GitHub / sdpython / onnx-array-api
Array APIs to write ONNX Graphs
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sdpython%2Fonnx-array-api
PURL: pkg:github/sdpython/onnx-array-api
Stars: 11
Forks: 0
Open issues: 1
License: mit
Language: Python
Size: 1.54 MB
Dependencies parsed at: Pending
Created at: over 2 years ago
Updated at: 4 months ago
Pushed at: 30 days ago
Last synced at: 29 days ago
Topics: array-api, machine-learning, numpy, onnx
0.2.0
0.2.0
- #77: supports ConcatOfShape and Slice with the light API
- #76, #79: add a mode to compare models without execution
- #75: add QuickGelu to ExtendedReferenceEvaluator
- #71: adds tools to compare two onnx graphs
- #61: adds function to plot onnx model as graphs
- #60: supports translation of local functions
- #59: add methods to update nodes in GraphAPI
Download
0.1.3
0.1.3
- #49: adds command line to export a model into code
- #48: support for subgraph in light API
- #47: extends export onnx to code to support inner API
- #46: adds an export to convert an onnx graph into light API code
- #45: fixes light API for operators with two outputs
Download
0.1.2
0.1.2
- #42: first sketch for a very simple API to create onnx graph in one or two lines
- #27: add function from_array_extended to convert
an array to a TensorProto, including bfloat16 and float 8 types - #24: add ExtendedReferenceEvaluator to support scenario
for the Array API onnx does not support - #22: support OrtValue in function ort_profile
- #17: implements ArrayAPI
- #3: fixes Array API with onnxruntime and scikit-learn
Download