Functions#
Summary#
function |
class parent |
truncated documentation |
---|---|---|
Dynamically creates a class for a specific operator. |
||
Adds operator ReduceL2 for float or double. |
||
Adds operator ReduceSum with opset>=13 following API from opset 12. |
||
Adds operator Reshape with opset>=14 following API from opset 13. |
||
Adds operator Split with opset>=13 following API from opset 11. |
||
Adds operator Squeeze with opset>=13 following API from opset 11. |
||
Adds operator Unsqueeze with opset>=13 following API from opset 11. |
||
Adds additional imports for experimental models. |
||
Extract information from a tree. |
||
Extract information from a tree in a HistGradientBoosting. |
||
Decomposes the generic matrix multiplication into numpy operations depending on the operator to use for matrix multiplication … |
||
Applies an optimisation function fct on a graph and not on the model. |
||
Applies an optimizing function on a subgraphs. |
||
Puts output dimension in the expected order. |
||
Put all dimensions in the same order. |
||
Implementation of operator ArrayFeatureExtractor with numpy. |
||
Private. |
||
Comments out all lines containing |
||
Common verifications for all implementations of |
||
Compares the expected output against the runtime outputs. This is specific to onnxruntime or mlprodict. … |
||
Modified version of softmaxcrossentropy.py … |
||
Default converter for a classifier with one input and two outputs, label and probabilities of the same input type. … |
||
Default converter for a clustering with one input and two outputs, label and distances of the same input type. It … |
||
Default converter for a regressor with one input and one output of the same type. It assumes instance operator … |
||
Default converter for a transformer with one input and one output of the same type. It assumes instance operator … |
||
Creates a benchmark file based in the information received through the argument. It uses one of the templates like … |
||
Creates a column from values with dtype |
||
Custom parser for XGBClassifier and LGBMClassifier. |
||
Applies strategy simple, numpy defined in by function |
||
Returns the default mapping between opset and ir_version. |
||
Converts domain into a name. |
||
Automatically generates classes for each of the operators module onnx defines and described at Operators … |
||
Infers shape for an element wise operator. The function returns but updates known_shapes. |
||
Infers shape for an element wise operator. The function returns but updates known_shapes. |
||
Loops over all possible models and fills a folder with benchmarks following asv concepts. |
||
Extracts the classes of a file. |
||
Extracts the name of the fitted models and the data used to train it. |
||
Converts the data from list to dictionaries. |
||
Determines the domain of an operator. Raises an exception if not found or if there is an ambiguity. |
||
Fixes a node for old versionsof skl2onnx. |
||
Formats a dictionary as code. |
||
Get informations from and lightgbm trees. |
||
Get informations from and lightgbm trees. |
||
Returns the list of functions defined in ONNX package. |
||
Converts an attribute into a C++ value. |
||
Returns created, location_model, prefix_import. |
||
Hash the content of an object. |
||
Splits a using split, insert HTML differences between pieces. The function relies on package pyquickhelper. … |
||
Same function as |
||
Constructs a NodeProto. |
||
Measures the execution time for a function. |
||
Measures a statement and returns the results as a dictionary. |
||
Extracts the main component of a model, removes suffixes such |
||
Modifies the number of features to increase or reduce the number of features. |
||
Multiplies values in time_kwargs following strategy time_kwargs_fact for a given model inst. |
||
Single function to create an array. |
||
Subpart of @see fn numpy_dot_inplace. |
||
Subpart of @see fn numpy_dot_inplace. |
||
Returns the equation equivalent to an extended version of an aligned matrix multiplication (see |
||
Defines op_type and op_domain based on dtype. |
||
Defines op_type and op_domain based on dtype. |
||
Defines op_type and op_domain based on dtype. |
||
Defines op_type and op_domain based on dtype. |
||
Parses nodes. |
||
The pool of all nodes’ indexes created when parsing a single tree. Different tree use different pools. |
||
Populates all schemas. |
||
Applies post processings before running the comparison such as changing type from list to arrays. |
||
Retrieves one template. |
||
Returns X, y, intial_types, method, name, X runtime for a scoring problem. It is based on Iris dataset. |
||
Returns X, y, intial_types, method, name, X runtime for a scoring problem. Binary classification. It is based … |
||
Returns X, y, intial_types, method, name, X runtime for a scoring problem. It is based on Iris dataset. |
||
Returns X, y, intial_types, method, name, X runtime for a scoring problem. Binary classification. It is based … |
||
Returns X, intial_types, method, name, X runtime for a clustering problem. It is based on Iris dataset. |
||
Returns X, intial_types, method, name, X runtime for a clustering problem, the score part, not the cluster. It … |
||
Returns a problem for the sklearn.feature_extraction.DictVectorizer. |
||
Returns a problem for the sklearn.feature_extraction.DictVectorizer. |
||
Returns a problem for the sklearn.preprocessing.LabelEncoder. |
||
Returns X, y, intial_types, method, node name, X runtime for a m-cl classification problem. It is based on Iris … |
||
Returns X, y, intial_types, method, name, X runtime for a scoring problem. It is based on Iris dataset. |
||
Returns X, intial_types, method, name, X runtime for a transformation problem. It is based on Iris dataset. |
||
Returns X, intial_types, method, name, X runtime for a transformation problem. It is based on Iris dataset. |
||
Returns X, intial_types, method, name, X runtime for a transformation problem. It is based on Iris dataset. |
||
Returns X, intial_types, method, name, X runtime for a transformation problem. It is based on Iris dataset. |
||
Returns a problem for the sklearn.preprocessing.OneHotEncoder. |
||
Returns X, intial_types, method, name, X runtime for a transformation problem. It is based on Iris dataset. |
||
Returns X, y, intial_types, method, node name, X runtime for a binary classification problem. It is based on Iris … |
||
Returns X, y, intial_types, method, node name, X runtime for a m-cl classification problem. It is based on Iris … |
||
Returns X, y, intial_types, method, node name, X runtime for a m-cl classification problem. It is based on Iris … |
||
Returns X, y, intial_types, method, name, X runtime for a mregression problem. It is based on Iris dataset. |
||
Returns X, y, intial_types, method, name, X runtime for a regression problem. It is based on Iris dataset. |
||
Returns a problem for the :epkg:`sklearn:feature_extraction:text:TfidfTransformer`. |
||
Returns a problem for the :epkg:`sklearn:feature_extraction:text:TfidfVectorizer`. |
||
Reads the testing pattern. |
||
Produces agregates features. |
||
This functions registers additional converters for lightgbm. |
||
This functions registers additional converters for mlinsights. |
||
This functions registers additional converters for skl2onnx. |
||
This functions registers additional converters for xgboost. |
||
Renames an input and adds an Identity node to connect the dots. |
||
Renames an output and adds an Identity node to connect the dots. |
||
Renames an input from a node. |
||
Renames an output from a node. |
||
Imports files in bdir, compile files and extra metadata from them. |
||
Use by |
||
Selects a benchmark type based on the problem kind. |
||
Default shape calculator for a classifier with one input and two outputs, label (int64) and probabilites of the same … |
||
Default shape calculator for a clustering with one input and two outputs, label (int64) and distances of the same type. … |
||
Default shape calculator for a regressor with one input and one output of the same type. |
||
Default shape calculator for a transformer with one input and one output of the same type. |
||
Adds ONNX graph to skl2onnx container and scope. |
||
Returns the list of subfolders for a model. |
||
Single function to create an sparse array (coo_matrix). |
||
Splits the attributes of a TreeEnsembleRegressor into multiple trees in order to do the summation in double instead … |
||
Tries onnx conversion. |
||
Converts a type into a readable string. |
||
Dynamically updates the module with operators defined by ONNX. |
||
Converts a protobuf object into something readable. The current implementation relies on json. That’s not … |
||
See |
||
See |
||
See |
||
Modifies a template such as |
||
Adds a whole ONNX graph to an existing one following skl2onnx API assuming this ONNX graph implements an … |
||
See |
||
See |
||
Analyses an einsum equation. |
||
Returns informations, statistics about a model, its number of nodes, its size… |
||
Annotates a heatmap. See |
||
Applies a sequence of operations on a list of inputs. The sequence of operations is produced by function |
||
See |
||
See |
||
Needed or operator ArgMax. |
||
See |
||
Needed or operator ArgMin. |
||
Implementation of operator ArrayFeatureExtractor with numpy. |
||
See |
||
See |
||
Compares two arrays knowing they contain strings. Raises an exception if the test fails. |
||
Computes ranges for every number in an array once converted into float32. The function returns two matrices which … |
||
Creates an asv benchmark in a folder but does not run it. |
||
See |
||
See |
||
Runs the benchmark published into the documentation (see Availability of scikit-learn model for runtime onnxruntime1 and Availability of scikit-learn model for runtime python_compiled). … |
||
Benchmarks a function which takes an array as an input and changes the number of rows. |
||
The command rerun a benchmark if models were stored by command line vaidate_runtime. |
||
Used to compare decision path. |
||
Defines parameters values for some operators. |
||
Defines parameters values for some operators. |
||
Used for documentation. |
||
Returns this folder. |
||
Shape calculator for LightGBM Booster (see lightgbm). |
||
See |
||
Some models are converted under the assumption batch prediction is not necessary. This function changes the first … |
||
Switches from AaBb into aa_bb. |
||
Switches from AaBb into aa_bb. |
||
Checks the library is working. It raises an exception. If you want to disable the logs: |
||
Checks that two floats or two arrays are almost equal. |
||
Checks that a trained model can be exported in a specific list of formats and produces the same outputs if the representation … |
||
Raises an exception if the model is not of the expected type. |
||
Returns any classifier from scikit-learn converted into ONNX assuming a converter is registered with sklearn-onnx. … |
||
Removes EOL from error messages in dataframes. |
||
See |
||
Returns any cluster from scikit-learn converted into ONNX assuming a converter is registered with sklearn-onnx. … |
||
|
||
The function compares the expected output (computed with the model before being converted to ONNX) and the ONNX output. … |
||
Compares expected values and output. Returns None if no error, an exception message otherwise. |
||
The function compares the expected output (computed with the model before being converted to ONNX) and the ONNX output … |
||
The function compares the expected output (computed with the model before being converted to ONNX) and the ONNX output … |
||
The function compares the expected output (computed with the model before being converted to ONNX) and the ONNX output … |
||
Compiles a C function with cffi. It takes one features vector. |
||
Writes page Python Runtime for ONNX operators. |
||
See |
||
Compares the processing time several functions. |
||
Given a shape and a permutation, computes many features used to predict the cost of the transposition. |
||
Operator concat, handle |
||
This converters reuses the code from LightGbm.py … |
||
Runs the appropriate conversion method. |
||
Converts function |
||
Converts a scorer into ONNX assuming there exists a converter associated to it. The function wraps the function … |
||
Converters for TransferTransformer. |
||
Converts a model stored in pkl file and measure the differences between the model and the ONNX predictions. |
||
This converters reuses the code from XGBoost.py … |
||
Converter for operator LightGBMConcat. |
||
See |
||
See |
||
Creates an asv benchmark in a folder but does not run it. |
||
Creates a tensor. |
||
Creates a constant. log(x) + numpy.float32(1) works but numpy.float32(32) + log(x) fails because Python calls … |
||
See |
||
Experimental implementation of operator Einsum when it does a matrix multiplication. Case: |
||
Implements function pad in python, only … |
||
Selects the appropriate converter for a @see cl CustomScorerTransform. |
||
This function updates the inputs and the outputs for a @see cl CustomScorerTransform. |
||
Computes the output shapes for a @see cl CustomScorerTransform. |
||
Dumps an object for debug purpose. |
||
|
||
Displays informations on an object. |
||
Decomposes an equation used in numpy.einsum knowing the input shapes. It returns a sequence of operations … |
||
Returns default values number and repeat to measure the execution of a function. |
||
See |
||
Returns the corresponding providers for a specific device. |
||
dgemm_dot(double[:, |
||
Returns a shortened string of the model. |
||
See |
||
Downloads a model and returns a link to the local ONNX file and data which can be used as inputs. |
||
Returns the name of a numpy dtype. |
||
Trains and dumps a model for a binary classification problem. The function trains a model and calls |
||
Dumps Booster to JSON format. Parameters ———- self: booster num_iteration : int or None, optional … |
||
Saves data with pickle, saves the model with pickle and onnx, runs and saves the predictions for the given model. … |
||
Dumps information when an error was detected using pickle. |
||
Dumps a Lightgbm booster into JSON. |
||
Trains and dumps a model for a binary classification problem. The function trains a model and calls |
||
Trains and dumps a model for a binary classification problem. The function trains a model and calls |
||
Trains and dumps a model for a multi regression problem. The function trains a model and calls |
||
Trains and dumps a model for a One Class outlier problem. The function trains a model and calls |
||
Trains and dumps a model for a regression problem. The function trains a model and calls |
||
Generates the documentation for ONNX operators. |
||
See |
||
Proposes a new implementation of numpy.einsum. It does not allow expresion using … and expects a right … |
||
Investigates whether or not the decomposing einsum is faster. |
||
Investigates whether or not the decomposing einsum is faster. |
||
Does nothing. |
||
Ensures and modifies the order of nodes to have a topological order (every node in the list can only be an input … |
||
Replays a benchmark stored with function |
||
Enumerates all cached einsum function. |
||
Lists all compatible opsets for a specific model. |
||
Looks into asv results and wraps all of them into a dataframe or flat data. |
||
Enumerate all fitted arrays included in a scikit-learn object. |
||
Enumerates all the nodes of a model. |
||
Enumerates models with models. |
||
Collects test from a sub folder of onnx/backend/test. Works as an enumerator to start processing them without … |
||
Enumerates all the models within a pipeline. |
||
Enumerates random matrices. |
||
Tests all possible configurations for all possible operators and returns the results. |
||
Returns content for pages such as linear_model. |
||
See scipy.special.erf. |
||
Evaluates a condition such as |
||
See |
||
See |
||
Expands shortened options. Long names hide some part of graphs in asv benchmark. This trick converts a string … |
||
See scipy.special.expit. |
||
Exports an ONNX model to the numpy syntax. The exports does not work with all operators. |
||
Exports an ONNX model to the onnx syntax. |
||
Exports an ONNX model to the tensorflow-onnx syntax. |
||
Exports an ONNX model to the onnx syntax. |
||
Looks into asv results and wraps all of them into a dataframe or flat data. |
||
Exports an ONNX model to the onnx syntax. |
||
Returns a dictionary with information extracted from a filename. An example is better: |
||
Extracts comparison option from filename. As example, |
||
Used for documentation. |
||
Finds in scikit-learn the missing pieces. |
||
Finds a node input by its name. |
||
Finds a node by its name. |
||
Finds the corresponding modulee for an element of scikit-learn. |
||
Defines suitables problems for additional converters. |
||
Determines problems suitable for a given scikit-learn operator. It may be |
||
Fits a classification model. |
||
Fits a classification model. |
||
Fits a classification model. |
||
Fits a regression model. |
||
The execution of a file through function exec does not import new modules. They must be there when it is … |
||
See |
||
Converts an array into an ONNX tensor. |
||
Retrieves an array from bytes then protobuf. |
||
Extracts tensor description from a protobuf. |
||
Gathers values along an axis specified by dim. For a 3-D tensor the output is specified by: |
||
|
||
Implements dot product with gemm when possible. |
||
Extracts arguments and optional parameters of a function. |
||
Returns a default context useful for most of the conversion from a function using numpy into ONNX. |
||
Returns a default useful context to compile the converter returned by |
||
Retrieves defined inputs in already declared variables bsed on their names. |
||
Gets types of predefined outputs when they cannot be inferred. Some part of it should be automated based on type … |
||
Returns the list of available domains. |
||
Returns the shape of a tensor. |
||
Produces input data for onnx runtime. |
||
Returns the corresponding IR_VERSION based on the selected opset. See ONNX Version. |
||
Returns the maximum value for a specific type. |
||
Retrieves examples associated to one operator stored in onnx packages. |
||
Returns the operator schema for a specific operator. |
||
Returns all schemas mapped to an operator name. |
||
Converts device into C_OrtDevice. |
||
Returns a documentation in RST format for all |
||
Returns a documentation in RST format for all OnnxOperator. |
||
Template to export ONNX into tensorflow-onnx code. |
||
Template to export ONNX into a code based on XOP API. |
||
Converts a proto type into a numpy type. |
||
Guesses initial types from an array or a dataframe. |
||
Guesses the corresponding numpy type based on data_type. |
||
Converts a string (such as ‘dtype(float32)’) into a numpy dtype. |
||
Converts a string (such as ‘float’) into a numpy dtype. |
||
Guesses the ONNX dtype given a numpy dtype. |
||
Returns a string equivalent to onnx_dtype. |
||
Guesses initial types from a dataset. |
||
Guesses initial types from a model. |
||
Hash the content of an object. |
||
Creates a heatmap from a numpy array and two lists of labels. See |
||
See |
||
Identifies the interpreter for a scikit-learn model. |
||
Identity. |
||
Inserts a node before one node input. |
||
Inserts results into an ONNX graph to produce an extended ONNX graph. It can saved and looked into with a tool such … |
||
Inspects a scikit-learn model and produces some figures which tries to represent the complexity of it. |
||
Converts a string into a dictionary. |
||
Returns |
||
Tells if a backend is enabled. Raises an exception if backend != ‘onnxruntime’. Unit tests only test models against … |
||
Tells if this is the most recent schema for this operator. |
||
Tells if a dtype is a numpy dtype. |
||
Tells if the permutation perm does nothing (itentity). |
||
See |
||
Measures the latency of a model (python API). |
||
Measures the latency of a model (python API). |
||
Agnostic parser for LightGBM Booster. |
||
Returns a linear regression converted into ONNX. |
||
Use to test conversion of sklearn.ensemble.GradientBoostingClassifier into ONNX. |
||
Restores protobuf data stored in a folder. |
||
Loads every file in a dictionary {key: filename}. The extension is either pkl and onnx and determines how it … |
||
To allow the call |
||
Sets up a class for a specific ONNX operator. |
||
Gets the operator related to the onnx node. |
||
Gets the operator related to the onnx node. This runtime does nothing and never complains. |
||
Gets the operator related to the onnx node. |
||
Dynamically creates a class for a every operator type in the given list. |
||
See |
||
See |
||
Returns a logistic regression converted into ONNX, option zipmap is set to false. |
||
Implements |
||
Creates a callable function able to cope with default values as the combination of functions compile and exec … |
||
Creates a hash of length length. |
||
Multiplies or reduces the rows of x to get exactly n rows. |
||
Creates a unique name. |
||
Converts an ONNX operators into numpy code. |
||
Creates a readable title based on the test information. |
||
Implements operator slice in numpy. |
||
Raises an exception if cond is not verified. |
||
Converts an ONNX operators into tf2onnx code. |
||
Converts a variable defined by its name, type and shape into onnx.ValueInfoProto. |
||
Converts ONNX type into numpy type. |
||
See |
||
Retrieves the max depth assuming the estimator is a decision tree. |
||
Returns the latest supported opset for the main domain. |
||
See |
||
Measures the relative difference between predictions between two ways of computing them. The functions returns nan … |
||
Measures a statement and returns the results as a dictionary. |
||
Merges several benchmarks run with command line validate_runtime. |
||
Merges results by name. The first ones are used to keep the order. |
||
LightGBM produces sometimes a tree with a node set to use rule |
||
Returns modules and versions currently used. |
||
Rewrites the converters implemented in sklearn-onnx to support custom functions implemented with Complete Numpy API for ONNX. … |
||
Rewrites the converters implemented in sklearn-onnx to support an operator supporting doubles. |
||
Rewrites the converters implemented in sklearn-onnx to support an operator supporting doubles. |
||
Rewrites the converters implemented in sklearn-onnx to support custom functions implemented with Complete Numpy API for ONNX. … |
||
Rewrites the converters implemented in sklearn-onnx to support an operator supporting doubles. |
||
Rewrites the converters implemented in sklearn-onnx to support an operator supporting doubles. |
||
Rewrites the converters implemented in sklearn-onnx to support an operator supporting doubles. |
||
Rewrites the converters implemented in sklearn-onnx to support an operator supporting doubles. |
||
Rewrites the converters implemented in sklearn-onnx to support an operator supporting doubles. |
||
Rewrites the converters implemented in sklearn-onnx to support an operator supporting doubles. |
||
Extracts diagonal coefficients from an array. |
||
Implements a dot product, deals with inplace information. See numpy.dot. |
||
Extended version of a matrix multiplication (numpy.dot) with two matrices m1, m2 of the same dimensions. … |
||
Implementation of |
||
Computes the output shape of results produced by function |
||
Implementation of |
||
Implements a matmul product, deals with inplace information. See numpy.matmul. Inplace computation does … |
||
Returns the maximum of an array. Deals with text as well. |
||
Returns the maximum of an array. Deals with text as well. |
||
Returns the minimum of an array. Deals with text as well. |
||
Returns the maximum of an array. Deals with text as well. |
||
Returns the minimum of an array. Deals with text as well. |
||
Converts a numpy dtyp into a TensorProto dtype. |
||
Converts a numpy dtyp into a TensorProto dtype. |
||
Converts an ONNX graph into a graph representation, edges, vertices. |
||
Exports an ONNX graph into a python code creating the same graph. |
||
Creates documentation in a folder for all known ONNX operators or a subset. |
||
Computes a distance between two ONNX graphs. They must not be too big otherwise this function might take for ever. … |
||
Implements a test with onnx syntax. |
||
Extracts opsets in a dictionary. |
||
Optimizes an ONNX model. |
||
Calls several possible optimisations including |
||
Implements numpy.pad based on ONNX signature. |
||
Removes as many nodes as possible without changing the outcome. It applies |
||
Removes as many Identity nodes as possible. The function looks into every node and subgraphs if recursive is … |
||
Removes redundant part of the graph. A redundant part is a set of nodes which takes the same inputs and produces … |
||
Removes unused nodes of the graph. An unused node is not involved in the output computation. |
||
Renames all names except the inputs and outputs. |
||
Shakes a model ONNX. Explores the ranges for every prediction. Uses |
||
Displays an ONNX graph into text. |
||
Computes statistics on ONNX models, extracts informations about the model such as the number of nodes. |
||
Computes statistics on an ONNX model. |
||
Uses |
||
Displays information about input and output types. |
||
Gives a textual representation of a tree ensemble. |
||
Decorator to declare a function implemented using numpy syntax but executed with ONNX operators. … |
||
Decorator with options to declare a function implemented using numpy syntax but executed with ONNX … |
||
Decorator to declare a function implemented using numpy syntax but executed with ONNX operators. … |
||
Decorator to declare a converter for a class derivated from scikit-learn, implementing inference method … |
||
Decorator to declare a converter for a classifier implemented using numpy syntax but executed with ONNX … |
||
Decorator to declare a converter for a cluster implemented using numpy syntax but executed with ONNX … |
||
Decorator to declare a converter for a regressor implemented using numpy syntax but executed with ONNX … |
||
Decorator to declare a converter for a transformer implemented using numpy syntax but executed with ONNX … |
||
Displays an ONNX graph into a notebook. |
||
Proposes a new implementation of numpy.einsum. It does not allow expresion using … and expects a right … |
||
Overwrites the main opset in an ONNX file. Does not change any node definition. |
||
It does not implement |
||
Computes pairwise distances between two lists of arrays l1 and l2. The distance is 1e9 if shapes are not equal. |
||
Parser for TransferTransformer. |
||
Plots a heatmap which represents a benchmark. See example below. |
||
Plots an ONNX graph on the standard output. |
||
Plots an ONNX graph into a matplotlib graph. |
||
Plots a graph which summarizes the performances of a benchmark validating a runtime for ONNX. |
||
Given a shape and a permutation, predicts the cost of the transposition. |
||
Prepares model and data to be profiled with tool perftest … |
||
Returns the code with line number. |
||
See |
||
Converts a proto type into a numpy type. |
||
Converts proto values to Variables. |
||
Creates an array with a single element from a constant. |
||
Function for python operator |
||
Function for python unary operator |
||
Function for python operator |
||
Computes function |
||
Pure python implementatin of GEMM. |
||
Creates a dictionary of random inputs. |
||
See |
||
This functions registers additional converters to the list of converters sklearn-onnx declares. |
||
Register magics function, can be called from a notebook. |
||
Registers a new runtime operator. |
||
Registers modified operators and returns the old values. |
||
Registers operators for @see cl CustomScorerTransform. |
||
Returns any regressor from scikit-learn converted into ONNX assuming a converter is registered with sklearn-onnx. … |
||
relu |
||
Reorders the node with breadth first seach (BFS). |
||
|
||
Restores speed up information to help modifying the structure of the tree. |
||
See |
||
Computes the sum of pairwise distances between expected_values and predictions. It has no particular purpose … |
||
Returns the list of the same attribute. [el.att for el in ens]. |
||
Takes a model and changes its outputs. |
||
Looks into model signature and add parameter n_jobs if available. The function does not overwrite the parameter. |
||
Sets all possible parameter random_state to 0. |
||
Sphinx extension mlprodict.npy.xop_sphinx displays documentation on ONN Operators. |
||
sgemm_dot(float[:, |
||
Infers shape for operator Abs. |
||
Infers shape for operator Acos. |
||
Infers shape for operator Acosh. |
||
Infers shape for operator Add. |
||
Infers shape for operator And. |
||
Infers shape for operator Asin. |
||
Infers shape for operator Asinh. |
||
Infers shape for operator Atan. |
||
Infers shape for operator Atanh. |
||
Shape calculator for operator LightGBMConcat. |
||
Shape calculator for TransferTransformer. |
||
Infers shape for operator CastLike. |
||
Infers shape for operator Ceil. |
||
Infers shape for operator Celu. |
||
Infers shape for operator Clip. |
||
Infers shape for operator Cos. |
||
Infers shape for operator Cosh. |
||
Infers shape for operator Abs. |
||
Calls the corresponding fucntion for every node. |
||
Infers shape for operator Div. |
||
Infers shape for operator Elu. |
||
Infers shape for operator Equal. |
||
Infers shape for operator Erf. |
||
Infers shape for operator Exp. |
||
Infers shape for operator Floor. |
||
Infers shape for operator Greater. |
||
Infers shape for operator GreaterOrEqual. |
||
Infers shape for operator Hardmax. |
||
Infers shape for operator HardSigmoid. |
||
Infers shape for operator Identity. |
||
Infers shape for operator IsInf. |
||
Infers shape for operator IsNan. |
||
Infers shape for operator LeakyRelu. |
||
Infers shape for operator Less. |
||
Infers shape for operator LessOrEqual. |
||
Infers shape for operator Log. |
||
Infers shape for operator LogSoftmax. |
||
Infers shape for operator Max. |
||
Infers shape for operator Min. |
||
Infers shape for operator Mod. |
||
Infers shape for operator Mul. |
||
Infers shape for operator Neg. |
||
Infers shape for operator Not. |
||
Infers shape for operator Or. |
||
Infers shape for operator Pow. |
||
Infers shape for operator Reciprocal. |
||
Infers shape for operator Relu. |
||
Infers shape for operator Round. |
||
Infers shape for operator Selu. |
||
Infers shape for operator Sigmoid. |
||
Infers shape for operator Sigmoid. |
||
Infers shape for operator Sin. |
||
Infers shape for operator Sinh. |
||
Infers shape for operator Softmax. |
||
Infers shape for operator Sqrt. |
||
Infers shape for operator Sub. |
||
Infers shape for operator Tan. |
||
Infers shape for operator Tanh. |
||
Infers shape for operator Trilu. |
||
Infers shape for operator Xor. |
||
Returns a short list from ONNX Zoo. |
||
Shortens onnx options into a string. Long names hide some part of graphs in asv benchmark. |
||
Compares the execution of two sessions. It calls method |
||
See scipy.special.expit. |
||
See |
||
See |
||
axes contains positive values, then it is the position of this axis in the original matrix, otherwise it is -1 … |
||
See |
||
|
||
Converts any kind of scikit-learn model into a grammar model. |
||
Converts a DecisionTreeRegressor … |
||
Converts a linear regression … |
||
Interprets a logistic regression … |
||
Builds the list of operators from scikit-learn. The function goes through the list of submodule and get … |
||
Converts a standard scaler … |
||
Modified version of softmaxcrossentropy.py … |
||
Functions used in the documentation to split a dataframe by columns into multiple dataframe to reduce the scrolling. … |
||
See |
||
Replacements for squareform … |
||
See |
||
See |
||
Finalizes the results computed by function |
||
See |
||
See |
||
Checks a runtime for operator QLinearConv. |
||
Measures the time for a given expression. |
||
Returns a series of repeat time measures for number executions of code assuming fct is a function. |
||
Converts an array into protobuf and then into bytes. |
||
Converts a model using on sklearn-onnx. |
||
Converts name, elem_type, shape into a sklearn-onnx type. |
||
See |
||
Retrieves the top-k elements. |
||
Retrieves the top-k elements using a C++ implementation when the axis is the last dimension, otherwise, it falls … |
||
Returns any transformer from scikit-learn converted into ONNX assuming a converter is registered with sklearn-onnx. … |
||
Translates a function into ONNX. The code it produces is using classes OnnxAbs, OnnxAdd, … |
||
See |
||
Mapping between types name and type integer value. |
||
See |
||
Registers or updates a converter for a new model so that it can be converted when inserted in a scikit-learn pipeline. … |
||
Validates the code produced by method |
||
Walks through most of scikit-learn operators or model or predictor or transformer, tries to convert them … |
||
Verifies python code. |
||
Verifies a model. |
||
Checks that models fitted in an example from scikit-learn documentation can be converted into ONNX. |
||
Converts a version number into a real number. |
||
Returns a jinja2 template to display DOT graph for each converter from sklearn-onnx. |
||
See |
||
See |