Does Huawei HiLens Only Support Models Trained by ModelArts?

Model Requirements

The models to be imported can be in .om, .pb, or .caffemodel format. Only models in .om format can run on HiLens Kit devices. If you import a model in .pb or .caffemodel format, the Huawei HiLens platform automatically converts it into the .om format.

Not all models can be successfully converted. Before importing and converting a model, check whether it uses the TensorFlow and Caffe operator boundaries supported by .om models. For details, see Caffe Operator Boundaries and TensorFlow Operator Boundaries.

Training Models on ModelArts

You can train your models on ModelArts and import them to Huawei HiLens. For details about how to train a model on ModelArts, see Introduction to Model Training.

• Models developed by ExeML of ModelArts cannot be imported to Huawei HiLens.
• Only the model files instead of models trained on ModelArts can be imported to Huawei HiLens.

Training Models Locally

Before importing a custom model, you need to upload it to OBS. A non-om model package contains Caffe model files .caffemodel and .prototxt and configuration file .cfg, or TensorFlow model file .pb and configuration file .cfg.

For details about how to upload a model file to OBS, see Object Storage Service > Getting Started. The directory to which the model files are uploaded must meet certain specifications. For details, see Model Input Directory Specifications.

Fees will be incurred when you upload files to OBS. For details about OBS pricing, see Product Pricing Details.

When uploading files to OBS, ensure that the OBS bucket and Huawei HiLens are in the same region and the OBS folder name meets the following requirements:

• The folder name cannot contain the following special characters: \:*?"<>|
• The folder name cannot start or end with a period (.) or slash (/).
• The absolute path of the folder can contain a maximum of 1,023 characters.
• The folder name cannot contain two or more adjacent slashes (/).