第P7周：马铃薯病害识别（VGG-16复现）

最新推荐文章于 2024-09-04 18:15:32 发布

计算机真好丸

最新推荐文章于 2024-09-04 18:15:32 发布

阅读量300

点赞数 5

文章标签：深度学习

本文链接：https://blog.csdn.net/weixin_52447211/article/details/141718001

版权

文章目录

一、前期准备
二、手动搭建VGG-16模型
- 2.查看模型详情
三、训练模型
四、结果可视化
总结：

🍨 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

一、前期准备

1.设置GPU

如果设备上支持GPU就使用GPU否则使用CPU

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

device(type='cpu')

2.导入数据

import os,PIL,random,pathlib

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

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

['Late_blight', 'healthy', 'Early_blight']

train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),     ## 将图片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-->转换为标准正态分布(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_transforms = transforms.Compose([
    transforms.Resize([224, 224]),    ## 将图片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-->转换为标准正态分布(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("./PotatoPlants/", transform=train_transforms)
total_data

Dataset ImageFolder
    Number of datapoints: 2152
    Root location: ./PotatoPlants/
    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])
           )

total_data.class_to_idx

{'Early_blight': 0, 'Late_blight': 1, 'healthy': 2}

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

(<torch.utils.data.dataset.Subset at 0x1058215a0>,
 <torch.utils.data.dataset.Subset at 0x105821480>)

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)

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

二、手动搭建VGG-16模型

VGG-16结构说明：

● 13个卷积层（Convolutional Layer），分别用blockX_convX表示

● 3个全连接层（Fully connected Layer），分别用fcX与predictions表示

● 5个池化层（Pool layer），分别用blockX_pool表示

VGG-16包含了16个隐藏层（13个卷积层和3个全连接层），故称为VGG-16

import torch.nn.functional as F

class vgg16(nn.Module):
    def __init__(self):
        super(vgg16, self).__init__()
        ## 卷积块1
        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))
        )
        ## 卷积块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))
        )
        ## 卷积块3
        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))
        )
        ## 卷积块4
        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))
        )
        ## 卷积块5
        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))
        )
        
        ## 全连接网络层，用于分类
        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=3),
        )
            
    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
            
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))

            
model = vgg16().to(device)
model

Using cpu device





vgg16(
  (block1): Sequential(
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU()
    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU()
    (4): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
  )
  (block2): Sequential(
    (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU()
    (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU()
    (4): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
  )
  (block3): Sequential(
    (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU()
    (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU()
    (4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): ReLU()
    (6): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
  )
  (block4): Sequential(
    (0): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU()
    (2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU()
    (4): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): ReLU()
    (6): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
  )
  (block5): Sequential(
    (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU()
    (2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU()
    (4): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (5): ReLU()
    (6): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
  )
  (classifier): Sequential(
    (0): Linear(in_features=25088, out_features=4096, bias=True)
    (1): ReLU()
    (2): Linear(in_features=4096, out_features=4096, bias=True)
    (3): ReLU()
    (4): Linear(in_features=4096, out_features=3, bias=True)
  )
)

2.查看模型详情

# 统计模型参数量以及其他指标
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
           Linear-32                 [-1, 4096]     102,764,544
             ReLU-33                 [-1, 4096]               0
           Linear-34                 [-1, 4096]      16,781,312
             ReLU-35                 [-1, 4096]               0
           Linear-36                    [-1, 3]          12,291
================================================================
Total params: 134,272,835
Trainable params: 134,272,835
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 218.52
Params size (MB): 512.21
Estimated Total Size (MB): 731.30
----------------------------------------------------------------

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
    
    train_loss, train_acc = 0, 0
    
    for X, y in dataloader:       ## 获取图片标签
        X, y = X.to(device), y.to(device) 
        
        ## 计算误差
        pred = model(X)           ## 网络输出
        loss = loss_fn(pred, y)   ## 计算误差
        
        ## 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
        
        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)      ## 测试集大小
    num_batches = len(dataloader)       ## 批次数目
    test_loss, test_acc = 0, 0
    
    with torch.no_grad():
        for imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)
            
            target_pred = model(imgs)
            loss = loss_fn(target_pred, target)
            
            test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()
            test_loss += loss.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 = 40

train_loss = []
train_acc = []
test_loss = []
test_acc = []

best_acc = 0      ## 设置一个最佳准确率，作为模型的判别标准

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)
    
    ## 保存到最佳模型 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_group'][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夹中
PATH = './best_model.pth'      ## 保存的参数文件名
torch.save(model.state_dict(), PATH)

print('Done')

Epoch: 1, Train_acc:45.6%, Train_loss:0.907, Test_acc:45.0%, Test_loss:0.906, Lr:1.00E-04
Epoch: 2, Train_acc:51.2%, Train_loss:0.810, Test_acc:81.4%, Test_loss:0.513, Lr:1.00E-04
Epoch: 3, Train_acc:83.0%, Train_loss:0.484, Test_acc:82.1%, Test_loss:0.485, Lr:1.00E-04
Epoch: 4, Train_acc:85.1%, Train_loss:0.407, Test_acc:85.4%, Test_loss:0.462, Lr:1.00E-04
Epoch: 5, Train_acc:88.7%, Train_loss:0.300, Test_acc:89.1%, Test_loss:0.260, Lr:1.00E-04
Epoch: 6, Train_acc:89.4%, Train_loss:0.243, Test_acc:88.6%, Test_loss:0.215, Lr:1.00E-04
Epoch: 7, Train_acc:88.1%, Train_loss:0.282, Test_acc:81.9%, Test_loss:0.406, Lr:1.00E-04
Epoch: 8, Train_acc:90.3%, Train_loss:0.217, Test_acc:88.2%, Test_loss:0.342, Lr:1.00E-04
Epoch: 9, Train_acc:90.9%, Train_loss:0.182, Test_acc:90.0%, Test_loss:0.198, Lr:1.00E-04
Epoch:10, Train_acc:90.9%, Train_loss:0.229, Test_acc:88.9%, Test_loss:0.261, Lr:1.00E-04
Epoch:11, Train_acc:96.1%, Train_loss:0.114, Test_acc:96.3%, Test_loss:0.130, Lr:1.00E-04
Epoch:12, Train_acc:96.5%, Train_loss:0.094, Test_acc:97.0%, Test_loss:0.119, Lr:1.00E-04
Epoch:13, Train_acc:97.9%, Train_loss:0.067, Test_acc:97.7%, Test_loss:0.086, Lr:1.00E-04
Epoch:14, Train_acc:98.4%, Train_loss:0.049, Test_acc:94.9%, Test_loss:0.131, Lr:1.00E-04
Epoch:15, Train_acc:98.7%, Train_loss:0.035, Test_acc:97.4%, Test_loss:0.101, Lr:1.00E-04
Epoch:16, Train_acc:98.5%, Train_loss:0.040, Test_acc:94.9%, Test_loss:0.129, Lr:1.00E-04
Epoch:17, Train_acc:98.9%, Train_loss:0.034, Test_acc:94.9%, Test_loss:0.118, Lr:1.00E-04
Epoch:18, Train_acc:98.2%, Train_loss:0.048, Test_acc:94.2%, Test_loss:0.216, Lr:1.00E-04
Epoch:19, Train_acc:97.9%, Train_loss:0.054, Test_acc:97.7%, Test_loss:0.108, Lr:1.00E-04
Epoch:20, Train_acc:98.7%, Train_loss:0.039, Test_acc:95.1%, Test_loss:0.167, Lr:1.00E-04
Epoch:21, Train_acc:99.4%, Train_loss:0.026, Test_acc:96.3%, Test_loss:0.190, Lr:1.00E-04
Epoch:22, Train_acc:99.4%, Train_loss:0.019, Test_acc:96.1%, Test_loss:0.200, Lr:1.00E-04
Epoch:23, Train_acc:98.7%, Train_loss:0.035, Test_acc:96.5%, Test_loss:0.089, Lr:1.00E-04
Epoch:24, Train_acc:99.3%, Train_loss:0.014, Test_acc:96.5%, Test_loss:0.160, Lr:1.00E-04
Epoch:25, Train_acc:99.4%, Train_loss:0.020, Test_acc:91.2%, Test_loss:0.360, Lr:1.00E-04
Epoch:26, Train_acc:98.6%, Train_loss:0.047, Test_acc:98.4%, Test_loss:0.079, Lr:1.00E-04
Epoch:27, Train_acc:99.3%, Train_loss:0.018, Test_acc:95.1%, Test_loss:0.195, Lr:1.00E-04
Epoch:28, Train_acc:99.9%, Train_loss:0.007, Test_acc:95.4%, Test_loss:0.278, Lr:1.00E-04
Epoch:29, Train_acc:99.8%, Train_loss:0.011, Test_acc:97.2%, Test_loss:0.099, Lr:1.00E-04
Epoch:30, Train_acc:99.1%, Train_loss:0.027, Test_acc:96.1%, Test_loss:0.232, Lr:1.00E-04
Epoch:31, Train_acc:98.2%, Train_loss:0.055, Test_acc:96.5%, Test_loss:0.096, Lr:1.00E-04
Epoch:32, Train_acc:99.0%, Train_loss:0.030, Test_acc:95.4%, Test_loss:0.172, Lr:1.00E-04
Epoch:33, Train_acc:99.5%, Train_loss:0.017, Test_acc:97.0%, Test_loss:0.153, Lr:1.00E-04
Epoch:34, Train_acc:100.0%, Train_loss:0.003, Test_acc:97.9%, Test_loss:0.189, Lr:1.00E-04
Epoch:35, Train_acc:99.6%, Train_loss:0.010, Test_acc:97.9%, Test_loss:0.084, Lr:1.00E-04
Epoch:36, Train_acc:100.0%, Train_loss:0.001, Test_acc:97.7%, Test_loss:0.100, Lr:1.00E-04
Epoch:37, Train_acc:100.0%, Train_loss:0.000, Test_acc:97.7%, Test_loss:0.121, Lr:1.00E-04
Epoch:38, Train_acc:100.0%, Train_loss:0.000, Test_acc:97.7%, Test_loss:0.151, Lr:1.00E-04
Epoch:39, Train_acc:100.0%, Train_loss:0.000, Test_acc:97.9%, Test_loss:0.155, Lr:1.00E-04
Epoch:40, Train_acc:100.0%, Train_loss:0.000, Test_acc:98.1%, Test_loss:0.202, 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()

2.指定图片进行预测

from PIL import Image

classes = list(total_data.class_to_idx)

def predict_one_image(image_path, model, transform, classes):
    
    test_img = Image.open(image_path).convert('RGB')
    plt.imshow(test_img)                            ## 展示预测图片
    
    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}')

## 预测训练集中的某张照片
predict_one_image(image_path='./PotatoPlants/Early_blight/1.JPG',
                  model=model,
                  transform=train_transforms,
                  classes=classes)

3.模型评估

best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)

epoch_test_acc, epoch_test_loss

总结：

本周学习了自己搭建VGG-16网络框架，更加深入了解了VGG-16网络结构。
本周学习搭建的的VGG-16网络框架计算量偏大（Total params:134,272,835），训练时间较长，目前暂未发现不影响准确率的前提下轻量化模型的方法。

计算机真好丸

关注

5
点赞
踩
5

收藏

觉得还不错? 一键收藏
0
评论
第P7周：马铃薯病害识别（VGG-16复现）

本周学习了自己搭建VGG-16网络框架，更加深入了解了VGG-16网络结构。本周学习搭建的的VGG-16网络框架计算量偏大（Total params:134,272,835），训练时间较长，目前暂未发现不影响准确率的前提下轻量化模型的方法。
复制链接

扫一扫