Skip to main content

Array (and numpy) API for ONNX

Project description

https://dev.azure.com/xavierdupre3/onnx-array-api/_apis/build/status/sdpython.onnx-array-api https://badge.fury.io/py/onnx-array-api.svg GitHub Issues MIT License size https://img.shields.io/badge/code%20style-black-000000.svg https://codecov.io/gh/sdpython/onnx-array-api/branch/main/graph/badge.svg?token=Wb9ZGDta8J

onnx-array-api implements APIs to create custom ONNX graphs. The objective is to speed up the implementation of converter libraries. The library is released on pypi/onnx-array-api and its documentation is published at APIs to create ONNX Graphs.

Numpy API

The first one matches numpy API. It gives the user the ability to convert functions written following the numpy API to convert that function into ONNX as well as to execute it.

import numpy as np
from onnx_array_api.npx import absolute, jit_onnx
from onnx_array_api.plotting.text_plot import onnx_simple_text_plot

def l1_loss(x, y):
    return absolute(x - y).sum()


def l2_loss(x, y):
    return ((x - y) ** 2).sum()


def myloss(x, y):
    return l1_loss(x[:, 0], y[:, 0]) + l2_loss(x[:, 1], y[:, 1])


jitted_myloss = jit_onnx(myloss)

x = np.array([[0.1, 0.2], [0.3, 0.4]], dtype=np.float32)
y = np.array([[0.11, 0.22], [0.33, 0.44]], dtype=np.float32)

res = jitted_myloss(x, y)
print(res)

print(onnx_simple_text_plot(jitted_myloss.get_onnx()))
[0.042]
opset: domain='' version=18
input: name='x0' type=dtype('float32') shape=['', '']
input: name='x1' type=dtype('float32') shape=['', '']
Sub(x0, x1) -> r__0
  Abs(r__0) -> r__1
    ReduceSum(r__1, keepdims=0) -> r__2
output: name='r__2' type=dtype('float32') shape=None

It supports eager mode as well:

import numpy as np
from onnx_array_api.npx import absolute, eager_onnx


def l1_loss(x, y):
    err = absolute(x - y).sum()
    print(f"l1_loss={err.numpy()}")
    return err


def l2_loss(x, y):
    err = ((x - y) ** 2).sum()
    print(f"l2_loss={err.numpy()}")
    return err


def myloss(x, y):
    return l1_loss(x[:, 0], y[:, 0]) + l2_loss(x[:, 1], y[:, 1])


eager_myloss = eager_onnx(myloss)

x = np.array([[0.1, 0.2], [0.3, 0.4]], dtype=np.float32)
y = np.array([[0.11, 0.22], [0.33, 0.44]], dtype=np.float32)

res = eager_myloss(x, y)
print(res)
l1_loss=[0.04]
l2_loss=[0.002]
[0.042]

Light API

The second API or Light API tends to do every thing in one line. It is inspired from the Reverse Polish Notation. The euclidean distance looks like the following:

import numpy as np
from onnx_array_api.light_api import start
from onnx_array_api.plotting.text_plot import onnx_simple_text_plot

model = (
    start()
    .vin("X")
    .vin("Y")
    .bring("X", "Y")
    .Sub()
    .rename("dxy")
    .cst(np.array([2], dtype=np.int64), "two")
    .bring("dxy", "two")
    .Pow()
    .ReduceSum()
    .rename("Z")
    .vout()
    .to_onnx()
)

GraphBuilder API

Almost every converting library (converting a machine learned model to ONNX) is implementing its own graph builder and customizes it for its needs. It handles some frequent tasks such as giving names to intermediate results, loading, saving onnx models. It can be used as well to extend an existing graph.

import numpy as np
from onnx_array_api.graph_api  import GraphBuilder

g = GraphBuilder()
g.make_tensor_input("X", np.float32, (None, None))
g.make_tensor_input("Y", np.float32, (None, None))
r1 = g.make_node("Sub", ["X", "Y"])  # the name given to the output is given by the class,
                                     # it ensures the name is unique
init = g.make_initializer(np.array([2], dtype=np.int64))  # the class automatically
                                                          # converts the array to a tensor
r2 = g.make_node("Pow", [r1, init])
g.make_node("ReduceSum", [r2], outputs=["Z"])  # the output name is given because
                                               # the user wants to choose the name
g.make_tensor_output("Z", np.float32, (None, None))

onx = g.to_onnx()  # final conversion to onnx

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

onnx-array-api-0.2.0.tar.gz (207.2 kB view details)

Uploaded Source

Built Distribution

onnx_array_api-0.2.0-py3-none-any.whl (229.4 kB view details)

Uploaded Python 3

File details

Details for the file onnx-array-api-0.2.0.tar.gz.

File metadata

  • Download URL: onnx-array-api-0.2.0.tar.gz
  • Upload date:
  • Size: 207.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.8

File hashes

Hashes for onnx-array-api-0.2.0.tar.gz
Algorithm Hash digest
SHA256 93c000b9258f5ad3c233a58d0252512646588881bab1ff4b45c12a13551b7eaf
MD5 97171977826b120eba3f913a6d0c0f12
BLAKE2b-256 181cf438c3665567582fc2e3cdddfd31edcc1713143285ba5b7809269672548b

See more details on using hashes here.

Provenance

File details

Details for the file onnx_array_api-0.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for onnx_array_api-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 dc5679037c374a4a71ef3ce9ff93b5ae958ee28d06b55f07a385cd0c76a9a87a
MD5 dea1b47431adf8f538a8b2310a0e8e9a
BLAKE2b-256 f7f65342cd3d337b1b41cff09fcfefc4d52e4bf9dc873d131584ae92cf104261

See more details on using hashes here.

Provenance

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page