Question

我在Keras有一个模特。该模型使用B.交叉熵（对数损失）。但是，我想为此创建自定义的B.C.E日志丢失。这是我的模特

    def get_model(train, num_users, num_items, layers=[20, 10, 5, 2]):
        num_layer = len(layers)  # Number of layers in the MLP
        user_matrix = K.constant(getTrainMatrix(train))
        item_matrix = K.constant(getTrainMatrix(train).T)

        # Input variables
        user_input = Input(shape=(1,), dtype='int32', name='user_input')
        item_input = Input(shape=(1,), dtype='int32', name='item_input')

        user_rating = Lambda(lambda x: tf.gather(user_matrix, tf.to_int32(x)))(user_input)
        item_rating = Lambda(lambda x: tf.gather(item_matrix, tf.to_int32(x)))(item_input)
        user_rating = Reshape((num_items, ))(user_rating)
        item_rating = Reshape((num_users, ))(item_rating)
        MLP_Embedding_User = Dense(layers[0]//2, activation="linear" , name='user_embedding')
        MLP_Embedding_Item  = Dense(layers[0]//2, activation="linear" , name='item_embedding')
        user_latent = MLP_Embedding_User(user_rating)
        item_latent = MLP_Embedding_Item(item_rating)

        # The 0-th layer is the concatenation of embedding layers
        vector = concatenate([user_latent, item_latent])

        # Final prediction layer
        prediction = Dense(1, activation='sigmoid', kernel_initializer=initializers.lecun_normal(),
                       name='prediction')(vector)

        model_ = Model(inputs=[user_input, item_input],
                   outputs=prediction)

        return model_

这是对编译函数的调用。

model.compile(optimizer=Adam(lr=learning_rate), loss='binary_crossentropy')

现在我的问题是如何为其定义自定义二进制交叉熵损失？

如何在Keras中定义和使用自定义损失函数

0 个答案: