我对深度学习还很陌生，但我设法构建了一个多分支图像分类架构，并产生了非常令人满意的结果。
不是那么重要：我正在研究 KKBox 客户流失 ( https://kaggle.com/c/kkbox-churn-prediction-challenge/data )，我将客户行为、交易和静态数据转换为热图，并尝试基于流失者分类在那。
分类本身工作得很好。当我尝试应用 LIME 来查看结果来自哪里时，我的问题就出现了。遵循此处的代码时：https ://marcotcr.github.io/lime/tutorials/Tutorial%20-%20images.html除了我使用输入列表 [members[0],transactions[0],user_logs[ 0]]，我收到以下错误：AttributeError: 'list' object has no attribute 'shape'
我想到的是，LIME 可能不是为像我这样的多输入架构而设计的。另一方面，Microsoft Azure 也有一个多分支架构（http://www.freepatentsonline.com/20180253637.pdf?fbclid=IwAR1j30etyDGPCmG-QGfb8qaGRysvnS_f5wLnKz-KdwEbp2Gk0_-OBsSepVc），据称他们使用 LIME 来解释他们的结果（https://www.slideshare.net/FengZhu18/predicting-azure-churn-with-deep-learning-and-explaining-predictions-with-lime）。
我试图将图像连接到单个输入中，但这种方法产生的结果比多输入方法差得多。不过，LIME 适用于这种方法（尽管不像通常的图像识别那样易于理解）。
DNN 架构：
# Members
members_input = Input(shape=(61,4,3), name='members_input')
x1 = Dropout(0.2)(members_input)
x1 = Conv2D(32, kernel_size = (61,4), padding='valid', activation='relu', strides=1)(x1)
x1 = GlobalMaxPooling2D()(x1)
# Transactions
transactions_input = Input(shape=(61,39,3), name='transactions_input')
x2 = Dropout(0.2)(transactions_input)
x2 = Conv2D(32, kernel_size = (61,1,), padding='valid', activation='relu', strides=1)(x2)
x2 = Conv2D(32, kernel_size = (1,39,), padding='valid', activation='relu', strides=1)(x2)
x2 = GlobalMaxPooling2D()(x2)
# User logs
userlogs_input = Input(shape=(61,7,3), name='userlogs_input')
x3 = Dropout(0.2)(userlogs_input)
x3 = Conv2D(32, kernel_size = (61,1,), padding='valid', activation='relu', strides=1)(x3)
x3 = Conv2D(32, kernel_size = (1,7,), padding='valid', activation='relu', strides=1)(x3)
x3 = GlobalMaxPooling2D()(x3)
# User_logs + Transactions + Members
merged = keras.layers.concatenate([x1,x2,x3]) # Merged layer
out = Dense(2)(merged)
out_2 = Activation('softmax')(out)
model = Model(inputs=[members_input, transactions_input, userlogs_input], outputs=out_2)
model.compile(optimizer="adam", loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()
尝试的 LIME 利用率：
explainer = lime_image.LimeImageExplainer()
explanation = explainer.explain_instance([members_test[0],transactions_test[0],user_logs_test[0]], model.predict, top_labels=2, hide_color=0, num_samples=1000)
型号总结：
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
transactions_input (InputLayer) (None, 61, 39, 3) 0
__________________________________________________________________________________________________
userlogs_input (InputLayer) (None, 61, 7, 3) 0
__________________________________________________________________________________________________
members_input (InputLayer) (None, 61, 4, 3) 0
__________________________________________________________________________________________________
dropout_2 (Dropout) (None, 61, 39, 3) 0 transactions_input[0][0]
__________________________________________________________________________________________________
dropout_3 (Dropout) (None, 61, 7, 3) 0 userlogs_input[0][0]
__________________________________________________________________________________________________
dropout_1 (Dropout) (None, 61, 4, 3) 0 members_input[0][0]
__________________________________________________________________________________________________
conv2d_2 (Conv2D) (None, 1, 39, 32) 5888 dropout_2[0][0]
__________________________________________________________________________________________________
conv2d_4 (Conv2D) (None, 1, 7, 32) 5888 dropout_3[0][0]
__________________________________________________________________________________________________
conv2d_1 (Conv2D) (None, 1, 1, 32) 23456 dropout_1[0][0]
__________________________________________________________________________________________________
conv2d_3 (Conv2D) (None, 1, 1, 32) 39968 conv2d_2[0][0]
__________________________________________________________________________________________________
conv2d_5 (Conv2D) (None, 1, 1, 32) 7200 conv2d_4[0][0]
__________________________________________________________________________________________________
global_max_pooling2d_1 (GlobalM (None, 32) 0 conv2d_1[0][0]
__________________________________________________________________________________________________
global_max_pooling2d_2 (GlobalM (None, 32) 0 conv2d_3[0][0]
__________________________________________________________________________________________________
global_max_pooling2d_3 (GlobalM (None, 32) 0 conv2d_5[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 96) 0 global_max_pooling2d_1[0][0]
global_max_pooling2d_2[0][0]
global_max_pooling2d_3[0][0]
__________________________________________________________________________________________________
dense_1 (Dense) (None, 2) 194 concatenate_1[0][0]
__________________________________________________________________________________________________
activation_1 (Activation) (None, 2) 0 dense_1[0][0]
==================================================================================================
因此我的问题是：有人对多输入 DNN 架构和 LIME 有经验吗？有没有我没有看到的解决方法？我可以使用另一种可解释的模型吗？
谢谢你。