Datawhale组队学习打卡营 任务2：softmax和分类模型

模型

损失函数：交叉熵

模型评估：使用准确率accuracy(预测正确的样本数/总的样本数)

使用pytorch来实现softmax

使用的数据集

# *****加载各种包或者模块*****
import torch
from torch import nn
from torch.nn import init
from collections import OrderedDict
import numpy as np
import sys
import d2lzh1981 as d2l         # Datawhale团队提供的包

# *****初始化参数和获取数据*****
batch_size = 256	# 设置batch的大小
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size) # 获取数据

# *****定义网络模型*****
num_inputs = 784  # 将28*28 的二维图片降为784的以为特征
num_outputs = 10  # 10个输出，10分类

# 网络的类，和线性回归类似
class LinearNet(nn.Module):
    def __init__(self, num_inputs, num_outputs):
        super(LinearNet, self).__init__()
        self.linear = nn.Linear(num_inputs, num_outputs)
    def forward(self, x): # x 的形状: (batch, 1, 28, 28)
        y = self.linear(x.view(x.shape[0], -1))
        return y
        
# 用来特征转换的类
class FlattenLayer(nn.Module):
    def __init__(self):
        super(FlattenLayer, self).__init__()
    def forward(self, x): # x 的形状: (batch, *, *, ...)
        return x.view(x.shape[0], -1)

net = nn.Sequential(
		# 方式一，第一种比较好理解，方便一点
        FlattenLayer(),
        LinearNet(num_inputs, num_outputs) 

		# 方式二
        #OrderedDict([
        #   ('flatten', FlattenLayer()),
        #   ('linear', nn.Linear(num_inputs, num_outputs))]) # 或者写成我们自己定义的 LinearNet(num_inputs, num_outputs) 也可以
        )

# *****初始化模型参数*****
init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0)

# *****定义损失函数*****
loss = nn.CrossEntropyLoss() # 下面是他的函数原型
# class torch.nn.CrossEntropyLoss(weight=None, size_average=None, ignore_index=-100, reduce=None, reduction='mean')

# *****定义优化函数*****
optimizer = torch.optim.SGD(net.parameters(), lr=0.1) # 下面是函数原型
# class torch.optim.SGD(params, lr=, momentum=0, dampening=0, weight_decay=0, nesterov=False)

# *****训练*****

# 预测准确率函数
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
    
# 训练函数
def train_fun(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)
            l = loss(y_hat, y).sum()

            # 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_()

            l.backward()
            if optimizer is None:
                sgd(params, lr, batch_size)
            else:
                optimizer.step()  # “softmax回归的简洁实现”一节将用到

            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))

num_epochs = 5
train_fun(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)