编译器:PyCharm Community Edition 2022.3
- 深度学习环境:torch==2.0,torchvision==0.15.1
本次目标:
- 了解Backbone模块
一、前期准备
将数据集导入。
import torch
import torch.nn as nn
from torchvision import transforms,datasets
from torchvision.models import vgg16
import PIL,pathlib,warnings
from torchinfo import summary
import matplotlib.pyplot as plt
data_path='F:\\weather\\weather_photos'
data_path=pathlib.Path(data_path)
data_paths = list(data_path.glob('*'))
classNames = [str(path).split('\\')[2] for path in data_paths]
print(classNames)
处理数据并划分数据集。
train_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(data_path, transform=train_transforms)
print(total_data)
print(total_data.class_to_idx)
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])
print(train_dataset,test_dataset)
print(train_size,test_size)
batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,batch_size=batch_size,shuffle=True)
test_dl = torch.utils.data.DataLoader(test_dataset,batch_size=batch_size)
二、构建包含Backbone模块的模型
def autopad(k, p=None):
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):
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)))
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))
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))
class SPPF(nn.Module):
def __init__(self, c1, c2, k=5):
super().__init__()
c_ = c1 // 2
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_ * 4, c2, 1, 1)
self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
def forward(self, x):
x = self.cv1(x)
with warnings.catch_warnings():
warnings.simplefilter('ignore')
y1 = self.m(x)
y2 = self.m(y1)
return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
class YOLOv5_backbone(nn.Module):
def __init__(self):
super(YOLOv5_backbone, self).__init__()
self.Conv_1 = Conv(3, 64, 3, 2, 2)
self.Conv_2 = Conv(64, 128, 3, 2)
self.C3_3 = C3(128, 128)
self.Conv_4 = Conv(128, 256, 3, 2)
self.C3_5 = C3(256, 256)
self.Conv_6 = Conv(256, 512, 3, 2)
self.C3_7 = C3(512, 512)
self.Conv_8 = Conv(512, 1024, 3, 2)
self.C3_9 = C3(1024, 1024)
self.SPPF = SPPF(1024, 1024, 5)
self.classifier = nn.Sequential(
nn.Linear(in_features=65536, out_features=100),
nn.ReLU(),
nn.Linear(in_features=100, out_features=4)
)
def forward(self, x):
x = self.Conv_1(x)
x = self.Conv_2(x)
x = self.C3_3(x)
x = self.Conv_4(x)
x = self.C3_5(x)
x = self.Conv_6(x)
x = self.C3_7(x)
x = self.Conv_8(x)
x = self.C3_9(x)
x = self.SPPF(x)
x = torch.flatten(x, start_dim=1)
x = self.classifier(x)
return x
model = YOLOv5_backbone().to("cpu")
summary(model)
'''
======================================================================
Layer (type:depth-idx) Param #
======================================================================
YOLOv5_backbone --
├─Conv: 1-1 --
│ └─Conv2d: 2-1 1,728
│ └─BatchNorm2d: 2-2 128
│ └─SiLU: 2-3 --
├─Conv: 1-2 --
│ └─Conv2d: 2-4 73,728
│ └─BatchNorm2d: 2-5 256
│ └─SiLU: 2-6 --
├─C3: 1-3 --
│ └─Conv: 2-7 --
│ │ └─Conv2d: 3-1 8,192
│ │ └─BatchNorm2d: 3-2 128
│ │ └─SiLU: 3-3 --
│ └─Conv: 2-8 --
│ │ └─Conv2d: 3-4 8,192
│ │ └─BatchNorm2d: 3-5 128
│ │ └─SiLU: 3-6 --
│ └─Conv: 2-9 --
│ │ └─Conv2d: 3-7 16,384
│ │ └─BatchNorm2d: 3-8 256
│ │ └─SiLU: 3-9 --
│ └─Sequential: 2-10 --
│ │ └─Bottleneck: 3-10 41,216
├─Conv: 1-4 --
│ └─Conv2d: 2-11 294,912
│ └─BatchNorm2d: 2-12 512
│ └─SiLU: 2-13 --
├─C3: 1-5 --
│ └─Conv: 2-14 --
│ │ └─Conv2d: 3-11 32,768
│ │ └─BatchNorm2d: 3-12 256
│ │ └─SiLU: 3-13 --
│ └─Conv: 2-15 --
│ │ └─Conv2d: 3-14 32,768
│ │ └─BatchNorm2d: 3-15 256
│ │ └─SiLU: 3-16 --
│ └─Conv: 2-16 --
│ │ └─Conv2d: 3-17 65,536
│ │ └─BatchNorm2d: 3-18 512
│ │ └─SiLU: 3-19 --
│ └─Sequential: 2-17 --
│ │ └─Bottleneck: 3-20 164,352
├─Conv: 1-6 --
│ └─Conv2d: 2-18 1,179,648
│ └─BatchNorm2d: 2-19 1,024
│ └─SiLU: 2-20 --
├─C3: 1-7 --
│ └─Conv: 2-21 --
│ │ └─Conv2d: 3-21 131,072
│ │ └─BatchNorm2d: 3-22 512
│ │ └─SiLU: 3-23 --
│ └─Conv: 2-22 --
│ │ └─Conv2d: 3-24 131,072
│ │ └─BatchNorm2d: 3-25 512
│ │ └─SiLU: 3-26 --
│ └─Conv: 2-23 --
│ │ └─Conv2d: 3-27 262,144
│ │ └─BatchNorm2d: 3-28 1,024
│ │ └─SiLU: 3-29 --
│ └─Sequential: 2-24 --
│ │ └─Bottleneck: 3-30 656,384
├─Conv: 1-8 --
│ └─Conv2d: 2-25 4,718,592
│ └─BatchNorm2d: 2-26 2,048
│ └─SiLU: 2-27 --
├─C3: 1-9 --
│ └─Conv: 2-28 --
│ │ └─Conv2d: 3-31 524,288
│ │ └─BatchNorm2d: 3-32 1,024
│ │ └─SiLU: 3-33 --
│ └─Conv: 2-29 --
│ │ └─Conv2d: 3-34 524,288
│ │ └─BatchNorm2d: 3-35 1,024
│ │ └─SiLU: 3-36 --
│ └─Conv: 2-30 --
│ │ └─Conv2d: 3-37 1,048,576
│ │ └─BatchNorm2d: 3-38 2,048
│ │ └─SiLU: 3-39 --
│ └─Sequential: 2-31 --
│ │ └─Bottleneck: 3-40 2,623,488
├─SPPF: 1-10 --
│ └─Conv: 2-32 --
│ │ └─Conv2d: 3-41 524,288
│ │ └─BatchNorm2d: 3-42 1,024
│ │ └─SiLU: 3-43 --
│ └─Conv: 2-33 --
│ │ └─Conv2d: 3-44 2,097,152
│ │ └─BatchNorm2d: 3-45 2,048
│ │ └─SiLU: 3-46 --
│ └─MaxPool2d: 2-34 --
├─Sequential: 1-11 --
│ └─Linear: 2-35 6,553,700
│ └─ReLU: 2-36 --
│ └─Linear: 2-37 404
======================================================================
Total params: 21,729,592
Trainable params: 21,729,592
Non-trainable params: 0
======================================================================
'''
三、训练模型
设置超参数。
loss_fn = nn.CrossEntropyLoss()
learn_rate = 1e-3
opt = torch.optim.SGD(model.parameters(),lr=learn_rate)
编写训练函数和测试函数。
def train(dataloader,model,loss_fn,optimizer):
size = len(dataloader.dataset)
num_batchs = len(dataloader)
train_loss, train_acc = 0, 0
for X,y in dataloader:
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_batchs
return train_acc,train_loss
def test(dataloader,model,loss_fn):
size=len(dataloader.dataset)
num_batchs=len(dataloader)
test_loss,test_acc=0,0
with torch.no_grad():
for imgs,target in dataloader:
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_batchs
return test_acc,test_loss
正式训练。
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,epoch_train_loss,epoch_test_acc,epoch_test_loss))
print('Done')
四、结果可视化
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='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
五、指定图片进行预测
classes = list(total_data.class_to_idx)
def predict_one_img(image_path, model, transform, classes):
test_img = PIL.Image.open(image_path).convert('RGB')
test_img=transform(test_img)
img = test_img.to('cpu').unsqueeze(0)
model.eval()
output = model(img)
x,pred = torch.max(output,1)
pred_class=classes[pred]
print(f'预测结果是{pred_class}')
predict_one_img(image_path='F:\\weather_photos\\cloudy\\cloudy1.jpg',model=model,transform=train_transforms,classes=classes)
保存模型参数
PATH = './model.pth'
torch.save(model.state_dict(),PATH)
model.load_state_dict(torch.load(PATH))