vpruthi/doc-exports
1
0
Fork 0
forked from docs/doc-exports
Code Pull Requests Activity
doc-exports/docs/modelarts/umn/modelarts_23_0108.html
Beibei edf86a8ae7
ModelArts GA UMN 06052022 from R&D (#5) 
ModelArts GA UMN 06052022 from R&D

R&D provided a new version of the ModelArts User Manual in May 2022.
Depends-On: #11

Reviewed-by: Artem Goncharov <Artem.goncharov@gmail.com>
2022-05-23 08:19:57 +00:00

3.4 KiB
Raw Permalink Blame History

Model Input Path Specifications

During model conversion, the model input directory must comply with certain specifications. This section describes how to upload your model package to OBS.

Ascend Chip(coming soon)

The requirements for converting the models run on the Ascend chip are as follows:

  • For TensorFlow-based models (in frozen_graph or saved_model format), the input path must comply with the following specifications during model conversion:
    frozen_graph format
    |
|---xxxx.pb                 (Mandatory) Model network file. Only one model network file can exist in the input path. The model must be in frozen_graph or saved_model format.
|---insert_op_conf.cfg      (Optional) Insertion operator configuration file. Only one insertion operator configuration file can exist in the input path.
|---plugin                  (Optional) Custom operator directory. The input directory can contain only one plugin folder. Only custom operators developed based on Tensor Engine (TE) are supported.

    saved_model format

    |
|---saved_model.pb          (Mandatory) Model network file. Only one model network file can exist in the input path. The model must be in frozen_graph or saved_model format.
|---variables               (Mandatory) Fixed subdirectory name, including the model weight deviation.
    |---variables.index     Mandatory
    |---variables.data-00000-of-00001 Mandatory
|---insert_op_conf.cfg      (Optional) Insertion operator configuration file. Only one insertion operator configuration file can exist in the input path.
|---plugin                  (Optional) Custom operator directory. The input directory can contain only one plugin folder. Only custom operators developed based on Tensor Engine (TE) are supported.