python - 交叉熵 Keras 中的自定义参数

Question

我需要构建自定义分类交叉熵损失函数，我应该在其中比较 y_true 和 Q*y_pred 而不仅仅是 y_pred。 Q 是一个矩阵。问题是批量大小不能等于1。所以，尺寸有问题。如何构建与 batch_size=200 一起使用的分类交叉熵损失函数？

例如，这是自定义分类交叉熵损失函数，在 batch_size = 1 的情况下可以正常工作。我有 3 个类，因此，y_pred 的形状为 (batch_size, 3, 1)，Q 的形状为 (3,3 ).
我还尝试使用 shape = (batch_size, 3, 3) 传输多维 numpy 数组 但它不起作用。

Q=np.matrix([[0, 0.7,0.2], [0,0,0.8],[1,0.3,0]])

def alpha_loss(y_true, y_pred):         
    return K.categorical_crossentropy(y_true,K.dot(tf.convert_to_tensor(Q,dtype=tf.float32 ),K.reshape(y_pred,(3,1)) ))

Answer 1

由于您使用的是 TensorFlow 后端，因此这可能有效:

Q=np.matrix([[0, 0.7,0.2], [0,0,0.8],[1,0.3,0]])

def alpha_loss(y_true, y_pred):
   # Edit: from the comments below it appears that y_pred has dim (batch_size, 3), so reshape it to have (batch_size, 3, 1)
   y_pred = tf.expand_dims(y_pred, axis=-1)

   q_tf = tf.convert_to_tensor(Q,dtype=tf.float32)

   # Changing the shape of Q from (3,3) to (batch_size, 3, 3)
   q_expanded = tf.tile(tf.expand_dims(q_tf, axis=0), multiples=[tf.shape(y_pred)[0], 1,1])

   # Calculate the matrix multiplication of Q and y_pred, gives a tensor of shape (batch_size, 3, 1)
   qy_pred = tf.matmul(q_expanded, y_pred)

   return K.categorical_crossentropy(y_true, qy_pred)