ONNC-bench is a Python wrapper of ONNC
Project description
ONNC-bench
ONNC-bench is a Python wrapper of ONNC
Installation
Using pip
pip install onnc-bench
Python API Example
Here is an example to show how to use ONNC python API
from onnc.bench import login, Project
# Setup your ONNC API key
api_key = "Your API KEY"
login(api_key)
# Instantiate a projct
project = Project('experiment-1')
# Add a model and its coresponding calibration samples
project.add_model('path/to/model', 'path/to/samples')
# Compile the model and optmize to `CMSIS-NN` backend
project.compile(target='CMSIS-NN-DEFAULT')
# Save the compiled model
deployment = project.save('./output')
print(deployment.report)
{
'sram_size': 2490,
'flash_size': 101970
}
The report shows we need: 2,490 bytes of SRAM 101,970 bytes of ROM to run this model on a CortexM device.
Please Check https://docs-tinyonnc.skymizer.com/index.html for the full documents.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
onnc-bench-4.1.4.tar.gz
(35.4 kB
view hashes)
Built Distribution
onnc_bench-4.1.4-py3-none-any.whl
(51.7 kB
view hashes)
Close
Hashes for onnc_bench-4.1.4-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 11012d41f69a1490cfea5839ba3e17ec24eb56e924986595b67a77bde139e9c3 |
|
MD5 | 873196d7b7748acf735ac0b311b7a837 |
|
BLAKE2b-256 | 2f9bc83453c1443876f3d513785b4a0e1f227229a643f9a982774412384db4ee |