转换 TensorFlow 模型时 OpenVino 模型优化器错误

Question

我使用 TensorFlow for Poets 2 存储库 (https://github.com/googlecodelabs/tensorflow-for-poets-2) 中的 python 脚本创建了自定义图像分类 .pb 模型文件。

我尝试使用以下脚本使用 OpenVino 模型优化器将其转换为中间表示：

python mo_tf.py --input_model retrained_graph.pb

python mo_tf.py --input_model retrained_graph.pb --mean_values [127.5,127.5,127.5] --input Mul

这两种情况都是这样发生的：

Model Optimizer arguments:
Common parameters:
        - Path to the Input Model:      C:\Program Files (x86)\IntelSWTools\openvino_2019.3.379\deployment_tools\model_optimizer\retrained_graph.pb
        - Path for generated IR:        C:\Program Files (x86)\IntelSWTools\openvino_2019.3.379\deployment_tools\model_optimizer\.
        - IR output name:       retrained_graph
        - Log level:    ERROR
        - Batch:        Not specified, inherited from the model
        - Input layers:         Not specified, inherited from the model
        - Output layers:        Not specified, inherited from the model
        - Input shapes:         Not specified, inherited from the model
        - Mean values:  Not specified
        - Scale values:         Not specified
        - Scale factor:         Not specified
        - Precision of IR:      FP32
        - Enable fusing:        True
        - Enable grouped convolutions fusing:   True
        - Move mean values to preprocess section:       False
        - Reverse input channels:       False
TensorFlow specific parameters:
        - Input model in text protobuf format:  False
        - Path to model dump for TensorBoard:   None
        - List of shared libraries with TensorFlow custom layers implementation:        None
        - Update the configuration file with input/output node names:   None
        - Use configuration file used to generate the model with Object Detection API:  None
        - Operations to offload:        None
        - Patterns to offload:  None
        - Use the config file:  None
Model Optimizer version:        2019.3.0-408-gac8584cb7
[ ERROR ]  -------------------------------------------------
[ ERROR ]  ----------------- INTERNAL ERROR ----------------
[ ERROR ]  Unexpected exception happened.
[ ERROR ]  Please contact Model Optimizer developers and forward the following information:
[ ERROR ]  local variable 'new_attrs' referenced before assignment
[ ERROR ]  Traceback (most recent call last):
  File "C:\Program Files (x86)\IntelSWTools\openvino_2019.3.379\deployment_tools\model_optimizer\mo\front\extractor.py", line 608, in extract_node_attrs
    supported, new_attrs = extractor(Node(graph, node))
  File "C:\Program Files (x86)\IntelSWTools\openvino_2019.3.379\deployment_tools\model_optimizer\mo\pipeline\tf.py", line 132, in <lambda>
    extract_node_attrs(graph, lambda node: tf_op_extractor(node, check_for_duplicates(tf_op_extractors)))
  File "C:\Program Files (x86)\IntelSWTools\openvino_2019.3.379\deployment_tools\model_optimizer\mo\front\tf\extractor.py", line 109, in tf_op_extractor
    attrs = tf_op_extractors[op](node)
  File "C:\Program Files (x86)\IntelSWTools\openvino_2019.3.379\deployment_tools\model_optimizer\mo\front\tf\extractor.py", line 65, in <lambda>
    return lambda node: pb_extractor(node.pb)
  File "C:\Program Files (x86)\IntelSWTools\openvino_2019.3.379\deployment_tools\model_optimizer\mo\front\tf\extractors\const.py", line 31, in tf_const_ext
    result['value'] = tf_tensor_content(pb_tensor.dtype, result['shape'], pb_tensor)
  File "C:\Program Files (x86)\IntelSWTools\openvino_2019.3.379\deployment_tools\model_optimizer\mo\front\tf\extractors\utils.py", line 76, in tf_tensor_content
    dtype=type_helper[0]),
UnicodeDecodeError: 'ascii' codec can't decode byte 0xff in position 0: ordinal not in range(128)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Program Files (x86)\IntelSWTools\openvino_2019.3.379\deployment_tools\model_optimizer\mo\main.py", line 298, in main
    return driver(argv)
  File "C:\Program Files (x86)\IntelSWTools\openvino_2019.3.379\deployment_tools\model_optimizer\mo\main.py", line 247, in driver
    is_binary=not argv.input_model_is_text)
  File "C:\Program Files (x86)\IntelSWTools\openvino_2019.3.379\deployment_tools\model_optimizer\mo\pipeline\tf.py", line 132, in tf2nx
    extract_node_attrs(graph, lambda node: tf_op_extractor(node, check_for_duplicates(tf_op_extractors)))
  File "C:\Program Files (x86)\IntelSWTools\openvino_2019.3.379\deployment_tools\model_optimizer\mo\front\extractor.py", line 614, in extract_node_attrs
    new_attrs['name'] if 'name' in new_attrs else '<UNKNOWN>',
UnboundLocalError: local variable 'new_attrs' referenced before assignment

[ ERROR ]  ---------------- END OF BUG REPORT --------------
[ ERROR ]  -------------------------------------------------

有人知道怎么解决吗？

Answer 1

最终我找到了适合我的解决方案。

我查看了 OpenVino 工具包文档并发现 this (02/03/2020)

'Supported Topologies' 下有一个列表，其中包含与 OpenVino 模型优化器一起使用的拓扑结构。当您使用 TensorFlow for Poets 2 创建模型时，您需要确保选择模型优化器支持的架构。

转换 TensorFlow 模型时 OpenVino 模型优化器错误

OpenVino Model Optimizer Error when converting TensorFlow model

computer-vision

object-recognition

tensorflow-slim

openvino

movidius