多层感知机的实现

本文主要是学习了Dive-into-DL-PyTorch这本书。因此这篇博客的大部分内容来源于此书。框架使用的是pytorch，开发工具是pycharm
参考 动手学深度学习Dive-into-DL-Pytorch
参考链接 https://github.com/ShusenTang/Dive-into-DL-PyTorch
https://github.com/zergtant/pytorch-handbook


实现代码

'''
引用
@book{zhang2019dive,
    title={Dive into Deep Learning},
    author={Aston Zhang and Zachary C. Lipton and Mu Li and Alexander J. Smola},
    note={\url{http://www.d2l.ai}},
    year={2020}
}
'''
import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
import torchvision


def load_data_fashion_mnist(batch_size, resize=None, root='~/Datasets/FashionMNIST'):
    """Download the fashion mnist dataset and then load into memory."""
    trans = []
    if resize:
        trans.append(torchvision.transforms.Resize(size=resize))
    trans.append(torchvision.transforms.ToTensor())

    transform = torchvision.transforms.Compose(trans)
    mnist_train = torchvision.datasets.FashionMNIST(root=root, train=True, download=True, transform=transform)
    mnist_test = torchvision.datasets.FashionMNIST(root=root, train=False, download=True, transform=transform)
    if sys.platform.startswith('win'):
        num_workers = 0  # 0表示不用额外的进程来加速读取数据
    else:
        num_workers = 4
    train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)
    test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)

    return train_iter, test_iter

#获取以及读取数据
batch_size = 256
train_iter, test_iter = load_data_fashion_mnist(batch_size)

#初始化参数
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_hiddens)), dtype=torch.float)
b1 = torch.zeros(num_hiddens, dtype=torch.float)
W2 = torch.tensor(np.random.normal(0, 0.01, (num_hiddens, num_outputs)), dtype=torch.float)
b2 = torch.zeros(num_outputs, dtype=torch.float)
params = [W1, b1, W2, b2]
for param in params:
    param.requires_grad_(requires_grad=True)

#定义激活函数
def relu(X):
    return torch.max(input=X, other=torch.tensor(0.0))

#定义模型
def net(X):
    X = X.view((-1, num_inputs))  #通过view函数将每张原始图像改成长度为num_inputs的向量
    H = relu(torch.matmul(X, W1) + b1)
    return torch.matmul(H, W2) + b2

#定义损失函数
loss = torch.nn.CrossEntropyLoss()

#训练   小批量随机梯度下降
def sgd(params, lr, batch_size):
    # 为了和原书保持一致，这里除以了batch_size，但是应该是不用除的，因为一般用PyTorch计算loss时就默认已经
    # 沿batch维求了平均了。
    for param in params:
        param.data -= lr * param.grad / batch_size  # 注意这里更改param时用的param.data

def evaluate_accuracy(data_iter, net, device=None):
    if device is None and isinstance(net, torch.nn.Module):
        # 如果没指定device就使用net的device
        device = list(net.parameters())[0].device
    acc_sum, n = 0.0, 0
    with torch.no_grad():
        for X, y in data_iter:
            if isinstance(net, torch.nn.Module):
                net.eval()  # 评估模式, 这会关闭dropout
                acc_sum += (net(X.to(device)).argmax(dim=1) == y.to(device)).float().sum().cpu().item()
                net.train()  # 改回训练模式
            else:  # 自定义的模型, 3.13节之后不会用到, 不考虑GPU
                if ('is_training' in net.__code__.co_varnames):  # 如果有is_training这个参数
                    # 将is_training设置成False
                    acc_sum += (net(X, is_training=False).argmax(dim=1) == y).float().sum().item()
                else:
                    acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
            n += y.shape[0]
    return acc_sum / n
def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
              params=None, lr=None, optimizer=None):
    for epoch in range(num_epochs):
        train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
        for X, y in train_iter:
            y_hat = net(X)  #调用模型，获得预测值
            l = loss(y_hat, y).sum() #每个小样本（batch size）的损失函数和

            # 梯度清零
            if optimizer is not None:
                optimizer.zero_grad()
            elif params is not None and params[0].grad is not None:
                for param in params:
                    param.grad.data.zero_()  #各个参数的梯度清零

            l.backward()
            if optimizer is None:
                sgd(params, lr, batch_size)
            else:
                optimizer.step()

            train_l_sum += l.item()
            train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
            n += y.shape[0]
        test_acc = evaluate_accuracy(test_iter, net)
        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
              % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc)) #损失的平均值  训练的平均精确度，测试数据的精确度

num_epochs, lr = 5, 100.0
train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr)

结果：

epoch 1, loss 0.0030, train acc 0.714, test acc 0.755
epoch 2, loss 0.0019, train acc 0.822, test acc 0.787
epoch 3, loss 0.0017, train acc 0.842, test acc 0.836
epoch 4, loss 0.0015, train acc 0.856, test acc 0.838
epoch 5, loss 0.0015, train acc 0.863, test acc 0.843