Huawei uses machine translation combined with human proofreading to translate this document to different languages in order to help you better understand the content of this document.
Note: Even the most advanced machine translation cannot match the quality of professional translators.
Huawei shall not bear any responsibility for translation accuracy and it is recommended that you refer to the English document (a link for which has been provided).
Introduction
Overview
You can use the open Ascend Graph APIs to construct offline models to implement offline inference on the Ascend AI Processor in either of the following ways:
- Construct a graph from operator prototypes and build it into an offline model. In this way, you can build graphs on Caffe, TensorFlow, or more other frameworks.
- Parse a source model into a graph and build it into an offline model. In this way, you can only build graphs on Caffe or TensorFlow.
Graph Structure
TensorFlow and ONNX define networks in similar formats. A network model consists of tensors, nodes (or operators), and a graph.
- A tensor involves the tensor description and tensor data. Tensor description describes the name, dtype, shape, and format of the tensor.
- An operator involves its name, type, input, and attributes.
- A graph consists of the network name, operator list, and input and output operators.
Model Construction Flow
Figure 1-1 shows the graph construction and build flow using Ascend Graph API.
