导出serve_input_fn（）：ValueError：太多值无法解包（预期2）

Madhi 发表于 Dev

大

我训练了一个Tensorflow估算器模型。当我尝试将模型导出到saved_model.pb文件时，我编写了以下代码来提供必须预测的输入功能。

def csv_serving_input():
    feature_placeholders = {
        'renancy': tf.placeholder(tf.float32, [None]),
        'freq': tf.placeholder(tf.float32, [None]),
        'monetary': tf.placeholder(tf.float32, [None])
    }
    features = feature_placeholders

    return tf.estimator.export.ServingInputReceiver(features,
                                                    feature_placeholders)

并导出模型

model = "trained_model/cluster_01"
export_dir = model_dir + "/export"
estimator.export_savedmodel(export_dir, csv_serving_input)

它引发以下错误ValueError：太多值无法解包（预期2）

我正在发布完整的追溯错误供参考

<ipython-input-93-ecb2562febb3> in <module>()
----> 1 estimator.export_savedmodel(export_dir, csv_serving_input_fn_vtwo)

c:\users\madhivarman\appdata\local\programs\python\python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py in export_savedmodel(self, export_dir_base, serving_input_fn, default_output_alternative_key, assets_extra, as_text, checkpoint_path, graph_rewrite_specs, strip_default_attrs)
   1386       input_ops = serving_input_fn()
   1387       input_alternatives, features = (
-> 1388           saved_model_export_utils.get_input_alternatives(input_ops))
   1389 
   1390       # TODO(b/34388557) This is a stopgap, pending recording model provenance.

c:\users\madhivarman\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\util\deprecation.py in new_func(*args, **kwargs)
    248               'in a future version' if date is None else ('after %s' % date),
    249               instructions)
--> 250       return func(*args, **kwargs)
    251     return tf_decorator.make_decorator(
    252         func, new_func, 'deprecated',

c:\users\madhivarman\appdata\local\programs\python\python35\lib\site-packages\tensorflow\contrib\learn\python\learn\utils\saved_model_export_utils.py in get_input_alternatives(input_ops)
    171     input_alternatives[DEFAULT_INPUT_ALTERNATIVE_KEY] = default_inputs
    172   else:
--> 173     features, unused_labels = input_ops
    174 
    175   if not features:

ValueError: too many values to unpack (expected 2)

我已附上Github Repo以获取完整的代码参考

你可以尝试一下：

def serving_input_fn(): feature_placeholders = { 'var1' : tf.placeholder(tf.float32, [None]), 'var2' : tf.placeholder(tf.float32, [None]), ... } features = { key: tf.expand_dims(tensor, -1) for key, tensor in feature_placeholders.items() } return tf.estimator.export.ServingInputReceiver(features, feature_placeholders)

本文收集自互联网，转载请注明来源。

如有侵权，请联系 [email protected] 删除。