小编ank*_*nia的帖子

我尝试过使用 Tensorflow 和 Pytorch CrossEntropyLoss 但它返回不同的值，我不知道为什么。请找到下面的代码和结果。感谢您的投入和帮助。

import tensorflow as tf
import numpy as np

y_true = [3, 3, 1]
y_pred = [
    [0.3377, 0.4867, 0.8842, 0.0854, 0.2147],
    [0.4853, 0.0468, 0.6769, 0.5482, 0.1570],
    [0.0976, 0.9899, 0.6903, 0.0828, 0.0647]
]

scce3 = tf.keras.losses.SparseCategoricalCrossentropy(reduction=tf.keras.losses.Reduction.AUTO)
loss3 = scce3(y_true, y_pred).numpy()
print(loss3)

上面的结果是：1.69

火炬损失：

from torch import nn
import torch
loss = nn.CrossEntropyLoss()
y_true = torch.Tensor([3, 3, 1]).long()
y_pred = torch.Tensor([
    [0.3377, 0.4867, 0.8842, 0.0854, 0.2147],
    [0.4853, 0.0468, 0.6769, 0.5482, 0.1570],
    [0.0976, 0.9899, 0.6903, 0.0828, 0.0647] …