Python Tensorflow输出节点替换为StatefulPartitionedCall，该调用在加载时抛出ValueError

我正在ssd_mobilenet_v2_coco_2018_03_29车型上应用迁移学习。培训结束后，我使用

tf.saved\u model.save（model，saved\u model\u dir）

将keras模型保存为saved\u model.pb

原始ssd_mobilenet_v2_coco_2018_03_29型号具有以下特征定义

signature_def['serving_default']:
  The given SavedModel SignatureDef contains the following input(s):
    inputs['inputs'] tensor_info:
        dtype: DT_UINT8
        shape: (-1, -1, -1, 3)
        name: image_tensor:0
  The given SavedModel SignatureDef contains the following output(s):
    outputs['detection_boxes'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 100, 4)
        name: detection_boxes:0
    outputs['detection_classes'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 100)
        name: detection_classes:0
    outputs['detection_scores'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 100)
        name: detection_scores:0
    outputs['num_detections'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1)
        name: num_detections:0
  Method name is: tensorflow/serving/predict

保存的模型具有以下特征定义（默认值）

原始模型有4个输出节点

detection\u框、detection\u类、detection\u分数、num\u detections

。当我将其导出为保存的模型时，它是如何获得

StatefulPartitionedCall

的？我使用tensorboard查看了保存的模型，所有4个输出节点都可见

[tensorboard图像]：[1]：

当我试图使用batchnorm加载（冻结）保存的模型时，我得到以下错误

ValueError:节点前缀/StatefulPartitionedCall的输入1是从prefix/Conv1/kernel传递的float:0与预期资源不兼容。

知道发生了什么吗？如何恢复原始输出节点（仍然可见）？

我在tf.keras中开发了多输出模型（三个输出），并且面临相同的问题，即所有输出名称都更改为StatefulPartitionedCall:0、StatefulPartitionedCall:1、StatefulPartitionedCall:2

  signature_def['__saved_model_init_op']:
  The given SavedModel SignatureDef contains the following input(s):
  The given SavedModel SignatureDef contains the following output(s):
    outputs['__saved_model_init_op'] tensor_info:
        dtype: DT_INVALID
        shape: unknown_rank
        name: NoOp
  Method name is:

signature_def['serving_default']:
  The given SavedModel SignatureDef contains the following input(s):
    inputs['mobilenetv2_1.00_224_input'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 224, 224, 3)
        name: serving_default_mobilenetv2_1.00_224_input:0
  The given SavedModel SignatureDef contains the following output(s):
    outputs['dense'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 5)
        name: StatefulPartitionedCall:0
  Method name is: tensorflow/serving/predict