Keras、AIX360(LIME) - ValueError：输入数组的形状必须为

Question

我正在尝试使用 Keras 的模型制作一些程序，然后使用 AIX360 的 Lime 解释器（它只是原始 LIME 的包装器）对其进行解释。所有数据都是 MNIST 灰度数字。但就我而言，我无法解释这个实例，因为我不知道该向解释者提供什么。我的代码：!pip install aix360!pip install tensorflow==2.2.0from __future__ import print_functionimport warnings# Supress jupyter warnings if required for cleaner outputwarnings.simplefilter('ignore')import numpy as npimport pandas as pdimport kerasimport keras.layersfrom keras.utils.np_utils import to_categorical # convert to one-hot-encodingfrom keras.models import Sequential # Sequeantial layer additionfrom aix360.algorithms.lime import LimeImageExplainerprint('Using keras:', keras.__version__)# Load datasetfrom keras.datasets import mnist# Tuple of Numpy arrays: (x_train, y_train), (x_test, y_test).(train, train_labels), (test, test_labels) = mnist.load_data()# save input image dimensionsimg_rows = train.shape[1]img_cols = train.shape[2]# Get classes and number of valuesvalue_counts = pd.value_counts(train_labels).sort_index()num_classes = value_counts.count()train = train/255test = test/255train = train.reshape(train.shape[0], img_rows, img_cols, 1)test = test.reshape(test.shape[0], img_rows, img_cols, 1)model = keras.Sequential([    keras.layers.Flatten(input_shape=(img_rows, img_cols,1)),    keras.layers.Dense(128, activation='relu'),    keras.layers.Dense(num_classes)])model.compile(loss='sparse_categorical_crossentropy',      optimizer='adam',      metrics=['accuracy'])batch_size = 128epochs = 1model.fit(train, train_labels,          batch_size=batch_size,          epochs=epochs,          verbose=1,          validation_data=(test, test_labels))score = model.evaluate(test, test_labels, verbose=0)print('Test loss:', score[0])print('Test accuracy:', score[1])limeExplainer = LimeImageExplainer()limeExplainer.explain_instance(test[0], model.predict_proba)最后一行是错误所在。不要关注模型是如何训练的，那不是问题。编辑：编辑代码，希望它可以在代码实验室中运行（添加第二行）EDIT2：要完成：tensorflow 2.2.0 keras 2.4.3 aix360 0.2.0

Answer 1

我添加了这个转换并对 RGB 图像进行了训练：

def to_rgb(x):

    x_rgb = np.zeros((x.shape[0], 28, 28, 3))

    for i in range(3):

        x_rgb[..., i] = x[..., 0]

    return x_rgb

train_rgb = to_rgb(train)

test_rgb = to_rgb(test)

它起作用了：

limeExplainer.explain_instance(test_rgb[0], model.predict_proba)

100%

1000/1000 [00:00<00:00, 2598.51it/s]

<lime.lime_image.ImageExplanation at 0x7f8d20381f50>