WinMLTools provide following tools for Windows ML:
Model Conversion
WinMLTools enables you to convert models from different machine learning toolkits into ONNX for use with Windows ML. Currently the following toolkits are supported:
apple CoreML
keras
scikit-learn
lightgbm
xgboost
libSVM
tensorflow (experimental)
Here is a simple example to convert a Core ML model:
from coremltools.models.utils import load_spec
from winmltools import convert_coreml
model_coreml = load_spec('example.mlmodel')
model_onnx = convert_coreml(model_coreml, 10, name='ExampleModel')
Post Training Weight Quantization
WinMLTools provides quantization tool to reduce the memory footprint of the model.
Here is an example to convert an ONNX model to a quantized ONNX model:
import winmltools
model = winmltools.load_model('model.onnx')
quantized_model = winmltools.quantize(model, per_channel=True, nbits=8, use_dequantize_linear=True)
winmltools.save_model(quantized_model, 'quantized.onnx')
Dependencies
In order to convert from different toolkits, you may have to install the following packages for different converters:
Toolkit |
Source |
|---|---|
keras |
|
tensorflow |
|
scikit-learn |
|
lightgbm |
|
xgboost |
|
libsvm |
You can download libsvm wheel from various web sources. One example can be found here: https://www.lfd.uci.edu/~gohlke/pythonlibs/#libsvm |
coremltools |
Currenlty coreml does not distribute coreml packaging on windows. You can install from source: pip install git+https://github.com/apple/coremltools |
For more information on WinMLTools, you can go to Convert ML models to ONNX with WinMLTools
License
MIT License
5 maintainers
Release files for winmltools 1.5.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| winmltools-1.5.1.tar.gz | 26.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| winmltools-1.5.1-py2.py3-none-any.whl | Python 3, Python 2 | none | any | Details |
Total release size: 67.6 kB
Release files / winmltools-1.5.1.tar.gz
| Download URL | winmltools-1.5.1.tar.gz |
|---|---|
| Size | 26.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
99fce78536866b235715d0489ddbae6df714f8beeae6bb54cae231fbd5e708f1
|
|
BLAKE2b-256 checksum How to use checksums |
8f16aa6d07bb7b873659dbe950194895c7253fa74c86b872ee3bb80c3dc7f547
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/1.15.0 pkginfo/1.5.0.1 requests/2.18.4 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.36.0 CPython/3.6.9
|
Release files / winmltools-1.5.1-py2.py3-none-any.whl
| Download URL | winmltools-1.5.1-py2.py3-none-any.whl |
|---|---|
| Size | 40.7 kB |
| Tags | Python 2 Python 3 |
|
SHA-256 checksum How to use checksums |
af343551272c305151b0f22b2f7d4fa4056b94bc02ebd2afdd378ee9f92e5d63
|
|
BLAKE2b-256 checksum How to use checksums |
b7fccbf8213110fdff2fec65ebef9069e927cd2bd737458db67c435fc2a1f96f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/1.15.0 pkginfo/1.5.0.1 requests/2.18.4 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.36.0 CPython/3.6.9
|
