文章目录
深度学习Week20——Pytorch实现残差网络和ResNet50V2算法
一、前言
二、我的环境
三、代码复现
3.1 配置数据集
3.2 构建模型
四、模型应用与评估
4.1 编写训练函数
4.2 编写测试函数
4.3 训练模型
4.4 结果可视化
一、前言
- 🍨 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
本周我们使用了Pytorch复现代码。
二、我的环境
- 电脑系统:Windows 10
- 语言环境:Python 3.8.0
- 编译器:Pycharm2023.2.3
深度学习环境:Pytorch
显卡及显存:RTX 3060 8G
三、代码复现
3.1 配置数据集
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warnings
warnings.filterwarnings("ignore") #忽略警告信息
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
data_dir = "/home/mw/input/data7619//bird_photos/bird_photos"
data_dir = pathlib.Path(data_dir)
data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[0] for path in data_paths]
print(classeNames)
['/home/mw/input/data7619/bird_photos/bird_photos/Bananaquit', '/home/mw/input/data7619/bird_photos/bird_photos/Black Throated Bushtiti', '/home/mw/input/data7619/bird_photos/bird_photos/Cockatoo', '/home/mw/input/data7619/bird_photos/bird_photos/Black Skimmer']
image_count = len(list(data_dir.glob('*/*')))
print("图片总数为:",image_count)
图片总数为: 565
数据增强
import torchvision.transforms as transforms
from torchvision import datasets
# 这里我们运用上前面学习到的数据增强的方式
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.RandomVerticalFlip(), # 随机垂直翻转
transforms.RandomRotation(15), # 随机旋转图片,范围为-15度到15度
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor,并归一化到[0,1]之间
])
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("/home/mw/input/data7619//bird_photos/bird_photos", transform=train_transforms)
print(total_data.class_to_idx)
{'Bananaquit': 0, 'Black Skimmer': 1, 'Black Throated Bushtiti': 2, 'Cockatoo': 3}
划分训练集、测试集
# 按比例将数据集分割为训练集和测试集
train_size = int(0.8 * len(total_data)) # 计算训练集的大小,占总数据集的80%
test_size = len(total_data) - train_size # 计算测试集的大小,占总数据集的20%
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size]) # 随机分割数据集
# 定义批量大小
batch_size = 32
# 创建训练集的数据加载器
train_dl = torch.utils.data.DataLoader(
train_dataset, # 训练集数据
batch_size=batch_size, # 每个批次的大小为32
shuffle=True, # 打乱数据
num_workers=0 # 使用的工作线程数
)
# 创建测试集的数据加载器
test_dl = torch.utils.data.DataLoader(
test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=0
)
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
Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y: torch.Size([32]) torch.int64
2、 构建模型
首先我们需要定义残差块(block2)和堆栈(stack2),然后创建ResNet50V2模型。
class Block2(nn.Module):
def __init__(self, in_channels, filters, stride=1, conv_shortcut=False):
super(Block2, self).__init__()
self.conv_shortcut = conv_shortcut
self.preact_bn = nn.BatchNorm2d(in_channels)
self.preact_relu = nn.ReLU(inplace=True)
if conv_shortcut:
self.shortcut = nn.Conv2d(in_channels, 4 * filters, kernel_size=1, stride=stride)
else:
self.shortcut = nn.Identity()
if stride > 1:
self.shortcut = nn.MaxPool2d(kernel_size=1, stride=stride)
self.conv1 = nn.Conv2d(in_channels, filters, kernel_size=1, stride=1, bias=False)
self.bn1 = nn.BatchNorm2d(filters)
self.conv2 = nn.Conv2d(filters, filters, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(filters)
self.conv3 = nn.Conv2d(filters, 4 * filters, kernel_size=1)
def forward(self, x):
shortcut = self.shortcut(x)
x = self.preact_bn(x)
x = self.preact_relu(x)
x = self.conv1(x)
x = self.bn1(x)
x = F.relu(x)
x = self.conv2(x)
x = self.bn2(x)
x = F.relu(x)
x = self.conv3(x)
x += shortcut
return x
class Stack2(nn.Module):
def __init__(self, in_channels, filters, blocks, stride1=2):
super(Stack2, self).__init__()
self.blocks = nn.ModuleList()
self.blocks.append(Block2(in_channels, filters, stride=stride1, conv_shortcut=True))
for _ in range(1, blocks):
self.blocks.append(Block2(4 * filters, filters))
def forward(self, x):
for block in self.blocks:
x = block(x)
return x
class ResNet50V2(nn.Module):
def __init__(self, num_classes=1000, include_top=True):
super(ResNet50V2, self).__init__()
self.include_top = include_top
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.conv2 = Stack2(64, 64, 3, stride1=1)
self.conv3 = Stack2(256, 128, 4)
self.conv4 = Stack2(512, 256, 6)
self.conv5 = Stack2(1024, 512, 3, stride1=1)
self.post_bn = nn.BatchNorm2d(2048)
self.post_relu = nn.ReLU(inplace=True)
if include_top:
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(2048, num_classes)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.conv2(x)
x = self.conv3(x)
x = self.conv4(x)
x = self.conv5(x)
x = self.post_bn(x)
x = self.post_relu(x)
if self.include_top:
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.fc(x)
return x
if __name__ == '__main__':
model = ResNet50V2(num_classes=1000)
print(model)
ResNet50V2(
(conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(conv2): Stack2(
(blocks): ModuleList(
(0): Block2(
(preact_bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))
(conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))
)
(1): Block2(
(preact_bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Identity()
(conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))
)
(2): Block2(
(preact_bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Identity()
(conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))
)
)
)
(conv3): Stack2(
(blocks): ModuleList(
(0): Block2(
(preact_bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2))
(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1))
)
(1): Block2(
(preact_bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Identity()
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1))
)
(2): Block2(
(preact_bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Identity()
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1))
)
(3): Block2(
(preact_bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Identity()
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1))
)
)
)
(conv4): Stack2(
(blocks): ModuleList(
(0): Block2(
(preact_bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2))
(conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
)
(1): Block2(
(preact_bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Identity()
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
)
(2): Block2(
(preact_bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Identity()
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
)
(3): Block2(
(preact_bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Identity()
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
)
(4): Block2(
(preact_bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Identity()
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
)
(5): Block2(
(preact_bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Identity()
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
)
)
)
(conv5): Stack2(
(blocks): ModuleList(
(0): Block2(
(preact_bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1))
(conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1))
)
(1): Block2(
(preact_bn): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Identity()
(conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1))
)
(2): Block2(
(preact_bn): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(preact_relu): ReLU(inplace=True)
(shortcut): Identity()
(conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1))
)
)
)
(post_bn): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(post_relu): ReLU(inplace=True)
(avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
(fc): Linear(in_features=2048, out_features=1000, bias=True)
)
四 、模型应用与评估
4.1 编写训练函数
def train(dataloader, model, loss_fn, optimizer):
model.train()
train_loss, train_acc = 0, 0
for X, y in dataloader:
X, y = X.to(device), y.to(device)
# 计算预测误差
pred = model(X)
loss = loss_fn(pred, y)
# 反向传播
optimizer.zero_grad()
loss.backward()
optimizer.step()
train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
train_loss += loss.item()
train_acc /= len(dataloader.dataset)
train_loss /= len(dataloader)
return train_acc, train_loss
4.2 编写测试函数
def test(dataloader, model, loss_fn):
model.eval()
test_loss, test_acc = 0, 0
with torch.no_grad():
for X, y in dataloader:
X, y = X.to(device), y.to(device)
pred = model(X)
loss = loss_fn(pred, y)
test_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
test_loss += loss.item()
test_acc /= len(dataloader.dataset)
test_loss /= len(dataloader)
return test_acc, test_loss
4.3 训练模型
import copy
import torch.nn.functional as F
optimizer = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
epochs = 10
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):
# 更新学习率(使用自定义学习率时使用)
# adjust_learning_rate(optimizer, epoch, learn_rate)
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
# scheduler.step() # 更新学习率(调用官方动态学习率接口时使用)
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')
Epoch: 1, Train_acc:51.8%, Train_loss:4.475, Test_acc:27.4%, Test_loss:5.794, Lr:1.00E-04
Epoch: 2, Train_acc:73.2%, Train_loss:1.766, Test_acc:30.1%, Test_loss:4.920, Lr:1.00E-04
Epoch: 3, Train_acc:79.0%, Train_loss:0.846, Test_acc:54.0%, Test_loss:2.211, Lr:1.00E-04
Epoch: 4, Train_acc:81.0%, Train_loss:0.567, Test_acc:76.1%, Test_loss:0.809, Lr:1.00E-04
Epoch: 5, Train_acc:85.8%, Train_loss:0.428, Test_acc:78.8%, Test_loss:0.761, Lr:1.00E-04
Epoch: 6, Train_acc:83.0%, Train_loss:0.473, Test_acc:79.6%, Test_loss:0.725, Lr:1.00E-04
Epoch: 7, Train_acc:83.6%, Train_loss:0.530, Test_acc:77.9%, Test_loss:0.620, Lr:1.00E-04
Epoch: 8, Train_acc:85.0%, Train_loss:0.479, Test_acc:78.8%, Test_loss:0.830, Lr:1.00E-04
Epoch: 9, Train_acc:85.6%, Train_loss:0.434, Test_acc:82.3%, Test_loss:0.824, Lr:1.00E-04
Epoch:10, Train_acc:88.5%, Train_loss:0.396, Test_acc:70.8%, Test_loss:0.865, Lr:1.00E-04
Done
4.4 结果可视化
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()