The Vivante ACUITY Toolkit offers both command line tools and APIs, enabling seamless deployment of machine learning neural network models onto devices with a neural processing unit (NPU). This toolkit facilitates the translation of model formats, network optimization, model training, quantization, and inference, until
final integrations with devices.
...
To ensure seamless deployment of neural network models on SP7350 platformsedge devices, select compatible versions of the ACUITY Toolkit, Vivante IDE, and Linux NPU driver as listed below:
Linux NPU Driver | Vivante ACUITY Toolkit | Vivante IDE |
v6.4.13.8 | 6.18.1 | 5.7.2 |
v6.4.15.9 | 6.21.1 | 5.8.2 |
v6.4.18.5 | 6.30.07 | 5.10.1 |
3. Installing ACUITY Binary Version
...
Extract the ACUITY package 'Verisilicon_Tool_Acuity_Toolkit_<version>.tgz' to your desired destination directory.
From this directory, locate and unpack the binary package 'Vivante_acuity-_toolkit-_binary-_<version>.tgz'. Once unpacking is complete, the installation process is finished.
...
Extract the ACUITY package, ‘Verisilicon_Tool_Acuity_Toolkit_<version>.tgz’, to a destination directory.
From this directory, locate and unpack the ACUITY Wheel package ‘acuity-toolkit-whl-<version>’ ‘Vivante_acuity_toolkit_whl_<version>_python<version>’.
From the './acuity-toolkit-whl-<version>/bin' directory, select and install a Wheel package with the following commands:
Code Block pip3 install ./acuity-*.whl
...
| Code Block |
|---|
pip3 install tensorflow==2.12.0 pip3 install scipy pip3 install networkx>=1.11 pip3 install lmdb==0.93 pip3 install protobuf<=3.20.3 pip3 install onnxoptimizer==0.3.13 pip3 install onnx==1.14.0 pip3 install dill==0.2.8.2 pip3 install ruamel.yaml==0.15.81 pip3 install ply==3.11 pip3 install torch==1.5.1 |
4.2.3 ACUITY Toolkit 6.30.
...
7
| Code Block |
|---|
pip3 install tensorflow==2.15.0 pip3 install scipy pip3 install networkx>=1.11 pip3 install lmdb==0.93 pip3 install protobuf<=3.20.3 pip3 install onnxoptimizer==0.3.13 pip3 install onnx==1.14.0 pip3 install dill==0.2.8.2 pip3 install ruamel.yaml==0.15.81 pip3 install ply==3.11 pip3 install torch==1.5.1 |
...