Python 3.x 这意味着我的训练设备成本为负是什么?
我试着训练我的模型,我的成本产出每一个历元都会下降,直到它达到接近零的值,然后变成负值 我想知道负成本产出的含义是什么Python 3.x 这意味着我的训练设备成本为负是什么?,python-3.x,tensorflow,neural-network,deep-learning,Python 3.x,Tensorflow,Neural Network,Deep Learning,我试着训练我的模型,我的成本产出每一个历元都会下降,直到它达到接近零的值,然后变成负值 我想知道负成本产出的含义是什么 Cost after epoch 0: 3499.608553 Cost after epoch 1: 2859.823284 Cost after epoch 2: 1912.205967 Cost after epoch 3: 1041.337282 Cost after epoch 4: 385.100483 Cost after epoch 5: 19.694999 C
Cost after epoch 0: 3499.608553
Cost after epoch 1: 2859.823284
Cost after epoch 2: 1912.205967
Cost after epoch 3: 1041.337282
Cost after epoch 4: 385.100483
Cost after epoch 5: 19.694999
Cost after epoch 6: 0.293331
Cost after epoch 7: 0.244265
Cost after epoch 8: 0.198684
Cost after epoch 9: 0.156083
Cost after epoch 10: 0.117224
Cost after epoch 11: 0.080965
Cost after epoch 12: 0.047376
Cost after epoch 13: 0.016184
Cost after epoch 14: -0.012692
Cost after epoch 15: -0.039486
Cost after epoch 16: -0.064414
Cost after epoch 17: -0.087688
Cost after epoch 18: -0.109426
Cost after epoch 19: -0.129873
Cost after epoch 20: -0.149069
Cost after epoch 21: -0.169113
Cost after epoch 22: -0.184217
Cost after epoch 23: -0.200351
Cost after epoch 24: -0.215847
Cost after epoch 25: -0.230574
Cost after epoch 26: -0.245604
Cost after epoch 27: -0.259469
Cost after epoch 28: -0.272469
Cost after epoch 29: -0.284447
我正在使用tensorflow进行训练这是一个简单的神经网络,有两个隐藏层
,学习率=0.0001,历元数=30,小批量规模=50,列检率=69/29,全部数据集为101434个训练实例
使用交叉熵方程计算成本
tf.nn.sigmoid_cross_entropy_with_logits(logits=Z3, labels=Y)
这意味着标签的格式不是成本函数所期望的格式 通过logits传递给
sigmoid\u cross\u entropy\u的每个标签应为0或1(用于二进制分类)或包含0和1的向量(用于2个以上的类)。否则,它将无法按预期工作
对于n
类,输出层应具有n
单元,标签应在使用逻辑将其传递给sigmoid\u cross\u entropy\u之前进行编码:
Y = tf.one_hot(Y, n)
这假设Y是一个列表或一维标签数组,范围从0
到n-1
标签是一个热向量吗?有多少类?是的,这是我的问题,我的类是从0到7的数字,不是0或1谢谢:)