使用Keras库实施的神经网络和以下的训练时的结果。最后,它打印测试分数和测试准确度。我无法弄清楚分数究竟代表什么,但我认为运行测试时预测的数量是正确的。当使用Keras评估模型时测试分数与测试准确度
Epoch 1/15 1200/1200 [==============================] - 4s - loss: 0.6815 - ACC:0.5550 - val_loss:0.6120 - val_acc:0.7525
大纪元2/15 1200/1200 [======================== ======] - 3 - 损失: 0.5481 - ACC:0.7250 - val_loss:0.4645 - val_acc:0.8025
大纪元3/15 1200/1200 [============ ==================] - 3s - loss: 0.5078 - acc:0.7558 - val_loss:0.4354 - val_acc:0.7975
Epoch 4/15 1200/1200 [==============================] - 3s - 损失: 0.4603 - acc: 0.7875 - val_loss:0.3978 - val_acc:0.8350
Epoch 5/15 1200/1200 [============================= =] - 3s - 损失: 0.4367 - acc:0.7992 - val_loss:0.3809 - val_acc:0.8300
Epoch 6/15 1200/1200 [================= =============] - 3s - 损失: 0.4276 - acc:0.8017 - val_loss:0.3884 - val_acc:0.8350
Epoch 7/15 1200/1200 [===== =========================] - 3s - 损失: 0.3975 - acc:0.8167 - val_loss:0.3666 - val_ac c:0.8400
Epoch 8/15 1200/1200 [==============================] - 3s - loss : 0.3916 - acc:0.8183 - val_loss:0.3753 - val_acc:0.8450
Epoch 9/15 1200/1200 [======================= =======] - 3s - 损失: 0.3814 - acc:0.8233 - val_loss:0.3505 - val_acc:0.8475
Epoch 10/15 1200/1200 [=========== ===================] - 3s - loss: 0.3842 - acc:0.8342 - val_loss:0.3672 - val_acc:0.8450
Epoch 11/15 1200/1200 [======= =======================] - 3s - loss: 0.3674 - acc:0.8375 - val_loss:0.3383 - val_acc:0.8525
Epoch 12/15 1200/1200 [==============================] - 3s - 损失: 0.3624 - acc:0.8367 - val_loss: 0.3423 - val_acc:0.8650
Epoch 13/15 1200/1200 [==============================] - 3s - 损失: 0.3497 - acc:0.8475 - val_loss:0.3069 - val_acc:0.8825
Epoch 14/15 1200/1200 [===================== =========] - 3s - 损失: 0.3406 - acc:0.8500 - val_loss:0.2993 - val_acc:0.8775
Epoch 15/15 1200/1200 [==============================] - 3s - 损失: 0.3252 - acc:0.8600 - val_loss:0.2960 - val_acc:0。8775
400分之400[==============================] - 0
测试得分:0.299598811865
测试精度:0.88
望着Keras documentation,我还是不明白是什么成绩。对于评估函数,它说:
返回测试模式下模型的损失值&度量值。
我注意到的一件事是,当测试的准确性越低,得分越高,而准确性越高,得分越低。
什么是你的keras版本,你可以提供的代码? – maz
@maz我使用的是Keras 2.0.3,我正在试验的代码是这样的:https://github.com/fchollet/keras/blob/master/examples/imdb_lstm.py –