깊이 손에 학습 분류 pytorch는 8 softmax를 달성

• 정의 및 모델을 초기화
• 크로스 엔트로피 손실 함수 softamx
• 사용자 정의 최적화 알고리즘
• 훈련자

import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append('..')
import d2lzh_pytorch as d2l
import torchvision
import torchvision.transforms as transforms

정의 및 모델을 초기화

#与上一节同样的数据集以及批量大小
batch_size= 256
mnist_train= torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',download=True,train=True,transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST',download=True,train=False,transform=transforms.ToTensor())

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

softmax를 출력 층은 완전히 연결 층이므로, 우리의 데이타 앞 샘플 X의 각 배치의 형상은 반환되기 때문에 우리는 선형 모듈이 될 수있는 사용 (BATCH_SIZE, 1,28,28), 우리는 첫 번째 (뷰를 사용) 전체 층으로 연결된 X 변환 (BATCH_SIZE, 784)

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):
        y = self.linear(x.view(x.shape[0],-1))
        return y
net = LinearNet(num_inputs,num_outputs)

# 我们将形状转化的这个功能定义成一个FlattenLayer
class FlattenLayer(nn.Module):
    def __init__(self):
        super(FlattenLayer,self).__init__()
    def forward(self,x):
        return x.view(x.shape[0],-1)

from collections import OrderedDict
net = nn.Sequential(
    OrderedDict(
[
    ('flatten',FlattenLayer()),
    ('linear',nn.Linear(num_inputs,num_outputs))  
])
)
# 之前线性回归的是num_output是1

init.normal_(net.linear.weight,mean=0,std=0.01)
init.constant_(net.linear.bias,val=0)

Parameter containing:
tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], requires_grad=True)

print(net)

Sequential(
  (flatten): FlattenLayer()
  (linear): Linear(in_features=784, out_features=10, bias=True)
)

크로스 엔트로피 손실 함수 softamx

#pytorch提供了一个包括softmax预算和交叉熵损失计算的函数
loss = nn.CrossEntropyLoss()

사용자 정의 최적화 알고리즘

optimizer = torch.optim.SGD(net.parameters(),lr=0.1)

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

훈련자

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:  
                # 上节的代码optimizer is None,使用的手写的代码SGD
                sgd(params, lr, batch_size)
            else:
                # optimizer 非None，
                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))

train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None,optimizer)

epoch 1, loss 0.0031, train acc 0.749, test acc 0.765
epoch 2, loss 0.0022, train acc 0.813, test acc 0.808
epoch 3, loss 0.0021, train acc 0.826, test acc 0.818
epoch 4, loss 0.0020, train acc 0.832, test acc 0.816
epoch 5, loss 0.0019, train acc 0.837, test acc 0.821