批量归一化与未归一化的比较

未归一化的比较： training on cpu epoch 1, loss 0.0091, train acc 0.104, test acc 0.100, time 61.8 sec epoch 2, loss 0.0053, train acc 0.464, test acc 0.611, time 59.1 sec epoch 3, loss 0.0034, train acc 0.652

>>阅读原文<<