<p>我使用云ML进行批量预测。我的一些模型可以工作,其他的则不行。我如何调试不起作用的模型?我看到的都是一堆错误:<code>Cloud ML only supports TF 1.0 or above and models saved in SavedModel format.</code>在<code>prediction.errors_stats-00000-of-00001</code>中。<code>saved_model_cli show --all --dir</code>的输出是(其他工作模型提供相同的输出)</p>
<pre><code>MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:
signature_def['prediction']:
The given SavedModel SignatureDef contains the following input(s):
inputs['example_proto'] tensor_info:
dtype: DT_STRING
shape: (-1)
name: input:0
The given SavedModel SignatureDef contains the following output(s):
outputs['id'] tensor_info:
dtype: DT_STRING
shape: (-1)
name: id:0
outputs['probability'] tensor_info:
dtype: DT_FLOAT
shape: (-1, 1)
name: probability:0
Method name is: tensorflow/serving/predict
signature_def['serving_default']:
The given SavedModel SignatureDef contains the following input(s):
inputs['example_proto'] tensor_info:
dtype: DT_STRING
shape: (-1)
name: input:0
The given SavedModel SignatureDef contains the following output(s):
outputs['id'] tensor_info:
dtype: DT_STRING
shape: (-1)
name: id:0
outputs['label'] tensor_info:
dtype: DT_INT64
shape: (-1)
name: label:0
outputs['probability'] tensor_info:
dtype: DT_FLOAT
shape: (-1, 1)
name: probability:0
Method name is: tensorflow/serving/predict
</code></pre>
<p>更新:我的数据是TF记录的形式,所以我不能做<code>gcloud ml-engine local predict</code>。在</p>