pytorch框架--网络方面--损失函数基本(回归、分类)

基础损失函数示例

import torch
from torch import nn
from torch.nn import L1Loss

inputs = torch.tensor([1, 2, 3], dtype=torch.float32)
targets = torch.tensor([1, 2, 5], dtype=torch.float32)

inputs = torch.reshape(inputs, (1, 1, 1, 3))
targets = torch.reshape(targets, (1, 1, 1, 3))

# 回归

# 差值相加    (1-1)+(2-2)+(5-3)
# loss = L1Loss(reduction='sum')
# 默认平均    (1-1)+(2-2)+(5-3) / 3（长度）
loss = L1Loss()
result = loss(inputs, targets)
print(result)

# 均方误差 (1-1)^2+(2-2)^2+(5-3)^2 / 3(长度或者个数)
loss_mse = nn.MSELoss()
result_mse = loss_mse(inputs, targets)
print(result_mse)

# 分类
# 交叉熵
x = torch.tensor([0.1, 0.2, 0.3])
y = torch.tensor([1])
# 预测概率、(多少个一组、几个类别)
x = torch.reshape(x, (1, 3))

loss_cross = nn.CrossEntropyLoss()
result_cross = loss_cross(x, y)
print(result_cross)