Epoch 0 - Loss: 29.517078385136386 Epoch 100 - Loss: 0.020163969858276648 Epoch 200 - Loss: 0.020163969858276648 Epoch 300 - Loss: 0.020163969858276648 Epoch 400 - Loss: 0.020163969858276648 Epoch 500 - Loss: 0.020163969858276648 Epoch 600 - Loss: 0.020163969858276648 Epoch 700 - Loss: 0.020163969858276648 Epoch 800 - Loss: 0.020163969858276648 Epoch 900 - Loss: 0.020163969858276648 Epoch 1000 - Loss: 0.020163969858276648 Epoch 1100 - Loss: 0.020163969858276648 Epoch 1200 - Loss: 0.020163969858276648 Epoch 1300 - Loss: 0.020163969858276648 Epoch 1400 - Loss: 0.020163969858276648 Epoch 1500 - Loss: 0.020163969858276648 Epoch 1600 - Loss: 0.020163969858276648 Epoch 1700 - Loss: 0.020163969858276648 Epoch 1800 - Loss: 0.020163969858276648 Epoch 1900 - Loss: 0.020163969858276648
时间: 2024-04-05 14:30:51 浏览: 55
Epoch200-Total_Loss2.0690-Val_Loss2.3955.pth
5星 · 资源好评率100%
这是一个训练神经网络的过程,输出的信息包括每个 epoch 的训练损失值。损失值是网络预测结果与真实值之间的差异程度,损失值越小,表示网络预测结果越接近真实值。在这个例子中,可以看到随着 epoch 的增加,损失值逐渐减小,表明神经网络的预测能力不断提高,最终收敛于一个较小的值。这说明网络已经训练好了,可以使用它进行预测了。
阅读全文