python - PyTorch 自定义损失函数

Question

自定义损失函数应该如何实现？使用以下代码会导致错误:

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
import numpy as np
import matplotlib.pyplot as plt
import torch.utils.data as data_utils
import torch.nn as nn
import torch.nn.functional as F

num_epochs = 20

x1 = np.array([0,0])
x2 = np.array([0,1])
x3 = np.array([1,0])
x4 = np.array([1,1])

num_epochs = 200

class cus2(torch.nn.Module):
    
    def __init__(self):
        super(cus2,self).__init__()
    
    def forward(self, outputs, labels):
        # reshape labels to give a flat vector of length batch_size*seq_len
        labels = labels.view(-1)  

        # mask out 'PAD' tokens
        mask = (labels >= 0).float()

        # the number of tokens is the sum of elements in mask
        num_tokens = int(torch.sum(mask).data[0])

        # pick the values corresponding to labels and multiply by mask
        outputs = outputs[range(outputs.shape[0]), labels]*mask

        # cross entropy loss for all non 'PAD' tokens
        return -torch.sum(outputs)/num_tokens


x = torch.tensor([x1,x2,x3,x4]).float()

y = torch.tensor([0,1,1,0]).long()

train = data_utils.TensorDataset(x,y)
train_loader = data_utils.DataLoader(train , batch_size=2 , shuffle=True)

device = 'cpu'

input_size = 2
hidden_size = 100 
num_classes = 2

learning_rate = .0001

class NeuralNet(nn.Module) : 
    def __init__(self, input_size, hidden_size, num_classes) : 
        super(NeuralNet, self).__init__()
        self.fc1 = nn.Linear(input_size , hidden_size)
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(hidden_size , num_classes)

    def forward(self, x) : 
        out = self.fc1(x)
        out = self.relu(out)
        out = self.fc2(out)
        return out
        
for i in range(0 , 1) :
        
        model = NeuralNet(input_size, hidden_size, num_classes).to(device)
        
        criterion = nn.CrossEntropyLoss()
#         criterion = Regress_Loss()
#         criterion = cus2()
        optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
        
        total_step = len(train_loader)
        for epoch in range(num_epochs) : 
            for i,(images , labels) in enumerate(train_loader) : 
                images = images.reshape(-1 , 2).to(device)
                labels = labels.to(device)
                
                outputs = model(images)
                loss = criterion(outputs , labels)
                
                optimizer.zero_grad()
                loss.backward()
                optimizer.step()
#                 print(loss)
                
        outputs = model(x)
        
        print(outputs.data.max(1)[1])

对训练数据做出完美预测:

tensor([0, 1, 1, 0])

使用来自 here 的自定义损失函数:

在上面的代码中实现为cus2

取消注释代码 # criterion = cus2() 以使用此损失函数返回:

tensor([0, 0, 0, 0])

同时返回一个警告:

UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. Use tensor.item() to convert a 0-dim tensor to a Python number

我没有正确实现自定义损失函数？

Answer 1

除以下情况外，您的损失函数在编程上是正确的:

    # the number of tokens is the sum of elements in mask
    num_tokens = int(torch.sum(mask).data[0])

当您执行 torch.sum 时，它会返回一个 0 维张量，因此会出现无法索引的警告。要解决此问题，请按照建议执行 int(torch.sum(mask).item()) 或 int(torch.sum(mask)) 也可以。

现在，您是否尝试使用自定义损失来模拟 CE 损失？如果是，那么您缺少 log_softmax

要解决此问题，请在语句 4 之前添加 outputs = torch.nn.functional.log_softmax(outputs, dim=1)。请注意，如果您已附加教程，log_softmax 已经在转发调用中完成。你也可以那样做。

另外，我注意到学习速度很慢，即使有 CE 损失，结果也不一致。在自定义和 CE 损失的情况下，将学习率提高到 1e-3 对我来说效果很好。