Extension package of TVM Deep Learning Compiler for Renesas DRP-AI accelerators powered by EdgeCortix MERA™ (DRP-AI TVM)
(C) Copyright EdgeCortix, Inc. 2022
(C) Copyright Renesas Electronics Corporation 2022
Contributors Licensed under an Apache-2.0 license.
Supported Embedded Platforms
- Renesas RZ/V2L Evaluation Board Kit (How to get)
- Renesas RZ/V2M Evaluation Board Kit (How to get)
- Renesas RZ/V2MA Evaluation Board Kit (How to get)
This compiler stack is an extension of the DRP-AI Translator to the TVM backend. CPU and DRP-AI can work together for the inference processing of the AI models.
|Sample compile script
|Sample inference application on the target board
|Setup scripts for building a TVM environment
|Pre-build runtime binaries
|Documents, i.e., Model list and API list
|Image files used in this document
|TVM repository from github
|3rd party tools
|Sample to solve specific problems, i.e., How to run validation between x86 and DRP-AI
Deploy AI models on DRP-AI
Following video shows brief tutorial for how to deploy ONNX model on RZ/V series board.
RZ/V DRP-AI TVM Tutorial - How to Run ONNX Model (YouTube)
To deploy the AI model to DRP-AI on the target board, you need to compile the model with DRP-AI TVM1 to generate Runtime Model Data (Compile).
SDK generated from RZ/V Linux Package and DRP-AI Support Package is required to compile the model.
After compiled the model, you need to copy the file to the target board (Deploy).
You also need to copy the C++ inference application and DRP-AI TVM1 Runtime Library to run the AI model inference.
Following pages show the example to compile the ResNet18 model and run it on the target board.
Please see Tutorial.
Run inference on board
Please see Application Example page.
To find more AI examples, please see How-to page.
Confirmed AI Model
If you want to know which models have been tested by Renesas, please refer to Model List.
If error occurred at compile/runtime operation, please refer error list.
How-to page includes following explanation.
- validation between x86 and DRP-AI;
If you have any questions, please contact Renesas Technical Support.