- 本文为365天深度学习训练营 中的学习记录博客
- 参考文章地址： 365天深度学习训练营-第P6周：好莱坞明星识别
- 作者：K同学啊
一、前期准备
1.设置GPU
import torch
from torch import nn
import torchvision
from torchvision import transforms,datasets,models
import matplotlib.pyplot as plt
import os,PIL,pathlib
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device
device(type='cuda')
2.导入数据
data_dir = './49-data/'
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classNames = [str(path).split('\\')[1] for path in data_paths]
classNames
['Dark', 'Green', 'Light', 'Medium']
train_transforms = transforms.Compose([
transforms.Resize([224,224]),# resize输入图片
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换成tensor
transforms.Normalize(
mean = [0.485, 0.456, 0.406],
std = [0.229,0.224,0.225]) # 从数据集中随机抽样计算得到
])
test_transforms = transforms.Compose([
transforms.Resize([224,224]),# resize输入图片
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换成tensor
transforms.Normalize(
mean = [0.485, 0.456, 0.406],
std = [0.229,0.224,0.225]) # 从数据集中随机抽样计算得到
])
total_data = datasets.ImageFolder(data_dir,transform=train_transforms)
total_data
Dataset ImageFolder
Number of datapoints: 1200
Root location: 49-data
StandardTransform
Transform: Compose(
Resize(size=[224, 224], interpolation=PIL.Image.BILINEAR)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)
total_data.class_to_idx
{'Dark': 0, 'Green': 1, 'Light': 2, 'Medium': 3}
3.数据集划分
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
train_size,test_size
(960, 240)
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)
imgs, labels = next(iter(train_dl))
imgs.shape
torch.Size([32, 3, 224, 224])
import numpy as np
# 指定图片大小，图像大小为20宽、5高的绘图(单位为英寸inch)
plt.figure(figsize=(20, 5))
for i, imgs in enumerate(imgs[:20]):
npimg = imgs.numpy().transpose((1,2,0))
npimg = npimg * np.array((0.229, 0.224, 0.225)) + np.array((0.485, 0.456, 0.406))
npimg = npimg.clip(0, 1)
# 将整个figure分成2行10列，绘制第i+1个子图。
plt.subplot(2, 10, i+1)
plt.imshow(npimg)
plt.axis('off')
for X,y in test_dl:
print('Shape of X [N, C, H, W]:', X.shape)
print('Shape of y:', y.shape)
break
Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y: torch.Size([32])
二、构建简单的CNN网络
1. 搭建模型
import torch.nn.functional as F
# class vgg16(nn.Module):
# def __init__(self):
# super(vgg16,self).__init__()
# self.block1 = nn.Sequential(
# nn.Conv2d(3,64,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.Conv2d(64,64,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.MaxPool2d(kernel_size=(2,2),stride=(2,2))
# )
# self.block2 = nn.Sequential(
# nn.Conv2d(64,128,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.Conv2d(128,128,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.MaxPool2d(kernel_size=(2,2),stride=(2,2))
# )
# self.block3 = nn.Sequential(
# nn.Conv2d(128,256,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.Conv2d(256,256,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.Conv2d(256,256,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.MaxPool2d(kernel_size=(2,2),stride=(2,2))
# )
# self.block4 = nn.Sequential(
# nn.Conv2d(256,512,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.Conv2d(512,512,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.Conv2d(512,512,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.MaxPool2d(kernel_size=(2,2),stride=(2,2))
# )
# self.block5 = nn.Sequential(
# nn.Conv2d(512,512,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.Conv2d(512,512,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.Conv2d(512,512,kernel_size=(3,3),stride=(1,1),padding=(1,1)),
# nn.ReLU(),
# nn.MaxPool2d(kernel_size=(2,2),stride=(2,2))
# )
# self.classifier = nn.Sequential(
# nn.Linear(in_features=512*7*7, out_features=4096),
# nn.ReLU(),
# nn.Linear(in_features=4096,out_features=4096),
# nn.ReLU(),
# nn.Linear(in_features=4096,out_features=4)
# )
# def forward(self,x):
# x = self.block1(x)
# x = self.block2(x)
# x = self.block3(x)
# x = self.block4(x)
# x = self.block5(x)
# x = torch.flatten(x, start_dim=1)
# x = self.classifier(x)
# return x
# model = vgg16().to(device)
# model
from torchvision.models import vgg16
model = vgg16(pretrained = True).to(device)
for param in model.parameters(): # 只训练输出层
param.requires_grad = False
model.classifier._modules['6'] = nn.Linear(4096,len(classNames))
model.to(device)
model
VGG(
(features): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU(inplace=True)
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU(inplace=True)
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(18): ReLU(inplace=True)
(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU(inplace=True)
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU(inplace=True)
(23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(25): ReLU(inplace=True)
(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(27): ReLU(inplace=True)
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU(inplace=True)
(30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
(classifier): Sequential(
(0): Linear(in_features=25088, out_features=4096, bias=True)
(1): ReLU(inplace=True)
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=4096, out_features=4096, bias=True)
(4): ReLU(inplace=True)
(5): Dropout(p=0.5, inplace=False)
(6): Linear(in_features=4096, out_features=4, bias=True)
)
)
2.查看模型详情
import torchsummary as summary
summary.summary(model,(3,224,224))
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 64, 224, 224] 1,792
ReLU-2 [-1, 64, 224, 224] 0
Conv2d-3 [-1, 64, 224, 224] 36,928
ReLU-4 [-1, 64, 224, 224] 0
MaxPool2d-5 [-1, 64, 112, 112] 0
Conv2d-6 [-1, 128, 112, 112] 73,856
ReLU-7 [-1, 128, 112, 112] 0
Conv2d-8 [-1, 128, 112, 112] 147,584
ReLU-9 [-1, 128, 112, 112] 0
MaxPool2d-10 [-1, 128, 56, 56] 0
Conv2d-11 [-1, 256, 56, 56] 295,168
ReLU-12 [-1, 256, 56, 56] 0
Conv2d-13 [-1, 256, 56, 56] 590,080
ReLU-14 [-1, 256, 56, 56] 0
Conv2d-15 [-1, 256, 56, 56] 590,080
ReLU-16 [-1, 256, 56, 56] 0
MaxPool2d-17 [-1, 256, 28, 28] 0
Conv2d-18 [-1, 512, 28, 28] 1,180,160
ReLU-19 [-1, 512, 28, 28] 0
Conv2d-20 [-1, 512, 28, 28] 2,359,808
ReLU-21 [-1, 512, 28, 28] 0
Conv2d-22 [-1, 512, 28, 28] 2,359,808
ReLU-23 [-1, 512, 28, 28] 0
MaxPool2d-24 [-1, 512, 14, 14] 0
Conv2d-25 [-1, 512, 14, 14] 2,359,808
ReLU-26 [-1, 512, 14, 14] 0
Conv2d-27 [-1, 512, 14, 14] 2,359,808
ReLU-28 [-1, 512, 14, 14] 0
Conv2d-29 [-1, 512, 14, 14] 2,359,808
ReLU-30 [-1, 512, 14, 14] 0
MaxPool2d-31 [-1, 512, 7, 7] 0
AdaptiveAvgPool2d-32 [-1, 512, 7, 7] 0
Linear-33 [-1, 4096] 102,764,544
ReLU-34 [-1, 4096] 0
Dropout-35 [-1, 4096] 0
Linear-36 [-1, 4096] 16,781,312
ReLU-37 [-1, 4096] 0
Dropout-38 [-1, 4096] 0
Linear-39 [-1, 4] 16,388
================================================================
Total params: 134,276,932
Trainable params: 16,388
Non-trainable params: 134,260,544
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 218.77
Params size (MB): 512.23
Estimated Total Size (MB): 731.57
----------------------------------------------------------------
三、训练模型
# 设置优化器
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)#要训练什么参数/
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.92)#学习率每5个epoch衰减成原来的1/10
loss_fn = nn.CrossEntropyLoss()
1. 编写训练函数
# 训练循环
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset) # 训练集的大小，一共900张图片
num_batches = len(dataloader) # 批次数目，29（900/32）
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
2.编写测试函数
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，8（255/32=8，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
epochs = 20
train_loss = []
train_acc = []
test_loss = []
test_acc = []
best_acc = 0
for epoch in range(epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
scheduler.step()#学习率衰减
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
# 保存最优模型
if epoch_test_acc > best_acc:
best_acc = epoch_train_acc
state = {
'state_dict': model.state_dict(),#字典里key就是各层的名字，值就是训练好的权重
'best_acc': best_acc,
'optimizer' : optimizer.state_dict(),
}
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')
print('best_acc：',best_acc)
Epoch:18, Train_acc:93.5%, Train_loss:0.270, Test_acc:95.4%，Test_loss:0.223
Epoch:19, Train_acc:94.5%, Train_loss:0.241, Test_acc:95.8%，Test_loss:0.223
Epoch:20, Train_acc:94.4%, Train_loss:0.243, Test_acc:96.2%，Test_loss:0.207
Done
best_acc： 0.94375
四、结果可视化
1.Loss与Accuracy图
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()
2.指定图片进行预测
from PIL import Image
classes = list(total_data.class_to_idx)
def predict_one_img(image_path,model,transform,classes):
test_img = Image.open(image_path).convert('RGB')
plt.imshow(test_img)
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}')
predict_one_img('./49-data/Dark/dark (1).png', model, train_transforms, classNames)
预测结果是：Dark
