Keras有没有办法指定一个不需要传递目标数据的损失函数?
我试图指定一个省略y_true
参数的损失函数,如下所示:
def custom_loss(y_pred):
但是我收到了以下错误:
Traceback (most recent call last):
File "siamese.py", line 234, in <module>
model.compile(loss=custom_loss,optimizer=Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0))
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 911, in compile
sample_weight, mask)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 436, in weighted
score_array = fn(y_true, y_pred)
TypeError: custom_loss() takes exactly 1 argument (2 given)
然后我尝试在不指定任何目标数据的情况下调用fit()
:
model.fit(x=[x_train,x_train_warped, affines], batch_size = bs, epochs=1)
但看起来没有传递任何目标数据会导致错误:
Traceback (most recent call last):
File "siamese.py", line 264, in <module>
model.fit(x=[x_train,x_train_warped, affines], batch_size = bs, epochs=1)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1435, in fit
batch_size=batch_size)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1322, in _standardize_user_data
in zip(y, sample_weights, class_weights, self._feed_sample_weight_modes)]
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 577, in _standardize_weights
return np.ones((y.shape[0],), dtype=K.floatx())
AttributeError: 'NoneType' object has no attribute 'shape'
我可以手动创建与神经网络输出相同形状的虚拟数据,但这看起来非常混乱。是否有一种简单的方法可以在Keras中指定我缺少的无监督损失函数?
答案 0 :(得分:1)
我认为最好的解决方案是自定义培训,而不是使用model.fit
方法。
完整的演练已发布在Tensorflow tutorials page中。
答案 1 :(得分:0)
将损失函数编写为具有两个参数:
y_true
y_pred
如果您没有y_true
,那很好,您不需要在内部使用它来计算损失,而是在函数原型中保留一个占位符,因此keras不会抱怨。 >
def custom_loss(y_true, y_pred):
# do things with y_pred
return loss
添加自定义参数
您可能还需要在损失函数内使用另一个参数,例如margin
,即使自定义函数只应接受这两个参数。但是有一种解决方法,请使用lambda函数
def custom_loss(y_pred, margin):
# do things with y_pred
return loss
但使用起来像
model.compile(loss=lambda y_true, y_pred: custom_loss(y_pred, margin), ...)