Python Runtime for ONNX models, other helpers to convert machine learned models in C++.
Project description
mlprodict
mlprodict was initially started to help implementing converters to ONNX. The main features is a python runtime for ONNX (class OnnxInference), visualization tools (see Visualization), and a numpy API for ONNX). The package also provides tools to compare predictions, to benchmark models converted with sklearn-onnx.
import numpy
from sklearn.linear_model import LinearRegression
from sklearn.datasets import load_iris
from mlprodict.onnxrt import OnnxInference
from mlprodict.onnxrt.validate.validate_difference import measure_relative_difference
from mlprodict import __max_supported_opset__, get_ir_version
iris = load_iris()
X = iris.data[:, :2]
y = iris.target
lr = LinearRegression()
lr.fit(X, y)
# Predictions with scikit-learn.
expected = lr.predict(X[:5])
print(expected)
# Conversion into ONNX.
from mlprodict.onnx_conv import to_onnx
model_onnx = to_onnx(lr, X.astype(numpy.float32),
black_op={'LinearRegressor'},
target_opset=__max_supported_opset__)
print("ONNX:", str(model_onnx)[:200] + "\n...")
# Predictions with onnxruntime
model_onnx.ir_version = get_ir_version(__max_supported_opset__)
oinf = OnnxInference(model_onnx, runtime='onnxruntime1')
ypred = oinf.run({'X': X[:5].astype(numpy.float32)})
print("ONNX output:", ypred)
# Measuring the maximum difference.
print("max abs diff:", measure_relative_difference(expected, ypred['variable']))
# And the python runtime
oinf = OnnxInference(model_onnx, runtime='python')
ypred = oinf.run({'X': X[:5].astype(numpy.float32)},
verbose=1, fLOG=print)
print("ONNX output:", ypred)
Installation
Installation from pip should work unless you need the latest development features.
pip install mlprodict
The package includes a runtime for ONNX. That’s why there is a limited number of dependencies. However, some features relies on sklearn-onnx, onnxruntime, scikit-learn. They can be installed with the following instructions:
pip install mlprodict[all]
The code is available at GitHub/mlprodict and has online documentation.
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
mlprodict-0.9.1883.tar.gz
(814.9 kB
view hashes)
Built Distributions
Close
Hashes for mlprodict-0.9.1883-cp310-cp310-win_amd64.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | a39323222595cb9f7ce16d167febd670e41be5c26ac334e475978266c3b494e6 |
|
| MD5 | 1844ae3e8d826046d6785c24d8cc34bf |
|
| BLAKE2b-256 | 8c05ca4996e5cd1aa11af640f2d29b3ae40d1a0deaa5a42bde4329daeaa97940 |
Close
Hashes for mlprodict-0.9.1883-cp310-cp310-manylinux_2_24_x86_64.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 9460033d0331aaefe79d19e45aa5ef04663ad2d89a3edcf674b64c8087c07101 |
|
| MD5 | de7c6bcc2371f8e744c90cb2e089bba0 |
|
| BLAKE2b-256 | 6fcf97957338b23f937d337e1b8ec9047aa19987257a1c9889ebe640e2fad5a4 |
Close
Hashes for mlprodict-0.9.1883-cp310-cp310-macosx_10_13_x86_64.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 3ca38c90d5f0ddf7715ec171074a5ed13265d1a70df69f718996b4824243b6af |
|
| MD5 | 2561723606cd7f9e9ee99ca47f70360f |
|
| BLAKE2b-256 | 54f91b152e47b910991107edbfdf7d14270d518883f18f9748d7cd1251fa2e10 |
Close
Hashes for mlprodict-0.9.1883-cp39-cp39-win_amd64.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 15465beed3fb1504a03d15986cff2c962d30fede0c6a04b248d24d4c32ac728a |
|
| MD5 | 7117d88104d192ac3758faf71ee5e47e |
|
| BLAKE2b-256 | 90076ce9f5f6579c56cfa827ff155d8600d62a9d7d93367555592c799d234a45 |
Close
Hashes for mlprodict-0.9.1883-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 6a97172bddfb16467992d17bc673f0ed8e11b626e5ed711fdfb4a99c5e07196c |
|
| MD5 | 78b76a8ff35823004b892ebeb4452732 |
|
| BLAKE2b-256 | 76c4231e76b59c9d0252e990afc710e8c919f7ec3bce38677b3bb72c14b31853 |
Close
Hashes for mlprodict-0.9.1883-cp39-cp39-macosx_10_13_x86_64.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 6a2843aabf25433967fa80bae244dc6eff3a42a7e947d03c47fdb93ac215fef8 |
|
| MD5 | 802bc7f502bd776cf35de05560b23838 |
|
| BLAKE2b-256 | 05ac6d9ffe86930951d3418604fd97b05dc4afa02a07e1a0ee387dca8b3258ae |
Close
Hashes for mlprodict-0.9.1883-cp38-cp38-win_amd64.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | fda5699f053b6014470b4bc645949a4fa6bb8246bbfdb090a50390efbcc421f0 |
|
| MD5 | 3f442562588b96fedcbd26640b83447b |
|
| BLAKE2b-256 | ccbcb2ca328e32f8098cddb69c8c99033ceff538b695ca5fed4914182c3138d4 |
Close
Hashes for mlprodict-0.9.1883-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 2d4ab90f145174ac71a556466ae374c0e51145957f71ede2fa78119696934774 |
|
| MD5 | 1db1ea036054dfaf92d3542b5b7808b5 |
|
| BLAKE2b-256 | 1e3c53a12d2942e6821231503d571cf3b67d72d239d858b0b987af17a0d716ae |
Close
Hashes for mlprodict-0.9.1883-cp38-cp38-macosx_10_13_x86_64.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 3d0f71d940a622960e528e4be6d6bd4eea901d0bfc0e5a81c90de5310e2e64a3 |
|
| MD5 | 595dc7d058377dbe6109ed6a34d7cba4 |
|
| BLAKE2b-256 | 7898f012e83f9f028f2f06bcb10724bc6415049e9660cf6c62da9fa345ef5b19 |
Close
Hashes for mlprodict-0.9.1883-cp37-cp37m-win_amd64.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | a6e4945379e5378532c35d9054538655407f081838b2c11158f73bcc5f10d65d |
|
| MD5 | 4b55af772ae08d9c8674908258176144 |
|
| BLAKE2b-256 | 97a6e83adbcd805fe583dfcdf4557f5b6a3ca3b3459fe22293aad21b3e6ebc2c |
Close
Hashes for mlprodict-0.9.1883-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 215c9a413fa9b24e66b6274daa4395f5d2713a7f7b718641e13abe908b42101c |
|
| MD5 | a1750a30f35fb9dbca0689c2b88a8a85 |
|
| BLAKE2b-256 | 9b5db36f8b0543089319fd82a0b4ff91e3206862b25c9b7dfcb57130f34030b8 |
