使用 LIME 解释神经网络

问：

我正在用以下玩具数据训练神经网络

import keras
import numpy as np
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense
from tensorflow import keras
from tensorflow.keras import layers
from lime import lime_tabular
from lime.lime_tabular import LimeTabularExplainer

X = np.array([[(1,2,3,3,1),(3,2,1,3,2),(3,2,2,3,3),(2,2,1,1,2),(2,1,1,1,1)],
              [(4,5,6,4,4),(5,6,4,3,2),(5,5,6,1,3),(3,3,3,2,2),(2,3,3,2,1)],
              [(7,8,9,4,7),(7,7,6,7,8),(5,8,7,8,8),(6,7,6,7,8),(5,7,6,6,6)],
              [(7,8,9,8,6),(6,6,7,8,6),(8,7,8,8,8),(8,6,7,8,7),(8,6,7,8,8)],
              [(4,5,6,5,5),(5,5,5,6,4),(6,5,5,5,6),(4,4,3,3,3),(5,5,4,4,5)],
              [(4,5,6,5,5),(5,5,5,6,4),(6,5,5,5,6),(4,4,3,3,3),(5,5,4,4,5)],
              [(1,2,3,3,1),(3,2,1,3,2),(3,2,2,3,3),(2,2,1,1,2),(2,1,1,1,1)]])
y = np.array([0, 1, 2, 2, 1,1,0])

我正在训练的神经网络架构如下

model = keras.Sequential([
    layers.LSTM(64, return_sequences=True, input_shape=(5, 5)),
    layers.Conv1D(64, kernel_size=3, activation='relu'),
    layers.MaxPooling1D(pool_size=2),
    layers.Flatten(),
    layers.Dense(128, activation='relu'),
    layers.Dense(3, activation='softmax')  # Adjust the number of output units based on your problem (3 for 3 classes)
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

model.fit(X, y, epochs=10)

我正在尝试确定与在 python 中实现的 LIME 系统最相关的功能。 我正在尝试以下代码

# Create a LIME explainer
explainer = lime_tabular.LimeTabularExplainer(X, mode='classification', feature_names=['feature_{}'.format(i) for i in range(X.shape[1])])

# Choose an instance from your dataset for explanation
instance_idx = 0  # You can choose any index from your dataset
instance = X[instance_idx]

# Explain the prediction for the chosen instance
exp = explainer.explain_instance(instance, model.predict, num_features=5)  # num_features is the number of features to include in the explanation

# Print the explanation
print(exp.as_list())

如果您尝试使用代码，则无法正常工作。 希望有人知道如何解决这个问题 谢谢你的回答。