使用torch.nn自带损失函数

import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")torchvision.datasets.MNIST(r"D:\\365天深度学习100列\\Pytorch实战  第P1周：实现mnist手写数字识别", train=True, transform=None, target_transform=None, download=True)
train_ds = torchvision.datasets.MNIST('data', train=True, transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensordownload=True)test_ds  = torchvision.datasets.MNIST('data', train=False, transform=torchvision.transforms.ToTensor(), # 将数据类型转化为Tensordownload=True)batch_size = 32
train_dl = torch.utils.data.DataLoader(train_ds, batch_size=batch_size, shuffle=True)test_dl  = torch.utils.data.DataLoader(test_ds, batch_size=batch_size)imgs, labels = next(iter(train_dl))
print(imgs.shape)import numpy as npimport torch.nn.functional as Fnum_classes = 10  # 图片的类别数class Model(nn.Module):def __init__(self):super().__init__()# 特征提取网络self.conv1 = nn.Conv2d(1, 32, kernel_size=3)  # 第一层卷积,卷积核大小为3*3self.pool1 = nn.MaxPool2d(2)                  # 设置池化层，池化核大小为2*2self.conv2 = nn.Conv2d(32, 64, kernel_size=3) # 第二层卷积,卷积核大小为3*3   self.pool2 = nn.MaxPool2d(2) # 分类网络self.fc1 = nn.Linear(1600, 64)          self.fc2 = nn.Linear(64, num_classes)# 前向传播def forward(self, x):x = self.pool1(F.relu(self.conv1(x)))     x = self.pool2(F.relu(self.conv2(x)))x = torch.flatten(x, start_dim=1)x = F.relu(self.fc1(x))x = self.fc2(x)return xfrom torchinfo import summary
# 将模型转移到GPU中（我们模型运行均在GPU中进行）
model = Model().to(device)summary(model)# 三、 训练模型
# 1. 设置超参数
loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-2 # 学习率
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)
# 训练循环
def train(dataloader, model, loss_fn, optimizer):size = len(dataloader.dataset)  # 训练集的大小，一共60000张图片num_batches = len(dataloader)   # 批次数目，1875（60000/32）train_loss, train_acc = 0, 0  # 初始化训练损失和正确率for X, y in dataloader:  # 获取图片及其标签X, y = X.to(device), y.to(device)# 计算预测误差pred = model(X)          # 网络输出loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失# 反向传播optimizer.zero_grad()  # grad属性归零loss.backward()        # 反向传播optimizer.step()       # 每一步自动更新# 记录acc与losstrain_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc  /= sizetrain_loss /= num_batchesreturn train_acc, train_lossdef test (dataloader, model, loss_fn):size        = len(dataloader.dataset)  # 测试集的大小，一共10000张图片num_batches = len(dataloader)          # 批次数目，313（10000/32=312.5，向上取整）test_loss, test_acc = 0, 0# 当不进行训练时，停止梯度更新，节省计算内存消耗with torch.no_grad():for imgs, target in dataloader:imgs, target = imgs.to(device), target.to(device)# 计算losstarget_pred = model(imgs)loss        = loss_fn(target_pred, target)test_loss += loss.item()test_acc  += (target_pred.argmax(1) == target).type(torch.float).sum().item()test_acc  /= sizetest_loss /= num_batchesreturn test_acc, test_lossepochs     = 5
train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []for epoch in range(epochs):model.train()epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)model.eval()epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)train_acc.append(epoch_train_acc)train_loss.append(epoch_train_loss)test_acc.append(epoch_test_acc)test_loss.append(epoch_test_loss)template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%，Test_loss:{:.3f}')print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')

Output:

torch.Size([32, 1, 28, 28])
=================================================================
Layer (type:depth-idx) Param #
=================================================================
Model –
├─Conv2d: 1-1 320
├─MaxPool2d: 1-2 –
├─Conv2d: 1-3 18,496
├─MaxPool2d: 1-4 –
├─Linear: 1-5 102,464
├─Linear: 1-6 650
=================================================================
Total params: 121,930
Trainable params: 121,930
Non-trainable params: 0
=================================================================
Epoch: 1, Train_acc:76.6%, Train_loss:0.803, Test_acc:92.8%，Test_loss:0.245
Epoch: 2, Train_acc:94.3%, Train_loss:0.188, Test_acc:96.5%，Test_loss:0.121
Epoch: 3, Train_acc:96.3%, Train_loss:0.120, Test_acc:97.1%，Test_loss:0.095
Epoch: 4, Train_acc:97.2%, Train_loss:0.093, Test_acc:97.7%，Test_loss:0.078
Epoch: 5, Train_acc:97.6%, Train_loss:0.078, Test_acc:98.0%，Test_loss:0.061
Done

Repl Closed

使用自定义损失函数

直接替换交叉熵损失函数即可

loss_fn    = CustomCrossEntropyLoss() # 创建损失函数
learn_rate = 1e-2 # 学习率

class CustomCrossEntropyLoss(torch.nn.Module):def __init__(self):super(CustomCrossEntropyLoss, self).__init__()def forward(self, inputs, targets):# 手动实现交叉熵损失函数log_softmax = inputs.log_softmax(dim=1)loss = -log_softmax[torch.arange(log_softmax.size(0)), targets].mean()return loss

Output：

torch.Size([32, 1, 28, 28])
=================================================================
Layer (type:depth-idx) Param #
=================================================================
Model –
├─Conv2d: 1-1 320
├─MaxPool2d: 1-2 –
├─Conv2d: 1-3 18,496
├─MaxPool2d: 1-4 –
├─Linear: 1-5 102,464
├─Linear: 1-6 650
=================================================================
Total params: 121,930
Trainable params: 121,930
Non-trainable params: 0
=================================================================
Epoch: 1, Train_acc:80.1%, Train_loss:0.664, Test_acc:92.9%，Test_loss:0.239
Epoch: 2, Train_acc:94.6%, Train_loss:0.181, Test_acc:96.1%，Test_loss:0.128
Epoch: 3, Train_acc:96.5%, Train_loss:0.117, Test_acc:97.4%，Test_loss:0.082
Epoch: 4, Train_acc:97.2%, Train_loss:0.090, Test_acc:97.7%，Test_loss:0.075
Epoch: 5, Train_acc:97.7%, Train_loss:0.075, Test_acc:98.0%，Test_loss:0.063
Done

Repl Closed

结论

对比官方所给交叉熵损失函数与自定义的损失函数，结果还是有轻微差别的。

天赋娱乐音乐