Help Center/ ModelArts/ Drawer/ Converting a Model/ Conversion Input Path
Updated on 2024-12-31 GMT+08:00

Conversion Input Path

Description

OBS path for storing the model to be converted. The requirements for the model input path vary according to the framework.

  • Caffe
    For Caffe-based models, the input path must comply with the following specifications during model conversion:
    |
    |---xxxx.caffemodel         Mandatory. Model parameter file. Only one such file can exist in the input path.
    |---xxxx.prototxt           Mandatory. Model network file. Only one such file can exist in the input path.
    |---insert_op_conf.cfg      Optional. Insertion operator configuration file. Only one such file can exist in the input path.
    |---plugin                  Optional. Custom operator directory. Only one such plugin folder can exist in the input path. Only custom operators developed based on Tensor Engine (TE) are supported.
  • TensorFlow
    For TensorFlow-based models, the input path must comply with the following specifications during model conversion:
    |
    |---saved_model.pb          Mandatory. Model network file. Only one such file can exist in the input path. The model must be in frozen_graph or saved_model format.
    |---variables               Name of a fixed sub-directory, which contains the weight and deviation rate of the model. It is mandatory for the saved_model format and optional for the frozen_graph format.
        |---variables.index     Mandatory
        |---variables.data-00000-of-00001 Mandatory
    |---insert_op_conf.cfg      Optional. Insertion operator configuration file. Only one such file can exist in the input path.
    |---plugin                  Optional. Custom operator directory. Only one such plugin folder can exist in the input path. Only custom operators developed based on Tensor Engine (TE) are supported.