import torch
import torchvision.datasets
from matplotlib import pyplot as plt
from torch.utils.data import DataLoader
from torchvision.transforms import transforms
import torch.nn as nn
import os
os.environ['KMP_DUPLICATE_LIB_OK'] = 'True'
# 调用torchvision中的models中的resnet网络结构
import torchvision.models as models
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
cuda_is_available = torch.cuda.is_available()
transform_train = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
transforms_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
# 超参数
Download = True
EPOCHS = 10
LR = 0.0001
BATCHSIZE = 64
train_data = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=transform_train, download=Download)
test_data = torchvision.datasets.CIFAR10(root="./dataset", train=False, transform=transforms_test, download=Download)
train_size = len(train_data)
test_size = len(test_data)
train_dataloader = DataLoader(dataset=train_data, batch_size=BATCHSIZE, shuffle=True)
test_dataloader = DataLoader(dataset=test_data, batch_size=BATCHSIZE, shuffle=True)
# 调整已经训练好的ResNet网络
class ResNet(nn.Module):
def __init__(self, num_classes=10): # num_classes,此处为 二分类值为2
super(ResNet, self).__init__()
net = models.resnet18(pretrained=True) # 从预训练模型加载resnet18网络参数
net.classifier = nn.Sequential() # 将分类层置空,下面将改变我们的分类层
# self.features = net # 保留resnet的特征层
self.layer0 = nn.Sequential(
net.conv1,
net.bn1,
net.relu,
net.maxpool
)
self.layer1 = net.layer1
self.layer2 = net.layer2
self.layer3 = net.layer3
self.layer4 = net.layer4
self.layer5 = nn.Sequential(
nn.Conv2d(512, 512, (3, 3), (2, 2), 1),
nn.BatchNorm2d(512),
nn.ReLU(True),
nn.Conv2d(512, 512, (3, 3), (1, 1), 1),
nn.BatchNorm2d(512),
nn.Conv2d(512, 512, (3, 3), (1, 1), 1),
nn.BatchNorm2d(512),
nn.ReLU(True),
nn.Conv2d(512, 1024, (3, 3), (1, 1), 1),
nn.BatchNorm2d(1024),
)
self.avgpool = net.avgpool
self.fc = nn.Linear(1024, 1000)
self.classifier = nn.Sequential( # 定义自己的分类层
nn.Linear(1000, 64), # 1000不能改变 ,由resnet18网络决定的,第二个参数为神经元个数可以微调
nn.ReLU(True),
nn.Dropout(0.5),
nn.Linear(64, num_classes),
)
def forward(self, x):
x = self.layer0(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.layer5(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
x = self.classifier(x)
return x
import ResNet_bySelf
# ResNet18 = ResNet_bySelf.ResNet18(3,10)
ResNet = ResNet()
print(ResNet)
from collections.abc import Iterable
def set_freeze_by_names(model, layer_names, freeze=True):
if not isinstance(layer_names, Iterable):
layer_names = [layer_names]
for name, child in model.named_children():
if name not in layer_names:
continue
for param in child.parameters():
param.requires_grad = not freeze
def freeze_by_names(model, layer_names):
set_freeze_by_names(model, layer_names, True)
def unfreeze_by_names(model, layer_names):
set_freeze_by_names(model, layer_names, False)
# 先把features层冻住,只训练FC层
unfreeze_by_names(ResNet, ("features"))
# 优化器选择Adam
optimizer = torch.optim.Adam(ResNet.parameters(), lr=LR)
# 损失函数
loss_func = nn.CrossEntropyLoss() # 目标标签是one-hotted
if cuda_is_available:
loss_func.cuda()
ResNet.cuda()
# 开始训练
train_loss = []
train_acc = []
test_loss = []
test_acc = []
for epoch in range(EPOCHS):
print("第{}轮训练开始:".format(epoch + 1))
total_train_loss = 0
total_test_loss = 0
total_train_acc = 0
total_test_acc = 0
for step, (b_x, b_y) in enumerate(train_dataloader): # 分配batch data
if cuda_is_available:
b_x = b_x.cuda()
b_y = b_y.cuda()
output = ResNet(b_x) # 先将数据放到cnn中计算output
loss = loss_func(output, b_y) # 输出和真实标签的loss,二者位置不可颠倒
total_train_loss += loss.data.item()
optimizer.zero_grad() # 清除之前学到的梯度的参数
loss.backward() # 反向传播,计算梯度
optimizer.step() # 应用梯度
_, train_pred_y = torch.max(output, 1)
train_accuracy = (train_pred_y == b_y).sum()
total_train_acc += train_accuracy.item()
print("整体训练集上的loss:{},正确率:{:.2f}%".format(total_train_loss / train_size, 100 * total_train_acc / train_size))
train_loss.append(total_train_loss / train_size)
train_acc.append(100 * total_train_acc / train_size)
for test_step, (test_x, test_y) in enumerate(test_dataloader):
if cuda_is_available:
test_x = test_x.cuda()
test_y = test_y.cuda()
test_output = ResNet(test_x)
_, pred_y = torch.max(test_output, 1)
test_loss_1 = loss_func(test_output, test_y)
total_test_loss += test_loss_1.data.item()
accuracy = (pred_y == test_y).sum()
total_test_acc += accuracy.item()
# print('| test loss: %.4f' % test_loss.data.numpy(), '| test accuracy: %.2f' % accuracy)
print("整体测试集上的loss:{},正确率:{:.2f}%".format(total_test_loss / test_size, 100 * total_test_acc / test_size))
test_loss.append(total_test_loss / test_size)
test_acc.append(100 * total_test_acc / test_size)
# torch.save(cnn.state_dict(), 'cnn2.pkl')#保存模型
# 加载模型,调用时需将前面训练及保存模型的代码注释掉,否则会再训练一遍
# cnn.load_state_dict(torch.load('cnn2.pkl'))
# cnn.eval()
x = range(EPOCHS)
ax = plt.gca()
plt.plot(x, train_loss, 'b', label="Train_loss")
plt.plot(x, test_loss, 'r', label="test_loss")
plt.title("Train and Test loss")
plt.legend(loc='upper right')
plt.figure()
plt.plot(x, train_acc, 'b', label="Train_accuracy")
plt.plot(x, test_acc, 'r', label="Test_accuracy")
plt.title("Train and Test accuracy")
plt.legend(loc="lower right")
plt.show()
CIFAR10_ResNet
最新推荐文章于 2023-12-20 13:31:12 发布