softmax(动手学深度学习）

softmax模型全编程

导入模块：

import torch
import torchvision
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

获取训练集数据和测试集数据：

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, root='/home/kesci/input/FashionMNIST2065')

模型参数初始化：

num_inputs = 784
print(28*28)
num_outputs = 10

W = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_outputs)), dtype=torch.float)
b = torch.zeros(num_outputs, dtype=torch.float)
W.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)

定义soft函数：

def softmax(X):
    X_exp = X.exp()
    partition = X_exp.sum(dim=1, keepdim=True)
    # print("X size is ", X_exp.size())
    # print("partition size is ", partition, partition.size())
    return X_exp / partition  # 这里应用了广播机制

 def net(X):
  return softmax(torch.mm(X.view((-1, num_inputs)), W) + b)

损失函数：

def cross_entropy(y_hat, y):
    return - torch.log(y_hat.gather(1, y.view(-1, 1)))

定义准确率：

def accuracy(y_hat, y):
    return (y_hat.argmax(dim=1) == y).float().mean().item() 

这里mean()是求平均值

定义模型准确率：

def evaluate_accuracy(data_iter, net):
    acc_sum, n = 0.0, 0
    for X, y in data_iter:
        acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
        n += y.shape[0]
    return acc_sum / n

训练模型：

num_epochs, lr = 5, 0.1

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)
          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:
              d2l.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))

softmax的简洁实现

导入模块：

import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

获取和读取数据：

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

定义模型

num_inputs = 784
num_outputs = 10

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
    
# net = LinearNet(num_inputs, num_outputs)

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)

from collections import OrderedDict
net = nn.Sequential(
        # FlattenLayer(),
        # LinearNet(num_inputs, num_outputs) 
        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)

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')``

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)

训练模型：

num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)