使用pytorch建立全连接神经网络

import torch
from torch.autograd import Variable
from torch import tensor, Tensor
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
from torch import nn, optim
from torchvision import datasets, transforms

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt


#定义超参数
batch_size = 64
learning_rate = 1e-2
num_epoches = 20


# 简单的三层全连接神经网络
class SimpleNet(nn.Module):
    def __init__(self, in_dim, n_hidden_1, n_hidden_2, out_dim):
        super().__init__()
        self.layer1 = nn.Linear(in_dim, n_hidden_1)
        self.layer2 = nn.Linear(n_hidden_1, n_hidden_2)
        self.layer3 = nn.Linear(n_hidden_2, out_dim)

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        return x


# 增加了激活函数的三层全连接神经网络
class ActivationNet(nn.Module):
    def __init__(self, in_dim, n_hidden_1, n_hidden_2, out_dim):
        super().__init__()
        self.layer1 = nn.Sequential(nn.Linear(in_dim, n_hidden_1), nn.ReLU(True))
        self.layer2 = nn.Sequential(nn.Linear(n_hidden_1, n_hidden_2), nn.ReLU(True))
        self.layer3 = nn.Sequential(nn.Linear(n_hidden_2, out_dim))

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        return x


# 增加了批标准化的三层全连接神经网络
class BatchNet(nn.Module):
    def __init__(self, in_dim, n_hidden_1, n_hidden_2, out_dim):
        super().__init__()
        self.layer1 = nn.Sequential(nn.Linear(in_dim, n_hidden_1), nn.BatchNorm1d(n_hidden_1), nn.ReLU(True))
        self.layer2 = nn.Sequential(nn.Linear(n_hidden_1, n_hidden_2), nn.BatchNorm1d(n_hidden_2), nn.ReLU(True))
        self.layer3 = nn.Sequential(nn.Linear(n_hidden_2, out_dim))

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        return x


data_tf = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize([0.5], [0.5])]
)

train_dataset = datasets.MNIST(root='./data', train=True, transform=data_tf, download=True)
test_dataset = datasets.MNIST(root='./data', train=False, transform=data_tf)
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

model = SimpleNet(28 * 28, 300, 100, 10)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=learning_rate)

model.eval()
eval_loss = 0
eval_acc = 0

for data in test_loader:
    img, label = data
    img = img.view(img.size(0), -1)
    # volatile已弃用，要改为torch.no_grad()
    # img = Variable(img, volatile=True)
    # label = Variable(label, volatile=True)
    with torch.no_grad():
        img = Variable(img)
        label = Variable(label)
    out = model(img)
    loss = criterion(out, label)
    eval_loss += loss.item() * label.size(0)
    _, pred = torch.max(out, 1)
    num_correct = (pred == label).sum()
    eval_acc += num_correct.item()
    print('Test Loss: {:.6f}, Acc: {:.6f}'.format(eval_loss/(len(test_dataset)), eval_acc/(len(test_dataset))))