深度学习yolov5-Backone模块实现

最新推荐文章于 2024-06-22 16:29:06 发布

我叫全脂牛奶

最新推荐文章于 2024-06-22 16:29:06 发布

阅读量386

点赞数 5

文章标签：深度学习 YOLO 人工智能

本文链接：https://blog.csdn.net/shentianyang0802/article/details/139184894

版权

深度学习第P9周

基础配置
一、前期准备
二、搭载包含Backone模块的模型
- 1.搭建模型
三、训练模型
四、结果可视化
- 1.Loss与Accuracy图
五、个人总结

⭐本文为365天深度学习训练营的学习记录博客
⭐原作者为K同学啊

基础配置

🏡 我的环境：

● 语言环境：Python3.8
● 编译器：jupyter notebook
● 深度学习环境：Pytorch

一、前期准备

1.设置GPU

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")
device

输出：

device(type='cpu')

2.导入数据

import os,PIL,random,pathlib

data_dir = './weather_photos/'
data_dir = pathlib.Path(data_dir)

data_paths  = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[1] for path in data_paths]
classeNames

输出:

['cloudy', 'rain', 'shine', 'sunrise']

# 关于transforms.Compose的更多介绍可以参考：https://blog.csdn.net/qq_38251616/article/details/124878863
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.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。
])

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("./weather_photos/",transform=train_transforms)
total_data

输出:

Dataset ImageFolder
    Number of datapoints: 1125
    Root location: ./weather_photos/
    StandardTransform
Transform: Compose(
               Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=True)
               ToTensor()
               Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
           )

3.划分数据集

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

输出：

(<torch.utils.data.dataset.Subset at 0x2743cf5b340>,
 <torch.utils.data.dataset.Subset at 0x2743cf5af50>)

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 test_dl:
    print("Shape of X [N, C, H, W]: ", X.shape)
    print("Shape of y: ", y.shape, y.dtype)
    break

输出：

Shape of X [N, C, H, W]:  torch.Size([4, 3, 224, 224])
Shape of y:  torch.Size([4]) torch.int64

二、搭载包含Backone模块的模型

1.搭建模型

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 SPPF(nn.Module):
    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
        super().__init__()
        c_ = c1 // 2  # hidden channels
        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')  # suppress torch 1.9.0 max_pool2d() warning
            y1 = self.m(x)
            y2 = self.m(y1)
            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
"""
这个是YOLOv5, 6.0版本的主干网络，这里进行复现
（注：有部分删改，详细讲解将在后续进行展开）
"""
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)
        
        # 全连接网络层，用于分类
        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

device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
    
model = YOLOv5_backbone().to(device)
model

输出：

Using cpu device
YOLOv5_backbone(
  (Conv_1): Conv(
    (conv): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(2, 2), bias=False)
    (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act): SiLU()
  )
  (Conv_2): Conv(
    (conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act): SiLU()
  )
  (C3_3): C3(
    (cv1): Conv(
      (conv): Conv2d(128, 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()
    )
    (cv2): Conv(
      (conv): Conv2d(128, 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()
    )
    (cv3): Conv(
      (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): 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()
        )
        (cv2): Conv(
          (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
      )
    )
  )
  (Conv_4): Conv(
    (conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act): SiLU()
  )
  (C3_5): C3(
    (cv1): Conv(
      (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv2): Conv(
      (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv3): Conv(
      (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
        (cv2): Conv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
      )
    )
  )
  (Conv_6): Conv(
    (conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act): SiLU()
  )
  (C3_7): C3(
    (cv1): Conv(
      (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv2): Conv(
      (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv3): Conv(
      (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
        (cv2): Conv(
          (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
      )
    )
  )
  (Conv_8): Conv(
    (conv): Conv2d(512, 1024, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
    (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (act): SiLU()
  )
  (C3_9): C3(
    (cv1): Conv(
      (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv2): Conv(
      (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv3): Conv(
      (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (m): Sequential(
      (0): Bottleneck(
        (cv1): Conv(
          (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
        (cv2): Conv(
          (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (act): SiLU()
        )
      )
    )
  )
  (SPPF): SPPF(
    (cv1): Conv(
      (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (cv2): Conv(
      (conv): Conv2d(2048, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (act): SiLU()
    )
    (m): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False)
  )
  (classifier): Sequential(
    (0): Linear(in_features=65536, out_features=100, bias=True)
    (1): ReLU()
    (2): Linear(in_features=100, out_features=4, bias=True)
  )
)

三、训练模型

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
    num_batches = len(dataloader)   # 批次数目, (size/batch_size，向上取整)

    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
    num_batches = len(dataloader)          # 批次数目, (size/batch_size，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

import copy

optimizer  = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn    = nn.CrossEntropyLoss() # 创建损失函数

epochs     = 60

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')

输出：

Epoch: 1, Train_acc:59.1%, Train_loss:1.128, Test_acc:65.8%, Test_loss:0.828, Lr:1.00E-04
Epoch: 2, Train_acc:67.2%, Train_loss:0.850, Test_acc:68.4%, Test_loss:0.703, Lr:1.00E-04
Epoch: 3, Train_acc:71.8%, Train_loss:0.729, Test_acc:77.8%, Test_loss:0.492, Lr:1.00E-04
Epoch: 4, Train_acc:73.6%, Train_loss:0.670, Test_acc:79.6%, Test_loss:0.523, Lr:1.00E-04
Epoch: 5, Train_acc:73.9%, Train_loss:0.646, Test_acc:84.0%, Test_loss:0.417, Lr:1.00E-04
Epoch: 6, Train_acc:80.2%, Train_loss:0.449, Test_acc:84.9%, Test_loss:0.376, Lr:1.00E-04
Epoch: 7, Train_acc:85.0%, Train_loss:0.400, Test_acc:89.8%, Test_loss:0.363, Lr:1.00E-04
Epoch: 8, Train_acc:84.8%, Train_loss:0.393, Test_acc:82.2%, Test_loss:0.688, Lr:1.00E-04
Epoch: 9, Train_acc:86.2%, Train_loss:0.352, Test_acc:81.8%, Test_loss:0.536, Lr:1.00E-04
Epoch:10, Train_acc:86.1%, Train_loss:0.345, Test_acc:82.7%, Test_loss:0.475, Lr:1.00E-04
Epoch:11, Train_acc:90.0%, Train_loss:0.254, Test_acc:87.1%, Test_loss:0.367, Lr:1.00E-04
Epoch:12, Train_acc:91.2%, Train_loss:0.231, Test_acc:91.1%, Test_loss:0.285, Lr:1.00E-04
Epoch:13, Train_acc:91.2%, Train_loss:0.278, Test_acc:89.3%, Test_loss:0.288, Lr:1.00E-04
Epoch:14, Train_acc:94.1%, Train_loss:0.180, Test_acc:91.6%, Test_loss:0.257, Lr:1.00E-04
Epoch:15, Train_acc:92.1%, Train_loss:0.182, Test_acc:84.9%, Test_loss:0.513, Lr:1.00E-04
Epoch:16, Train_acc:92.9%, Train_loss:0.201, Test_acc:89.8%, Test_loss:0.359, Lr:1.00E-04
Epoch:17, Train_acc:93.9%, Train_loss:0.164, Test_acc:89.3%, Test_loss:0.318, Lr:1.00E-04
Epoch:18, Train_acc:95.0%, Train_loss:0.145, Test_acc:85.8%, Test_loss:0.421, Lr:1.00E-04
Epoch:19, Train_acc:94.3%, Train_loss:0.170, Test_acc:84.4%, Test_loss:0.540, Lr:1.00E-04
Epoch:20, Train_acc:92.9%, Train_loss:0.217, Test_acc:85.3%, Test_loss:0.413, Lr:1.00E-04
Epoch:21, Train_acc:94.6%, Train_loss:0.155, Test_acc:91.6%, Test_loss:0.282, Lr:1.00E-04
Epoch:22, Train_acc:95.7%, Train_loss:0.126, Test_acc:92.9%, Test_loss:0.230, Lr:1.00E-04
Epoch:23, Train_acc:94.7%, Train_loss:0.144, Test_acc:87.6%, Test_loss:0.292, Lr:1.00E-04
Epoch:24, Train_acc:98.0%, Train_loss:0.051, Test_acc:88.9%, Test_loss:0.344, Lr:1.00E-04
Epoch:25, Train_acc:98.2%, Train_loss:0.053, Test_acc:92.4%, Test_loss:0.272, Lr:1.00E-04
Epoch:26, Train_acc:97.6%, Train_loss:0.080, Test_acc:89.3%, Test_loss:0.323, Lr:1.00E-04
Epoch:27, Train_acc:96.2%, Train_loss:0.125, Test_acc:86.7%, Test_loss:0.415, Lr:1.00E-04
Epoch:28, Train_acc:97.3%, Train_loss:0.075, Test_acc:89.8%, Test_loss:0.428, Lr:1.00E-04
Epoch:29, Train_acc:96.3%, Train_loss:0.108, Test_acc:92.9%, Test_loss:0.263, Lr:1.00E-04
Epoch:30, Train_acc:97.1%, Train_loss:0.097, Test_acc:91.1%, Test_loss:0.339, Lr:1.00E-04
Epoch:31, Train_acc:96.8%, Train_loss:0.095, Test_acc:91.1%, Test_loss:0.390, Lr:1.00E-04
Epoch:32, Train_acc:96.6%, Train_loss:0.104, Test_acc:92.4%, Test_loss:0.241, Lr:1.00E-04
Epoch:33, Train_acc:97.9%, Train_loss:0.054, Test_acc:91.1%, Test_loss:0.336, Lr:1.00E-04
Epoch:34, Train_acc:98.9%, Train_loss:0.042, Test_acc:94.2%, Test_loss:0.267, Lr:1.00E-04
Epoch:35, Train_acc:98.8%, Train_loss:0.028, Test_acc:92.9%, Test_loss:0.294, Lr:1.00E-04
Epoch:36, Train_acc:97.7%, Train_loss:0.078, Test_acc:87.6%, Test_loss:0.591, Lr:1.00E-04
Epoch:37, Train_acc:97.4%, Train_loss:0.071, Test_acc:86.2%, Test_loss:0.433, Lr:1.00E-04
Epoch:38, Train_acc:93.9%, Train_loss:0.193, Test_acc:88.9%, Test_loss:0.443, Lr:1.00E-04
Epoch:39, Train_acc:98.6%, Train_loss:0.053, Test_acc:90.7%, Test_loss:0.300, Lr:1.00E-04
Epoch:40, Train_acc:99.3%, Train_loss:0.016, Test_acc:88.9%, Test_loss:0.368, Lr:1.00E-04
Epoch:41, Train_acc:98.8%, Train_loss:0.033, Test_acc:88.9%, Test_loss:0.505, Lr:1.00E-04
Epoch:42, Train_acc:99.3%, Train_loss:0.023, Test_acc:89.8%, Test_loss:0.430, Lr:1.00E-04
Epoch:43, Train_acc:99.2%, Train_loss:0.019, Test_acc:93.8%, Test_loss:0.284, Lr:1.00E-04
Epoch:44, Train_acc:99.0%, Train_loss:0.035, Test_acc:91.1%, Test_loss:0.438, Lr:1.00E-04
Epoch:45, Train_acc:95.1%, Train_loss:0.178, Test_acc:89.8%, Test_loss:0.442, Lr:1.00E-04
Epoch:46, Train_acc:97.4%, Train_loss:0.063, Test_acc:91.6%, Test_loss:0.495, Lr:1.00E-04
Epoch:47, Train_acc:99.4%, Train_loss:0.017, Test_acc:89.3%, Test_loss:0.585, Lr:1.00E-04
Epoch:48, Train_acc:99.4%, Train_loss:0.018, Test_acc:89.3%, Test_loss:0.539, Lr:1.00E-04
Epoch:49, Train_acc:97.0%, Train_loss:0.099, Test_acc:89.8%, Test_loss:0.449, Lr:1.00E-04
Epoch:50, Train_acc:99.0%, Train_loss:0.030, Test_acc:86.2%, Test_loss:0.884, Lr:1.00E-04
Epoch:51, Train_acc:98.0%, Train_loss:0.061, Test_acc:92.0%, Test_loss:0.376, Lr:1.00E-04
Epoch:52, Train_acc:99.3%, Train_loss:0.022, Test_acc:92.0%, Test_loss:0.444, Lr:1.00E-04
Epoch:53, Train_acc:98.1%, Train_loss:0.055, Test_acc:89.3%, Test_loss:0.608, Lr:1.00E-04
Epoch:54, Train_acc:96.9%, Train_loss:0.086, Test_acc:87.1%, Test_loss:0.367, Lr:1.00E-04
Epoch:55, Train_acc:99.0%, Train_loss:0.026, Test_acc:93.3%, Test_loss:0.278, Lr:1.00E-04
Epoch:56, Train_acc:99.3%, Train_loss:0.022, Test_acc:92.4%, Test_loss:0.457, Lr:1.00E-04
Epoch:57, Train_acc:99.9%, Train_loss:0.005, Test_acc:92.4%, Test_loss:0.432, Lr:1.00E-04
Epoch:58, Train_acc:99.2%, Train_loss:0.026, Test_acc:90.7%, Test_loss:0.382, Lr:1.00E-04
Epoch:59, Train_acc:97.6%, Train_loss:0.067, Test_acc:88.0%, Test_loss:0.475, Lr:1.00E-04
Epoch:60, Train_acc:98.4%, Train_loss:0.057, Test_acc:92.0%, Test_loss:0.385, Lr:1.00E-04
Done

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()