### `mlonnx.ArrayFeatureExtractor` (MLONNXArrayFeatureExtractorOp) ONNX ArrayFeatureExtractor operation "Select elements of the input tensor based on the indices passed.
" " The indices are applied to the last axes of the tensor." #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values `Y` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Z` | memref of any type values or tensor of any type values ### `mlonnx.Binarizer` (MLONNXBinarizerOp) ONNX Binarizer operation "Maps the values of the input tensor to either 0 or 1, element-wise, based on the outcome of a comparison against a threshold value." #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `threshold` | FloatAttr | 32-bit float attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.CastMap` (MLONNXCastMapOp) ONNX CastMap operation "Converts a map to a tensor.
The map key must be an int64 and the values will be ordered" " in ascending order based on this key.
The operator supports dense packing or sparse packing." " If using sparse packing, the key cannot exceed the max_map-1 value." #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `cast_to` | StringAttr | string attribute `map_form` | StringAttr | string attribute `max_map` | IntegerAttr | 64-bit signless integer attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.CategoryMapper` (MLONNXCategoryMapperOp) ONNX CategoryMapper operation "Converts strings to integers and vice versa.
" " Two sequences of equal length are used to map between integers and strings," " with strings and integers at the same index detailing the mapping.
" " Each operator converts either integers to strings or strings to integers, depending " " on which default value attribute is provided. Only one default value attribute" " should be defined.
" " If the string default value is set, it will convert integers to strings." " If the int default value is set, it will convert strings to integers." #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `cats_int64s` | ArrayAttr | 64-bit integer array attribute `cats_strings` | ArrayAttr | string array attribute `default_int64` | IntegerAttr | 64-bit signless integer attribute `default_string` | StringAttr | string attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.DictVectorizer` (MLONNXDictVectorizerOp) ONNX DictVectorizer operation "Uses an index mapping to convert a dictionary to an array.
" " Given a dictionary, each key is looked up in the vocabulary attribute corresponding to" " the key type. The index into the vocabulary array at which the key is found is then" " used to index the output 1-D tensor 'Y' and insert into it the value found in the dictionary 'X'.
" " The key type of the input map must correspond to the element type of the defined vocabulary attribute." " Therefore, the output array will be equal in length to the index mapping vector parameter." " All keys in the input dictionary must be present in the index mapping vector." " For each item in the input dictionary, insert its value in the output array." " Any keys not present in the input dictionary, will be zero in the output array.
" " For example: if the ``string_vocabulary`` parameter is set to ``[\"a\", \"c\", \"b\", \"z\"]``," " then an input of ``{\"a\": 4, \"c\": 8}`` will produce an output of ``[4, 8, 0, 0]``." " " #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `int64_vocabulary` | ArrayAttr | 64-bit integer array attribute `string_vocabulary` | ArrayAttr | string array attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.FeatureVectorizer` (MLONNXFeatureVectorizerOp) ONNX FeatureVectorizer operation "Concatenates input tensors into one continuous output.
" " All input shapes are 2-D and are concatenated along the second dimention. 1-D tensors are treated as [1,C]." " Inputs are copied to the output maintaining the order of the input arguments.
" " All inputs must be integers or floats, while the output will be all floating point values." #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `inputdimensions` | ArrayAttr | 64-bit integer array attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.Imputer` (MLONNXImputerOp) ONNX Imputer operation "Replaces inputs that equal one value with another, leaving all other elements alone.
" " This operator is typically used to replace missing values in situations where they have a canonical" " representation, such as -1, 0, NaN, or some extreme value.
" " One and only one of imputed_value_floats or imputed_value_int64s should be defined -- floats if the input tensor" " holds floats, integers if the input tensor holds integers. The imputed values must all fit within the" " width of the tensor element type. One and only one of the replaced_value_float or replaced_value_int64 should be defined," " which one depends on whether floats or integers are being processed.
" " The imputed_value attribute length can be 1 element, or it can have one element per input feature.
In other words, if the input tensor has the shape [*,F], then the length of the attribute array may be 1 or F. If it is 1, then it is broadcast along the last dimension and applied to each feature." #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `imputed_value_floats` | ArrayAttr | 32-bit float array attribute `imputed_value_int64s` | ArrayAttr | 64-bit integer array attribute `replaced_value_float` | FloatAttr | 32-bit float attribute `replaced_value_int64` | IntegerAttr | 64-bit signless integer attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.LabelEncoder` (MLONNXLabelEncoderOp) ONNX LabelEncoder operation "Maps each element in the input tensor to another value.
" " The mapping is determined by the two parallel attributes, 'keys_*' and" " 'values_*' attribute. The i-th value in the specified 'keys_*' attribute" " would be mapped to the i-th value in the specified 'values_*' attribute. It" " implies that input's element type and the element type of the specified" " 'keys_*' should be identical while the output type is identical to the" " specified 'values_*' attribute. If an input element can not be found in the" " specified 'keys_*' attribute, the 'default_*' that matches the specified" " 'values_*' attribute may be used as its output value.
" " Let's consider an example which maps a string tensor to an integer tensor." " Assume and 'keys_strings' is [\"Amy\", \"Sally\"], 'values_int64s' is [5, 6]," " and 'default_int64' is '-1'. The input [\"Dori\", \"Amy\", \"Amy\", \"Sally\"," " \"Sally\"] would be mapped to [-1, 5, 5, 6, 6].
" " Since this operator is an one-to-one mapping, its input and output shapes" " are the same. Notice that only one of 'keys_*'/'values_*' can be set.
" " For key look-up, bit-wise comparison is used so even a float NaN can be" " mapped to a value in 'values_*' attribute.
" #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `default_float` | FloatAttr | 32-bit float attribute `default_int64` | IntegerAttr | 64-bit signless integer attribute `default_string` | StringAttr | string attribute `keys_floats` | ArrayAttr | 32-bit float array attribute `keys_int64s` | ArrayAttr | 64-bit integer array attribute `keys_strings` | ArrayAttr | string array attribute `values_floats` | ArrayAttr | 32-bit float array attribute `values_int64s` | ArrayAttr | 64-bit integer array attribute `values_strings` | ArrayAttr | string array attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.LinearClassifier` (MLONNXLinearClassifierOp) ONNX LinearClassifier operation "Linear classifier" #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `classlabels_ints` | ArrayAttr | 64-bit integer array attribute `classlabels_strings` | ArrayAttr | string array attribute `coefficients` | ArrayAttr | 32-bit float array attribute `intercepts` | ArrayAttr | 32-bit float array attribute `multi_class` | IntegerAttr | 64-bit signless integer attribute `post_transform` | StringAttr | string attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values `Z` | memref of any type values or tensor of any type values ### `mlonnx.LinearRegressor` (MLONNXLinearRegressorOp) ONNX LinearRegressor operation "Generalized linear regression evaluation.
" " If targets is set to 1 (default) then univariate regression is performed.
" " If targets is set to M then M sets of coefficients must be passed in as a sequence" " and M results will be output for each input n in N.
" " The coefficients array is of length n, and the coefficients for each target are contiguous." " Intercepts are optional but if provided must match the number of targets." #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `coefficients` | ArrayAttr | 32-bit float array attribute `intercepts` | ArrayAttr | 32-bit float array attribute `post_transform` | StringAttr | string attribute `targets` | IntegerAttr | 64-bit signless integer attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.Normalizer` (MLONNXNormalizerOp) ONNX Normalizer operation "Normalize the input. There are three normalization modes, which have the corresponding formulas," " defined using element-wise infix operators '/' and '^' and tensor-wide functions 'max' and 'sum':
" "
" " Max: Y = X / max(X)
" " L1: Y = X / sum(X)
" " L2: Y = sqrt(X^2 / sum(X^2)}
" " In all modes, if the divisor is zero, Y == X." "
" " For batches, that is, [N,C] tensors, normalization is done along the C axis. In other words, each row" " of the batch is normalized independently." #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `norm` | StringAttr | string attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.OneHotEncoder` (MLONNXOneHotEncoderOp) ONNX OneHotEncoder operation "Replace each input element with an array of ones and zeros, where a single" " one is placed at the index of the category that was passed in. The total category count " " will determine the size of the extra dimension of the output array Y.
" " For example, if we pass a tensor with a single value of 4, and a category count of 8, " " the output will be a tensor with ``[0,0,0,0,1,0,0,0]``.
" " This operator assumes every input feature is from the same set of categories.
" " If the input is a tensor of float, int32, or double, the data will be cast" " to integers and the cats_int64s category list will be used for the lookups." #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `cats_int64s` | ArrayAttr | 64-bit integer array attribute `cats_strings` | ArrayAttr | string array attribute `zeros` | IntegerAttr | 64-bit signless integer attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.SVMClassifier` (MLONNXSVMClassifierOp) ONNX SVMClassifier operation "Support Vector Machine classifier" #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `classlabels_ints` | ArrayAttr | 64-bit integer array attribute `classlabels_strings` | ArrayAttr | string array attribute `coefficients` | ArrayAttr | 32-bit float array attribute `kernel_params` | ArrayAttr | 32-bit float array attribute `kernel_type` | StringAttr | string attribute `post_transform` | StringAttr | string attribute `prob_a` | ArrayAttr | 32-bit float array attribute `prob_b` | ArrayAttr | 32-bit float array attribute `rho` | ArrayAttr | 32-bit float array attribute `support_vectors` | ArrayAttr | 32-bit float array attribute `vectors_per_class` | ArrayAttr | 64-bit integer array attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values `Z` | memref of any type values or tensor of any type values ### `mlonnx.SVMRegressor` (MLONNXSVMRegressorOp) ONNX SVMRegressor operation "Support Vector Machine regression prediction and one-class SVM anomaly detection." #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `coefficients` | ArrayAttr | 32-bit float array attribute `kernel_params` | ArrayAttr | 32-bit float array attribute `kernel_type` | StringAttr | string attribute `n_supports` | IntegerAttr | 64-bit signless integer attribute `one_class` | IntegerAttr | 64-bit signless integer attribute `post_transform` | StringAttr | string attribute `rho` | ArrayAttr | 32-bit float array attribute `support_vectors` | ArrayAttr | 32-bit float array attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.Scaler` (MLONNXScalerOp) ONNX Scaler operation "Rescale input data, for example to standardize features by removing the mean and scaling to unit variance." #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `offset` | ArrayAttr | 32-bit float array attribute `scale` | ArrayAttr | 32-bit float array attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.TreeEnsembleClassifier` (MLONNXTreeEnsembleClassifierOp) ONNX TreeEnsembleClassifier operation "Tree Ensemble classifier. Returns the top class for each of N inputs.
" " The attributes named 'nodes_X' form a sequence of tuples, associated by " " index into the sequences, which must all be of equal length. These tuples" " define the nodes.
" " Similarly, all fields prefixed with 'class_' are tuples of votes at the leaves." " A leaf may have multiple votes, where each vote is weighted by" " the associated class_weights index.
" " One and only one of classlabels_strings or classlabels_int64s" " will be defined. The class_ids are indices into this list." #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `base_values` | ArrayAttr | 32-bit float array attribute `class_ids` | ArrayAttr | 64-bit integer array attribute `class_nodeids` | ArrayAttr | 64-bit integer array attribute `class_treeids` | ArrayAttr | 64-bit integer array attribute `class_weights` | ArrayAttr | 32-bit float array attribute `classlabels_int64s` | ArrayAttr | 64-bit integer array attribute `classlabels_strings` | ArrayAttr | string array attribute `nodes_falsenodeids` | ArrayAttr | 64-bit integer array attribute `nodes_featureids` | ArrayAttr | 64-bit integer array attribute `nodes_hitrates` | ArrayAttr | 32-bit float array attribute `nodes_missing_value_tracks_true` | ArrayAttr | 64-bit integer array attribute `nodes_modes` | ArrayAttr | string array attribute `nodes_nodeids` | ArrayAttr | 64-bit integer array attribute `nodes_treeids` | ArrayAttr | 64-bit integer array attribute `nodes_truenodeids` | ArrayAttr | 64-bit integer array attribute `nodes_values` | ArrayAttr | 32-bit float array attribute `post_transform` | StringAttr | string attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values `Z` | memref of any type values or tensor of any type values ### `mlonnx.TreeEnsembleRegressor` (MLONNXTreeEnsembleRegressorOp) ONNX TreeEnsembleRegressor operation "Tree Ensemble regressor. Returns the regressed values for each input in N.
" " All args with nodes_ are fields of a tuple of tree nodes, and" " it is assumed they are the same length, and an index i will decode the" " tuple across these inputs. Each node id can appear only once" " for each tree id.
" " All fields prefixed with target_ are tuples of votes at the leaves.
" " A leaf may have multiple votes, where each vote is weighted by" " the associated target_weights index.
" " All trees must have their node ids start at 0 and increment by 1.
" " Mode enum is BRANCH_LEQ, BRANCH_LT, BRANCH_GTE, BRANCH_GT, BRANCH_EQ, BRANCH_NEQ, LEAF" #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `aggregate_function` | StringAttr | string attribute `base_values` | ArrayAttr | 32-bit float array attribute `n_targets` | IntegerAttr | 64-bit signless integer attribute `nodes_falsenodeids` | ArrayAttr | 64-bit integer array attribute `nodes_featureids` | ArrayAttr | 64-bit integer array attribute `nodes_hitrates` | ArrayAttr | 32-bit float array attribute `nodes_missing_value_tracks_true` | ArrayAttr | 64-bit integer array attribute `nodes_modes` | ArrayAttr | string array attribute `nodes_nodeids` | ArrayAttr | 64-bit integer array attribute `nodes_treeids` | ArrayAttr | 64-bit integer array attribute `nodes_truenodeids` | ArrayAttr | 64-bit integer array attribute `nodes_values` | ArrayAttr | 32-bit float array attribute `post_transform` | StringAttr | string attribute `target_ids` | ArrayAttr | 64-bit integer array attribute `target_nodeids` | ArrayAttr | 64-bit integer array attribute `target_treeids` | ArrayAttr | 64-bit integer array attribute `target_weights` | ArrayAttr | 32-bit float array attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Y` | memref of any type values or tensor of any type values ### `mlonnx.ZipMap` (MLONNXZipMapOp) ONNX ZipMap operation "Creates a map from the input and the attributes.
" " The values are provided by the input tensor, while the keys are specified by the attributes." " Must provide keys in either classlabels_strings or classlabels_int64s (but not both).
" " The columns of the tensor correspond one-by-one to the keys specified by the attributes. There must be as many columns as keys.
" #### Attributes: | Attribute | MLIR Type | Description | | :-------: | :-------: | ----------- | `classlabels_int64s` | ArrayAttr | 64-bit integer array attribute `classlabels_strings` | ArrayAttr | string array attribute #### Operands: | Operand | Description | | :-----: | ----------- | `X` | memref of any type values or tensor of any type values #### Results: | Result | Description | | :----: | ----------- | `Z` | memref of any type values or tensor of any type values