代码实战（小土堆）——损失函数和反向传播

Loss:计算实际输出和目标之间的差距，为我们更新输出提供一定的依据（反向传播），grad 

L1Loss 

import torch
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))

loss = L1Loss()
result = loss(inputs, targets)

print(result)

MSELoss  

import torch
from torch import nn
from torch.nn import L1Loss, MSELoss

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))

loss_mse = nn.MSELoss()
result_mse = loss_mse(inputs, targets)

print(result_mse)

CrossEntropyLoss 

import torch
from torch import nn
from torch.nn import L1Loss, MSELoss

x = torch.tensor([0.1, 0.2, 0.3])
y = torch.tensor([1])
# 1batch_size,3类
x = torch.reshape(x, (1, 3))
loss_cross = nn.CrossEntropyLoss()
result_cross = loss_cross(x, y)
print(result_cross)

 

反向传播

计算参数的梯度，之后选合适的优化器通过梯度对参数进行优化，降低loss

result_loss = loss(outputs, targets)
result_loss.backward()