这个是从代码层面，详细了解损失函数！
CrossEntropyLoss
import torch
import torch.nn as nn
# 实际中遇到的
outputs = torch.tensor([[0.5870, 0.4130],
[0.6517, 0.3483],
[0.4455, 0.5545],
[0.4786, 0.5214]], requires_grad=True)
y_train_tensor = torch.tensor([0, 0, 1, 1])
print(outputs)
print(y_train_tensor)
# 使用 CrossEntropyLoss 计算损失
criterion = nn.CrossEntropyLoss()
loss = criterion(outputs, y_train_tensor)
print('Outputs:', outputs)
print('Labels:', y_train_tensor)
print('Loss:', loss)
,
标签：函数,outputs,代码,torch,损失,CrossEntropyLoss,train,print,tensor From： https://www.cnblogs.com/mxleader/p/18220796