在尝试将我的Keras模型转换为CoreML模型时，我收到错误'InputLayer object has no attribute'inbound_nodes' .
这是我的代码：
loaded_model = load_model("diffinception.h5")
coreml_model = coremltools.converters.keras.convert(loaded_model,
input_names="imageSculp", output_names="category")
coreml_model.save("transfertestinception.mlmodel")
“diffinception.h5”是从Keras导入的Inception模型，其中包含我为转移学习而训练的其他图层 .
这是我生成该模型的代码：
model = applications.InceptionV3(weights = "imagenet", include_top=False,
input_shape = (img_width, img_height, 3), pooling = max)
# Freeze layers
for layer in model.layers:
layer.trainable = False
#Adding custom Layers
x = model.output
x = Flatten()(x)
x = Dense(1024, activation="relu")(x)
x = Dropout(0.5)(x)
x = Dense(1024, activation="relu")(x)
predictions = Dense(2, activation="softmax")(x)
# creating the final model
model_final = Model(inputs = model.input, outputs = predictions)
# compile the model
model_final.compile(loss = "categorical_crossentropy", optimizer =
optimizers.SGD(lr=0.001, momentum=0.9), metrics=["accuracy"])
我与Keras的版本保持同步 . 使用Python 2.7
1 回答
我在我的机器上更新了_topology2.py代码以匹配下面的版本（2018年1月17日更新）：
https://github.com/apple/coremltools/blob/master/coremltools/converters/keras/_topology2.py
这解决了这个问题 .