使用 OpenVINO 工具包转换posenet模型？

Posted 2023-02-16

【中文标题】使用 OpenVINO 工具包转换posenet模型？

【英文标题】：Convert posenet model with OpenVINO toolkit?

【发布时间】：2019-06-03 12:41:21

【问题描述】：

我正在尝试使用 OpenVINO 模型优化器转换posenet 模型（MobileNetV1 架构）。但它会引发如下错误。 我正在使用以下命令进行转换。

python3 mo_tf.py --input_model /vino/models/posenet/_models/model-mobilenet_v1_101.pb --input_meta_graph /vino/models/posenet/_models/checkpoints/model-mobilenet_v1_101.ckpt.meta  --output_dir /vino/models/posenet/

我收到的错误是：

Model Optimizer arguments:
Common parameters:
    - Path to the Input Model:  /vino/models/posenet/_models/model-mobilenet_v1_101.pb
    - Path for generated IR:    /vino/models/posenet/
    - IR output name:   model-mobilenet_v1_101
    - 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:    2019.1.0-341-gc9b66a2
[ ERROR ]  Unknown configuration of input model parameters

我怀疑，我使用了错误的命令，但即使在浏览了它的文档之后也无法弄清楚。任何关于我做错了什么的线索都会非常有帮助。

【参考方案1】：

尽量只提供 input_meta_graph，而不提供 input_model。

https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_TensorFlow.html