This repository was archived by the owner on Jan 13, 2024. It is now read-only.
Releases: sdpython/mlprodict
Releases · sdpython/mlprodict
0.8
- #322: Add tokenizers with onnxruntime-extensions (2021-12-29)
- #340: Implements tokenizer following scikit-learn's API using onnxruntime-extensions (2021-12-29)
- #335: op_label_encoder support for keys_strings & values_floats (2021-12-29)
- #338: Updated to support key_strings and values_floats combo (2021-12-29)
- #339: op_label_encoder support for keys_strings & values_floats (2) (replaces #335) (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)
- #334: update history (2021-12-19)
- #333: Adds command line latency to measure the latency of a runtime (2021-12-18)
- #332: Improves dot rendering, fixes disconnected subgraphs (2021-12-18)
- #331: Removes measure_time (2021-12-15)
- #330: Reduces verbosity when onnxruntime is used as a runtime for OnnxInference (2021-12-14)
- #329: Fixes type issue in shape inference for operator If (2021-12-14)
- #328: Extends command line onnx_stats (2021-12-14)
- #327: Adds runtime for operator LeakyRelu (2021-12-13)
- #326: Better error messages when name is shared with results and node name in onnx_simple_text_plot (2021-12-10)
- #325: Implements a simple text display for ONNX graph (2021-12-08)
- #324: Adds runtime for gradient operators YieldOp, BroadcastGradientArgs (2021-11-30)
- #323: Implements if with numpy API (2021-11-26)
- #320: Fix exporter to tf2onnx (2021-11-13)
- #319: Supports operator SequenceAt in OnnxInference (2021-11-09)
- #318: Disable onnxruntime optimisation on one particular graph (2021-11-04)
- #317: plot_onnx fails when node names contains '.' (2021-10-28)
- #316: failed to use RandomForestRegressor ort in android studio (2021-10-28)
- #315: Fixes import issue for python 3.6 (2021-10-21)
- #314: Builds mlprodict for python 3.6 on linux (2021-10-11)
- #313: Fix a bug related to shapes when exporting a model to tf2onnx (2021-10-10)
- #312: Add more tests for einsum decomposition (2021-10-08)
- #311: Support opset 15 (onnx>=1.10) (2021-10-02)
- #310: Raise an exception when inplace and intermediate are True (OnnxInference.run) (2021-09-23)
0.7
- #309: Adds function insert_results_into_onnx to insert results into a graph to debug (2021-09-21)
- #308: Adds function to rename all results in ONNX graphs (2021-09-13)
- #307: Adds runtime for operator SequenceConstruct (2021-09-13)
- #305: Add option to split lightgbm converter into multipule TreeEnsemble (2021-09-10)
- #304: Add tree text visualization for TreeEnsemble (2021-09-01)
- #303: Implements a estimator speeding up the inference using ONNX (2021-08-31)
- #302: Removes unused nodes after changing the outputs. (2021-08-23)
- #298: Remove unused nodes after changing the outputs (2021-08-23)
- #301: Different build for manylinux on python 3.9 (2021-08-18)
- #300: Improves Lightgbm converter design + fix wrong prediction for TreeEnsemble with non contiguous arrays (2021-08-18)
- #297: Adds function to convert ONNX into numpy code. (2021-08-13)
- #296: Lightgbm + add function matmul to numpy API for ONNX (2021-08-07)
- #295: Implements runtime for operator FFT (2021-08-03)
- #291: Fixes infinite loop with operator loop, add support for static variables in Loop (2021-07-31)
- #294: Implements text representation of an ONNX graph (bigraph) (2021-07-30)
- #293: Add a tool to display an ONNX graph into text format (2021-07-30)
- #292: Adds operator AveragePool to the python runtime (2021-07-29)
- #290: Increases code coverage, add infer_size for Loop runtime (2021-07-28)
- #289: Avoids raising an exception when an optional parameter is not specified (2021-07-26)
- #288: Extends code coverage (2021-07-25)
- #287: Adds python runtime for operator Loop, SequenceInsert, ConcatFromSequence (2021-07-25)
- #286: Adds runtime for operator Range (2021-07-13)
0.6
- #285: Adds function cst to create constant with numpy API for ONNX (2021-07-12)
- #283: Commutative property (2021-07-12)
- #281: Infers temporary allocation needed while computing the outputs (2021-07-12)
- #284: Adds function transpose to numpy API for ONNX (2021-07-10)
- #282: Upgrade requirements to skl2onnx>=1.9.0 (2021-07-02)
- #280: More robustness for the python runtime (2021-07-01)
- #279: Implements method infer_types in OnnxInference (2021-06-28)
- #278: Adds operators ReduceSum, Max to OnnxMicroRuntime (2021-06-27)
- #277: Switch to python 3.9 in CI (2021-06-25)
- #276: Use openmp to parallelize QLinearConv (2021-06-25)
- #275: Adds new strategy to pick up the best einsum equation based on ML (2021-06-25)
- #274: Fixes issue raised with scipy 1.7.0 (2021-06-22)
- #273: Adds operator where, improves numpy api (x[x<0]= 2) (2021-06-18)
- #272: Explore custom implementation of operator add (2021-06-18)
- #271: Updates default opset from 13 to 14 (2021-06-17)
- #270: Adds more tests for QLinearConv runtime (2021-06-16)
- #269: Adds runtime for operator QLinearConv (2021-06-04)
- #268: Adds function to prepare data for onnxruntime_perf_test (2021-05-17)
- #267: Moves onnxruntime code inside a wrapper to reduce logs (2021-05-14)
- #266: Optimizes einsum even if not decomposed (2021-05-13)
- #265: Refactoring, moves files to onnx_tools (2021-05-12)
- #264: Support SessionOptions for runtime onnxruntime2 (2021-05-12)
- #263: Refactor einsum files (2021-05-06)
- #262: Refactoring, moving files into onnx_tools (2021-05-06)
- #261: Improves einsum decomposition by using gemm and removing a transpose (2021-05-05)
- #260: New command line to benchmark einsum decomposition (2021-05-03)
- #259: Minor changes to Einsum decomposition (2021-05-02)
- #258: Decomposes Einsum into simple matrix operations (2021-04-30)
- #257: Fixes #256, add method to validate input data in numpy API for ONNX (2021-04-20)
- #256: Add virtual method to validate input before predictions in numpy API for ONNX (2021-04-20)