转换为 CoreMLModel 的 Keras 卷积神经网络具有多数组而不是图像的输入

Question

# Importing the Keras libraries and packages
from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
from keras.layers import Dropout
# Initialising the CNN
chars74k_classifier = Sequential()
# Adding the first convolutional layer
chars74k_classifier.add(Conv2D(32, (3, 3), activation = 'relu', input_shape = (64, 64, 3)))
# Adding the max pooling layer
chars74k_classifier.add(MaxPooling2D(pool_size = (2, 2)))
chars74k_classifier.add(Dropout(0.25))
# Adding the second convolutional layer
chars74k_classifier.add(Conv2D(32, (3, 3), activation='relu'))
# Adding a second max pooling layer
chars74k_classifier.add(MaxPooling2D(pool_size = (2, 2)))
# Adding the third convolutional layer
chars74k_classifier.add(Conv2D(64, (3, 3), activation='relu'))
# Adding a third max pooling layer
chars74k_classifier.add(MaxPooling2D(pool_size = (2, 2)))
chars74k_classifier.add(Dropout(0.50))
# Adding the fourth convolutional layer
chars74k_classifier.add(Conv2D(128, (3, 3), activation='relu'))
# Adding a fourth max pooling layer
chars74k_classifier.add(MaxPooling2D(pool_size = (2, 2)))
# Adding the flattening layer
chars74k_classifier.add(Flatten())
# Adding the fully connected layers (Normal ANN)
chars74k_classifier.add(Dense(activation = 'relu', units = 128))
chars74k_classifier.add(Dense(activation = 'relu', units = 128))
chars74k_classifier.add(Dense(activation = 'softmax', units = 26))
# Compiling the CNN
chars74k_classifier.compile(optimizer='Adadelta',
              loss='categorical_crossentropy',
              metrics=['accuracy'])

这是我为 Keras 卷积神经网络编写的代码，在 keras 中使用 keras 2.0.6 和 tensorflow 1.1.0 进行训练时，它在测试集上的准确率为 86%。当我将此模型导出到 CoreML 模型时，输入的不是图像，而是多数组？我该如何解决这个问题，因为网络的输入实际上是带有颜色的 64x64 图像？

Answer 1

在 coremltools 转换脚本中，指定 input_image_names="input" 参数。