Sklearn 指标值与 Keras 值非常不同

Question

我需要一些帮助来了解在 Keras 中拟合模型时如何计算准确度。这是训练模型的样本历史：Train on 340 samples, validate on 60 samplesEpoch 1/100340/340 [==============================] - 5s 13ms/step - loss: 0.8081 - acc: 0.7559 - val_loss: 0.1393 - val_acc: 1.0000Epoch 2/100340/340 [==============================] - 3s 9ms/step - loss: 0.7815 - acc: 0.7647 - val_loss: 0.1367 - val_acc: 1.0000Epoch 3/100340/340 [==============================] - 3s 10ms/step - loss: 0.8042 - acc: 0.7706 - val_loss: 0.1370 - val_acc: 1.0000...Epoch 25/100340/340 [==============================] - 3s 9ms/step - loss: 0.6006 - acc: 0.8029 - val_loss: 0.2418 - val_acc: 0.9333Epoch 26/100340/340 [==============================] - 3s 9ms/step - loss: 0.5799 - acc: 0.8235 - val_loss: 0.3004 - val_acc: 0.8833那么，第一个时期的验证准确度是 1 吗？验证准确率如何优于训练准确率？这些数字显示了准确性和损失的所有值：