基于Pytorch的MINIST数据集soft target的知识蒸馏代码实验

知识蒸馏：教师学生模型，通过软目标实现从教师到学生模型的知识传递

单独训练教师模型

教师模型采用三个全连接层，隐藏层的神经元为1200–>2400–>1200，为防止过拟合，加入Dropout

模型训练采用交叉熵损失，Adam优化器，学习率为1e-4，训练批次epoch=10，batch-size=64

import torch
from torch import nn
from tqdm import tqdm
import torchvision
from torchvision import transforms
from torch.utils.data import DataLoader


class TeacherModel(nn.Module):
    def __init__(self, in_channel=1, num_classes=10):
        super(TeacherModel, self).__init__()
        self.relu = nn.ReLU()
        self.fc1 = nn.Linear(784, 1200)
        self.fc2 = nn.Linear(1200, 2400)
        self.fc3 = nn.Linear(2400, 1200)
        self.fc4 = nn.Linear(1200, num_classes)
        self.dropout = nn.Dropout(p=0.5)

    def forward(self, x):
        x = x.view(-1, 784)
        x = self.fc1(x)
        x = self.dropout(x)
        x = self.relu(x)

        x = self.fc2(x)
        x = self.dropout(x)
        x = self.relu(x)

        x = self.fc3(x)
        x = self.dropout(x)
        x = self.relu(x)

        x = self.fc4(x)

        return x 
    

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")


#load MNIST datasets
train_dataset = torchvision.datasets.MNIST(
    root = "./dataset/",
    train=True,
    transform=transforms.ToTensor(),
    download=True
)
test_dataset = torchvision.datasets.MNIST(
    root = "./dataset/",
    train = False,
    transform=transforms.ToTensor(),
    download=True
)
train_loader = DataLoader(dataset=train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(dataset=test_dataset, batch_size=64, shuffle=False)

if __name__