• 查看Tensorflow SavedModel模型信息(转)


    当我们拿到别人提供的pb模型时,我们很可能不清楚inputs所需的参数,可以使用以下方法来查看模型信息:

    找到你的tensorflow安装位置,依次定位到以下目录:
    tensorflow_core/python/tools
    执行如下命令:
    python saved_model_cli.py show --dir 模型路径 --all
    之后可以得到如下信息:

    signature_def['serving_default']:
      The given SavedModel SignatureDef contains the following input(s):
        inputs['image_shape'] tensor_info:
            dtype: DT_FLOAT
            shape: (2)
            name: Placeholder_366:0
        inputs['input_image'] tensor_info:
            dtype: DT_FLOAT
            shape: (-1, -1, -1, 3)
            name: input_1:0
      The given SavedModel SignatureDef contains the following output(s):
        outputs['concat_11/concat:0'] tensor_info:
            dtype: DT_FLOAT
            shape: (-1, 4)
            name: concat_11/concat:0
        outputs['concat_12/concat:0'] tensor_info:
            dtype: DT_FLOAT
            shape: (-1)
            name: concat_12/concat:0
        outputs['concat_13/concat:0'] tensor_info:
            dtype: DT_INT32
            shape: (-1)
            name: concat_13/concat:0
      Method name is: tensorflow/serving/predict

    转自:https://blog.csdn.net/github_34790294/article/details/103725850

  • 相关阅读:
    mybatis-plus学习
    代码规范系列
    Error:Abnormal build process termination:
    SpringBoot常用注解
    git深度学习
    spring中创建bean的方式
    jenkis构建“ERROR: Error fetching remote repo ‘origin’“
    tensor2tensor安装bug修复
    Swin-Transformer代码工程进行物体检测
    Linux常用命令
  • 原文地址:https://www.cnblogs.com/zl1991/p/16049675.html
Copyright © 2020-2023  润新知