我想利用谷歌的人工智能平台来部署我的keras模型,这要求模型采用tensorflow SavedModel格式。我正在将 keras 模型保存到张量流估计器模型,然后导出此估计器模型。我在定义serving_input_receiver_fn
时遇到了问题。
以下是我的模型摘要:
Model: "model_49"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_49 (InputLayer) [(None, 400, 254)] 0
_________________________________________________________________
gru_121 (GRU) (None, 400, 64) 61248
_________________________________________________________________
gru_122 (GRU) (None, 64) 24768
_________________________________________________________________
dropout_73 (Dropout) (None, 64) 0
_________________________________________________________________
1M (Dense) (None, 1) 65
=================================================================
Total params: 86,081
Trainable params: 86,081
Non-trainable params: 0
_________________________________________________________________
这是我遇到的错误:
KeyError: "The dictionary passed into features does not have the expected
inputs keys defined in the keras model.ntExpected keys:
{'input_49'}ntfeatures keys: {'col1','col2', ..., 'col254'}
下面是我的代码。
def serving_input_receiver_fn():
feature_placeholders = {
column.name: tf.placeholder(tf.float64, [None]) for column in INPUT_COLUMNS
}
# feature_placeholders = {
# 'input_49': tf.placeholder(tf.float64, [None])
# }
features = {
key: tf.expand_dims(tensor, -1)
for key, tensor in feature_placeholders.items()
}
return tf.estimator.export.ServingInputReceiver(features, feature_placeholders)
def run():
h5_model_file = '../models/model2.h5'
json_model_file = '../models/model2.json'
model = get_keras_model(h5_model_file, json_model_file)
print(model.summary())
estimator_model = tf.keras.estimator.model_to_estimator(keras_model=model, model_dir='estimator_model')
export_path = estimator_model.export_saved_model('export',
serving_input_receiver_fn=serving_input_receiver_fn)
似乎我的模型需要一个特征键:input_49
(我的神经网络的第一层(,但是,从我看到的代码示例中,例如,serving_receiver_input_fn
将所有特征的字典输入到我的模型中。
我该如何解决这个问题?
我正在使用张量流==2.0.0-beta1。
我已经设法保存了一个 Keras 模型,并使用 tf.saved_model.Builder()
对象使用 TF 服务来托管它。我不确定这是否可以很容易地推广到您的应用程序,但以下是对我有用的方法,尽可能通用。
# Set the path where the model will be saved.
export_base_path = os.path.abspath('models/versions/')
model_version = '1'
export_path = os.path.join(tf.compat.as_bytes(export_base_path),
tf.compat.as_bytes(model_version))
# Make the model builder.
builder = tf.saved_model.builder.SavedModelBuilder(export_path)
# Define the TensorInfo protocol buffer objects that encapsulate our
# input/output tensors.
# Note you can have a list of model.input layers, or just a single model.input
# without any indexing. I'm showing a list of inputs and a single output layer.
# Input tensor info.
tensor_info_input0 = tf.saved_model.utils.build_tensor_info(model.input[0])
tensor_info_input1 = tf.saved_model.utils.build_tensor_info(model.input[1])
# Output tensor info.
tensor_info_output = tf.saved_model.utils.build_tensor_info(model.output)
# Define the call signatures used by the TF Predict API. Note the name
# strings here should match what the layers are called in your model definition.
# Might have to play with that because I forget if it's the name parameter, or
# the actual object handle in your code.
prediction_signature = (
tf.saved_model.signature_def_utils.build_signature_def(
inputs={'input0': tensor_info_input0, 'input1': tensor_info_input1},
outputs={'prediction': tensor_info_output},
method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME))
# Now we build the SavedModel protocol buffer object and then save it.
builder.add_meta_graph_and_variables(sess,
[tf.saved_model.tag_constants.SERVING],
signature_def_map={'predict': prediction_signature})
builder.save(as_text=True)
我会试着找到让我来到这里的参考资料,但当时我没有记下它们。当我找到链接时,我会更新它们。
我最终更改了以下内容:
feature_placeholders = {
column.name: tf.placeholder(tf.float64, [None]) for column in INPUT_COLUMNS
}
对此:
feature_placeholders = {
'input_49': tf.placeholder(tf.float32, (254, None), name='input_49')
}
我能够得到一个带有我的 saved_model.pb 的文件夹。