几天来我一直在遇到以下错误,但仍然无法提出解决方案:
InvalidArgumentError(请参见上面的回溯):您必须使用dtype float和形状[?,?,1]的占位符张量'decoder_input'输入值
[[节点解码器输入(在/Users/me/Downloads/google-cloud-sdk/lib/third_party/ml_sdk/cloud/ml/prediction/frameworks/tf_prediction_lib.py:210中定义)]]
(错误代码:2)
我训练了tf.keras.Model
(Python 3.6,Tensorflow 1.13.1)并将其成功导出到Google Cloud ML引擎。
通过运行saved_model_cli show --all --dir=trainer/predict-dir/1552642125
我得到:
MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:
signature_def['serving_default']:
The given SavedModel SignatureDef contains the following input(s):
inputs['decoder_input'] tensor_info:
dtype: DT_FLOAT
shape: (-1, -1, 1)
name: decoder_input_1:0
inputs['encoder_input'] tensor_info:
dtype: DT_FLOAT
shape: (-1, -1, 1)
name: encoder_input_1:0
The given SavedModel SignatureDef contains the following output(s):
outputs['reg_sequence_prediction'] tensor_info:
dtype: DT_FLOAT
shape: (-1, -1, 1)
name: reg_sequence_prediction/BiasAdd:0
Method name is: tensorflow/serving/predict
我的instances.json
文件是:
{"decoder_input": [[0.0], [0.0], [0.0], [0.0], [0.0], [0.0], [0.0], [0.0], [0.0], [0.0], [0.0], [0.0], [0.0], [0.0], [0.0], [0.0]], "encoder_input": [[-1.1672], [-1.1672], [-1.1672], [-1.1672], [-1.1672], [-1.1672], [-1.1672], [-1.1672], [-1.1672], [-1.1672], [-1.1672], [-1.1672], [-1.1672], [-1.1672], [-1.1672], [-1.1672]]}
如您所见,我包括了两个必要的输入值,但仍然收到相同的错误。
我没有添加任何Dropout或Regularization层,该模型是一个简单的seq2seq keras模型,其中包含RNN和GRUCells。
预先感谢您的帮助。