Mlprodict

==============================

* 456: Fixes python runtime for TfIdfVectorizer (2022-07-22)
* 455: Fixes division by zero in Normalizer (2022-07-21)

==============================

* 454: Fixes compilation issues on windows and python 3.10 (2022-07-20)
* 453: Uses f strings (2022-07-19)
* 452: Extends code coverage (2022-07-18)
* 451: Adds a table for all versions and all operators (2022-07-13)
* 450: Implements node Expression to compress graph (2022-07-12)
* 449: Improves code coverage (2022-07-11)
* 448: Fixes template to export an onnx graph to python (2022-07-06)
* 447: Adds an example to check export issues (2022-07-05)
* 446: Creates an exporter to python (2022-07-05)
* 445: Removes ShapeObject, replaces by OnnxShapeInference (2022-07-02)
* 444: Fixes a bug in to_onnx when as_function=True (2022-07-01)
* 443: Add compiled dynamic libraries to .gitignore (2022-06-30)
* 442: Converts onnx with functions to code based on XOP API (2022-06-30)
* 433: Converts a sklearn model into multiple functions (2022-06-29)
* 441: Renames check_model into check_onnx (2022-06-25)
* 440: Update azure-pipelines.yml (2022-06-22)
* 439: Drops support for python 3.6 (2022-06-22)
* 438: Fixes xgboost converter when base_score is specified (2022-06-22)
* 437: Renders vector attributes in onnx_simple_text_plot (2022-06-21)
* 436: Supports for attributes in onnx functions (2022-06-21)
* 435: Extends documentation to onnxruntime (2022-06-13)

==============================

* 432: None and [] should be different function get_tensor_shape (2022-05-25)
* 431: Adds functions to change the shape of inputs and outputs (2022-05-25)
* 430: Adds function to rename inputs or outputs (2022-05-23)
* 429: Adds more functions to manipulate graphs (2022-05-20)
* 428: Investigates SVC discrepancies (2022-05-20)
* 427: Adds function to inline function on onnx graph (2022-05-12)
* 426: Adds support for operator RoiAlign for python runtime (2022-04-25)
* 425: Adds support for operator GridSample for python runtime (2022-04-22)
* 424: Adds support for operator GRU in python runtime (2022-04-19)
* 423: Adds support for Momentum for python runtime (2022-04-15)
* 422: Adds support for NonMaxSuppression for python runtime (2022-04-14)
* 421: Adds support for Adagrad, Adam in python runtime (2022-04-12)
* 420: Adds support for operator Resize for python runtime (2022-04-10)
* 419: Adds support for ThresholdedRelu for python runtime (2022-04-09)
* 418: Adds support for operator OneHot, ScatterND for python runtime (2022-04-09)
* 417: C++ implementation for Im2col and Col2Im in 2D (2022-04-09)
* 416: Adds support for DepthToSpace and SpaceToDepth for python runtime (2022-04-08)
* 415: Implements experimentation im2col (used in image convolution) (2022-04-08)
* 414: Adds support for operator NonZero in python runtime (2022-04-06)
* 413: Adds support for operator Shink for python runtime (2022-04-06)
* 412: Adds support for DynamicQuantizeLinear for python runtime (2022-04-05)
* 411: Adds support for operators Unique, SoftPlus, SoftSign for python runtime (2022-04-05)
* 410: Supports operator GatherND for python runtime (2022-04-05)
* 409: Fixes bug with EyeLike in python runtime (2022-04-04)
* 408: Improves backtest coverage, update documentation (2022-04-03)
* 407: Supports operator Hardmax for python runtime (2022-03-30)
* 406: Supports operator Bernoulli for python runtime (2022-03-30)
* 405: Supports operator PRelu for python runtime (2022-03-30)
* 404: Fixes Trilu (2022-03-30)
* 403: Supports ReduceLogSum for python runtime (2022-03-30)
* 402: Supports operator Xor for python runtime (2022-03-30)
* 401: Removes parameter device, adds parameter provider (2022-03-30)
* 400: Supports local functions calling local functions for python runtime (2022-03-28)
* 399: Supports function SoftmaxCrossEntropyLoss for python runtime (2022-03-28)
* 397: Implements method f in OnnxOperatorItem (2022-03-27)
* 396: Move grammar_sklearn to subfolder. (2022-03-27)
* 395: Supports eager evaluation in XOP API (2022-03-27)
* 394: Enables expression OnnxCos[15](...) (2022-03-26)
* 393: Adds domain in function onnx_simple_text_plot (2022-03-25)
* 392: Supports random operators for python runtime (2022-03-25)
* 391: Adds support for onnx predefined functions for python runtime (2022-03-24)
* 390: Adds support for operator HardSigmoid for python runtime (2022-03-23)
* 389: Adds support for operator Selu for python runtime (2022-03-23)
* 388: Adds support for operator Trilu in python runtime (2022-03-23)
* 387: Supports operator Elu for python runtime (2022-03-23)
* 386: Supports operator BitShift for python runtime (2022-03-23)
* 384: Supports FunctionProto in XOP API. (2022-03-21)
* 383: Improves python runtime for ONNX (2022-03-19)
* 382: Adds one unit test to check lightgbm conversion with opsetml==3 (2022-03-18)
* 381: Documentation, more notebooks on FFT (2022-03-17)
* 380: Removes method get_output in xop API (2022-03-16)
* 379: Improves python runtime coverage (2022-03-14)
* 378: Adds function export2xop, exports onnx graph to XOP API (2022-03-12)

==============================

* 377: Implements TreeEnsemble* for opsetml==3 (2022-03-10)
* 376: Avoids one circular import. (2022-03-07)
* 375: Adds code to turn onnx example into python unit test (2022-03-05)
* 374: Implements onnx backend with python runtime (2022-03-05)
* 372: Improves importing time (2022-03-05)
* 373: Adds support for Expand in python runtime (2022-03-04)
* 371: Support for ONNX functions (2022-03-04)
* 370: Refactors numpy API to use Xop API (2022-03-03)
* 369: Supports recursive display in onnx_simple_text_plot (2022-02-28)
* 368: Updates requirements, skl2onnx>=1.11 (2022-02-28)
* 367: Refactors results name in Xop API (2022-02-27)
* 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)
* 363: Refactoring, moving files testing.experimental_c (2022-02-23)
* 362: Adds command line plot_onnx (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)
* 355: Fixes for onnx==1.11 (2022-02-18)
* 353: Experimentations with a new API to create ONNX graphs (2022-02-18)
* 352: Supports for shape inference on unary operators (2022-02-14)

==============================

* 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)
* 346: Adds runtime for operator CastLike (2022-02-05)
* 347: numpy API for onnx: wrapped function can call other wrapped functions (2022-02-04)
* 345: Improves command line to measure latency for a model (2022-02-03)
* 344: Adds a method to_onnx to easily retrieve the onnx graph from numpy onnx function (2022-02-03)
* 343: Shows links in onnx_simple_text_plot (2022-02-03)
* 342: Displays small arrays in onnx_simple_text_plot (2022-01-22)

==============================

* 340: Implements tokenizer following scikit-learn's API using onnxruntime-extensions (2021-12-29)
* 339: op_label_encoder support for keys_strings & values_floats (2) (replaces 335) (2021-12-29)
* 338: Updated to support key_strings and values_floats combo (2021-12-29)
* 335: op_label_encoder support for keys_strings & values_floats (2021-12-29)
* 322: Add tokenizers with onnxruntime-extensions (2021-12-29)
* 337: Supports operator Scan when exporting an onnx graph to onnx code (2021-12-21)
* 336: Enables GPU with OnnxInference and onnxruntime (2021-12-21)