machine-learning - Keras 中的无监督损失函数

Question

Keras中有没有办法指定不需要传递目标数据的损失函数？

我尝试指定一个损失函数，该函数省略了 y_true 参数，如下所示:

def custom_loss(y_pred):

但我收到以下错误:

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)

但看起来不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形状相同的虚拟数据，但这看起来非常困惑。有没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？

Answer 1

我认为最好的解决方案是自定义训练，而不是使用 model.fit 方法。

完整的演练发布在 Tensorflow tutorials page 中.