神经网络与深度学习（邱锡鹏）编程练习4 FNN 交叉熵-多分类 numpy vs. pytorch

import numpy as np
import torch.nn as nn
import torch


# https://blog.csdn.net/QLBFA/article/details/107536486

def cross_entropy_error(y, t):
    delta = 1e-7  # 添加一个微小值可以防止负无限大(np.log(0))的发生。
    return -np.sum(t * np.log(y + delta))


predict = torch.Tensor([[0.1, 0.05, 0.6, 0.0, 0.05, 0.1, 0.0, 0.1, 0.0, 0.0]])
label = torch.tensor([[0.0, 0, 1, 0, 0, 0, 0, 0, 0, 0]])

# numpy
softmax = nn.Softmax(dim=-1)
lossinput = softmax(predict)
print(cross_entropy_error(np.array(lossinput),np.array(label)))  #输出0.510825457099338
# pytorch
cross_loss = nn.CrossEntropyLoss()
print(cross_loss(predict, label))