Help Center> ModelArts> FAQs> Model Management> Compressing and Converting Models> What Are the Differences Between ModelArts and HiLens Model Conversion?
View PDF

What Are the Differences Between ModelArts and HiLens Model Conversion?

ModelArts supports model conversion in the following scenarios:

  • If you use the Caffe (in .caffemodel format) or TensorFlow framework (in frozen_graph or saved_model format) to train a model, you can convert the model to the .om format. The converted model can be deployed and run on Ascend chips.
  • If you use the TensorFlow framework to train a model (in frozen_graph or saved_model format), you can convert the model to the .tflite format. The converted model can be deployed and run on Arm.
  • If you use the TensorFlow framework to train a model (in frozen_graph or saved_model format), you can convert the model to the TensorRT format. The converted model can be deployed and run on the NVIDIA Tesla P4 GPU.

HiLens supports automatic model conversion in the following scenarios during model import:

  • If you use the Caffe (in .caffemodel format) or TensorFlow framework (in frozen_graph or saved_model format) to train a model, you can convert the model to the .om format. The converted model can be deployed and run on Ascend chips.

The .om templates generated using TF-FrozenGraph-To-Ascend-HiLens or TF-SavedModel-To-Ascend-HiLens can run on HiLens Kit.