全连接FC(Batch*Num)

搭建建议网络：

from torch import nnclass Mnist_NN(nn.Module):def __init__(self):super().__init__()self.hidden1 = nn.Linear(784, 128)self.hidden2 = nn.Linear(128, 256)self.out  = nn.Linear(256, 10)def forward(self, x):x = F.relu(self.hidden1(x))x = F.relu(self.hidden2(x))x = self.out(x)return x

封装数据

from torch.utils.data import TensorDataset
from torch.utils.data import DataLoadertrain_ds = TensorDataset(x_train, y_train)
train_dl = DataLoader(train_ds, batch_size=bs, shuffle=True)valid_ds = TensorDataset(x_valid, y_valid)
valid_dl = DataLoader(valid_ds, batch_size=bs * 2)def get_data(train_ds, valid_ds, bs):return (DataLoader(train_ds, batch_size=bs, shuffle=True),DataLoader(valid_ds, batch_size=bs * 2),)

训练模型：

import numpy as npdef fit(steps, model, loss_func, opt, train_dl, valid_dl):for step in range(steps):model.train()for xb, yb in train_dl:loss_batch(model, loss_func, xb, yb, opt)model.eval()with torch.no_grad():losses, nums = zip(*[loss_batch(model, loss_func, xb, yb) for xb, yb in valid_dl])val_loss = np.sum(np.multiply(losses, nums)) / np.sum(nums)print('当前step:'+str(step), '验证集损失：'+str(val_loss))

一般在训练模型时加上model.train()，这样会正常使用Batch Normalization和 Dropout；测试的时候一般选择model.eval()，这样就不会使用Batch Normalization和 Dropout

批量损失函数

from torch import optim
def get_model():model = Mnist_NN()return model, optim.SGD(model.parameters(), lr=0.001)def loss_batch(model, loss_func, xb, yb, opt=None):loss = loss_func(model(xb), yb)if opt is not None:loss.backward()opt.step()opt.zero_grad()return loss.item(), len(xb)

优化器
SGD是一种简单且易于实现的优化算法，但在大规模数据集和复杂模型上收敛缓慢。
Adam是一种自适应学习率调整的优化算法，能够更快地收敛，但可能会占用更多的内存。
在实践中，根据具体问题和数据集的特点，选择适合的优化算法可以提高训练效果。

卷积神经网络CNN(Batch * C * H * W)

Channel First
引入py库

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torchvision import datasets,transforms 
import matplotlib.pyplot as plt
import numpy as np

预处理

# 定义超参数 
input_size = 28  #图像的总尺寸28*28
num_classes = 10  #标签的种类数
num_epochs = 3  #训练的总循环周期
batch_size = 64  #一个撮（批次）的大小，64张图片# 训练集
train_dataset = datasets.MNIST(root='./data',  train=True,   transform=transforms.ToTensor(),  download=True) # 测试集
test_dataset = datasets.MNIST(root='./data', train=False, transform=transforms.ToTensor())# 构建batch数据
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=True)

构建CNN

class CNN(nn.Module):def __init__(self):super(CNN, self).__init__()self.conv1 = nn.Sequential(         # 输入大小 (1, 28, 28)nn.Conv2d(in_channels=1,              # 灰度图out_channels=16,            # 要得到几多少个特征图kernel_size=5,              # 卷积核大小stride=1,                   # 步长padding=2,                  # 如果希望卷积后大小跟原来一样，需要设置padding=(kernel_size-1)/2 if stride=1),                              # 输出的特征图为 (16, 28, 28)nn.ReLU(),                      # relu层nn.MaxPool2d(kernel_size=2),    # 进行池化操作（2x2 区域）, 输出结果为： (16, 14, 14))self.conv2 = nn.Sequential(         # 下一个套餐的输入 (16, 14, 14)nn.Conv2d(16, 32, 5, 1, 2),     # 输出 (32, 14, 14)nn.ReLU(),                      # relu层nn.Conv2d(32, 32, 5, 1, 2),nn.ReLU(),nn.MaxPool2d(2),                # 输出 (32, 7, 7))self.conv3 = nn.Sequential(         # 下一个套餐的输入 (16, 14, 14)nn.Conv2d(32, 64, 5, 1, 2),     # 输出 (32, 14, 14)nn.ReLU(),             # 输出 (32, 7, 7))self.out = nn.Linear(64 * 7 * 7, 10)   # 全连接层得到的结果def forward(self, x):x = self.conv1(x)x = self.conv2(x)x = self.conv3(x)x = x.view(x.size(0), -1)           # flatten操作，结果为：(batch_size, 32 * 7 * 7)output = self.out(x)return output

定义准确率

def accuracy(predictions, labels):pred = torch.max(predictions.data, 1)[1] rights = pred.eq(labels.data.view_as(pred)).sum() return rights, len(labels)

训练网络模型

# 实例化
net = CNN() 
#损失函数
criterion = nn.CrossEntropyLoss() 
#优化器
optimizer = optim.Adam(net.parameters(), lr=0.001) #定义优化器，普通的随机梯度下降算法#开始训练循环
for epoch in range(num_epochs):#当前epoch的结果保存下来train_rights = [] for batch_idx, (data, target) in enumerate(train_loader):  #针对容器中的每一个批进行循环net.train()                             output = net(data) loss = criterion(output, target) optimizer.zero_grad() loss.backward() optimizer.step() right = accuracy(output, target) train_rights.append(right) if batch_idx % 100 == 0: net.eval() val_rights = [] for (data, target) in test_loader:output = net(data) right = accuracy(output, target) val_rights.append(right)#准确率计算train_r = (sum([tup[0] for tup in train_rights]), sum([tup[1] for tup in train_rights]))val_r = (sum([tup[0] for tup in val_rights]), sum([tup[1] for tup in val_rights]))print('当前epoch: {} [{}/{} ({:.0f}%)]\t损失: {:.6f}\t训练集准确率: {:.2f}%\t测试集正确率: {:.2f}%'.format(epoch, batch_idx * batch_size, len(train_loader.dataset),100. * batch_idx / len(train_loader), loss.data, 100. * train_r[0].numpy() / train_r[1], 100. * val_r[0].numpy() / val_r[1]))