Skip to content
This repository has been archived by the owner on Jan 13, 2024. It is now read-only.

Commit

Permalink
documentation
Browse files Browse the repository at this point in the history
  • Loading branch information
sdpython committed Feb 24, 2022
1 parent 492871b commit d4b0c86
Show file tree
Hide file tree
Showing 4 changed files with 22 additions and 8 deletions.
24 changes: 19 additions & 5 deletions HISTORY.rst
Expand Up @@ -5,9 +5,27 @@
History
=======

current - 2022-02-11 - 0.00Mb
current - 2022-02-24 - 0.00Mb
=============================

* #366: Adds python runtime for CategoryMapper (2022-02-24)
* #365: Adds command line benchmark_doc (2022-02-24)
* #364: Runs onnx backend test with python runtime (2022-02-23)
* #362: Adds command line plot_onnx (2022-02-23)
* #363: Refactoring, moving files testing.experimental_c (2022-02-23)
* #361: Introduces __max_supported_opset__ and refactors the library (2022-02-23)
* #360: Xop API, adds class OnnxSubOnnx to insert ONNX graph (2022-02-22)
* #359: Supports domains in Xop API (2022-02-21)
* #358: Extends supported operator by OnnxShapeInference (2022-02-21)
* #357: Modifies OnnxShapeInference to deal with untyped outputs (2022-02-19)
* #356: Supports multiple affectations (xop) (2022-02-18)
* #353: Experimentations with a new API to create ONNX graphs (2022-02-18)
* #355: Fixes for onnx==1.11 (2022-02-18)
* #352: Supports for shape inference on unary operators (2022-02-14)

0.8.1697 - 2022-02-11 - 1.97Mb
==============================

* #351: Adds name in ShapeResult, fixes zoo links (2022-02-11)
* #350: First version of runtime OnnxShapeInference (2022-02-09)
* #348: Moves OnnxMicroRuntime to onnxrt (2022-02-05)
Expand Down Expand Up @@ -323,10 +341,6 @@ current - 2022-02-11 - 0.00Mb
* #104: Enable / disable parallelisation in topk (2020-02-23)
* #103: Implements plot benchmark ratio depending on two parameters (2020-02-22)
* #102: Fix conversion for xgboost 1.0 (2020-02-21)

0.3.975 - 2020-02-19 - 0.28Mb
=============================

* #100: add notebook on TreeEnsemble (2020-02-19)
* #99: Fixes #93, use same code for TreeEnsembleClassifier and TreeEnsembleRegression (2020-02-19)
* #93: Use pointer for TreeClassifier (2020-02-19)
Expand Down
2 changes: 1 addition & 1 deletion _doc/sphinxdoc/source/_exts/generate_automated_pages.py
Expand Up @@ -78,7 +78,7 @@ def write_page_onnxrt_benches(app, runtime, skip=None, white_list=None):

logger.info("[mlprodict] shape '{}'.".format(piv.shape))
print("[mlprodict-sphinx] shape '{}'".format(piv.shape))

def make_link(row):
link = ":ref:`{name} <l-{name}-{problem}-{scenario}-{optim}-{opset}>`"
name = row['name']
Expand Down
2 changes: 1 addition & 1 deletion bin/run_bench_documentation.sh
Expand Up @@ -4,4 +4,4 @@ python -m mlprodict benchmark_doc --verbose=1 --out_raw=bench_python_compiled.xs

echo --ONNXRUNTIME--
mkdir bench_onnxruntime1
python -m mlprodict benchmark_doc --verbose=1 --out_raw=bench_onnxruntime1.xslx --out_summary=bench_sum_onnxruntime1.xlsx --dump_dir=./bench_onnxruntime1 --runtime=onnxruntime1
python -m mlprodict benchmark_doc --verbose=1 --out_raw=bench_onnxruntime1.xslx --out_summary=bench_sum_onnxruntime1.xlsx --dump_dir=./bench_onnxruntime1 --runtime=onnxruntime1
2 changes: 1 addition & 1 deletion mlprodict/__init__.py
Expand Up @@ -5,7 +5,7 @@
converting investigate issues with ONNX models.
"""

__version__ = "0.8.1697"
__version__ = "0.8.1727"
__author__ = "Xavier Dupré"
__max_supported_opset__ = 15 # Converters are tested up to this version.
__max_supported_opsets__ = {
Expand Down

0 comments on commit d4b0c86

Please sign in to comment.