onnx_diagnostic.helpers.onnx_helper¶

onnx_diagnostic.helpers.onnx_helper.check_model_ort(onx: ModelProto, providers: str | List[Any] | None = None, dump_file: str | None = None) → onnxruntime.InferenceSession[source][source]¶

Loads a model with onnxruntime.

Parameters:

onx – ModelProto
providers – list of providers, None fur CPU, cpu for CPU, cuda for CUDA
dump_file – if not empty, dumps the model into this file if an error happened

Returns:

InferenceSession

onnx_diagnostic.helpers.onnx_helper.convert_endian(tensor: TensorProto) → None[source][source]¶

Call to convert endianness of raw data in tensor.

Args:: tensor: TensorProto to be converted.

onnx_diagnostic.helpers.onnx_helper.dtype_to_tensor_dtype(dt: dtype | torch.dtype) → int[source][source]¶

Converts a torch dtype or numpy dtype into a onnx element type.

Parameters:: to – dtype
Returns:: onnx type

Converts an array into a onnx.TensorProto.

Parameters:

tensor – numpy array or torch tensor
name – name

Returns:

TensorProto

Converts a numpy array to a tensor def assuming the dtype is defined in ml_dtypes.

Args:: arr: a numpy array. name: (optional) the name of the tensor.
Returns:: TensorProto: the converted tensor def.

onnx_diagnostic.helpers.onnx_helper.get_onnx_signature(model: ModelProto) → Tuple[Tuple[str, Any], ...][source][source]¶

Produces a tuple of tuples corresponding to the signatures.

Parameters:: model – model
Returns:: signature

onnx_diagnostic.helpers.onnx_helper.iterator_initializer_constant(model: FunctionProto | GraphProto | ModelProto, use_numpy: bool = True, prefix: str = '') → Iterator[Tuple[str, torch.Tensor | ndarray]][source][source]¶

Iterates on iniatialiers and constant in an onnx model.

Parameters:

model – model
use_numpy – use numpy or pytorch
prefix – for subgraph

Returns:

iterator

onnx_diagnostic.helpers.onnx_helper.np_dtype_to_tensor_dtype(dt: dtype) → int[source][source]¶

Converts a numpy dtype into a onnx element type.

Parameters:: to – dtype
Returns:: onnx type

onnx_diagnostic.helpers.onnx_helper.onnx_dtype_name(itype: int) → str[source][source]¶

Returns the ONNX name for a specific element type.

<<<

import onnx
from onnx_diagnostic.helpers.onnx_helper import onnx_dtype_name

itype = onnx.TensorProto.BFLOAT16
print(onnx_dtype_name(itype))
print(onnx_dtype_name(7))

>>>

    BFLOAT16
    INT64

onnx_diagnostic.helpers.onnx_helper.onnx_dtype_to_np_dtype(itype: int) → Any[source][source]¶

Converts an onnx type into a to numpy dtype. That includes ml_dtypes dtypes.

Parameters:: to – onnx dtype
Returns:: numpy dtype

onnx_diagnostic.helpers.onnx_helper.onnx_find(onx: str | ModelProto, verbose: int = 0, watch: Set[str] | None = None) → List[NodeProto | TensorProto][source][source]¶

Looks for node producing or consuming some results.

Parameters:

onx – model
verbose – verbosity
watch – names to search for

Returns:

list of nodes

onnx_diagnostic.helpers.onnx_helper.onnx_lighten(onx: str | ModelProto, verbose: int = 0) → Tuple[ModelProto, Dict[str, Dict[str, float]]][source][source]¶

Creates a model without big initializers but stores statistics into dictionaries. The function can be reversed with onnx_diagnostic.helpers.onnx_helper.onnx_unlighten(). The model is modified inplace.

Parameters:

onx – model
verbose – verbosity

Returns:

new model, statistics

onnx_diagnostic.helpers.onnx_helper.onnx_unlighten(onx: str | ModelProto, stats: Dict[str, Dict[str, float]] | None = None, verbose: int = 0) → ModelProto[source][source]¶

Function fixing the model produced by function onnx_diagnostic.helpers.onnx_helper.onnx_lighten(). The model is modified inplace.

Parameters:

onx – model
stats – statistics, can be None if onx is a file, then it loads the file <filename>.stats, it assumes it is json format
verbose – verbosity

Returns:

new model, statistics

Displays an onnx prot in a better way.

Parameters:

with_attributes – displays attributes as well, if only a node is printed
highlight – to highlight some names
shape_inference – run shape inference before printing the model

Returns:

text

onnx_diagnostic.helpers.onnx_helper.tensor_dtype_to_np_dtype(tensor_dtype: int) → dtype[source][source]¶

Converts a TensorProto’s data_type to corresponding numpy dtype. It can be used while making tensor.

Parameters:: tensor_dtype – TensorProto’s data_type
Returns:: numpy’s data_type

onnx_diagnostic.helpers.onnx_helper.tensor_statistics(tensor: ndarray | TensorProto) → Dict[str, float | str][source][source]¶

Produces statistics on a tensor.

Parameters:: tensor – tensor
Returns:: statistics

<<<

import pprint
import numpy as np
from onnx_diagnostic.helpers.onnx_helper import tensor_statistics

t = np.random.rand(40, 50).astype(np.float16)
pprint.pprint(tensor_statistics(t))

>>>

    {'>0.0': 2000,
     '>0.00010001659393310547': 2000,
     '>0.0010004043579101562': 2000,
     '>0.01000213623046875': 1990,
     '>0.0999755859375': 1797,
     '>0.5': 967,
     '>1.0': 0,
     '>1.0013580322265625e-05': 2000,
     '>1.0132789611816406e-06': 2000,
     '>1.1920928955078125e-07': 2000,
     '>1.9599609375': 0,
     '>10.0': 0,
     '>100.0': 0,
     '>1000.0': 0,
     '>10000.0': 0,
     'itype': 10,
     'max': 0.99951171875,
     'mean': 0.49365234375,
     'min': 0.0022335052490234375,
     'nnan': 0.0,
     'numel': 2000,
     'q0.1': 0.09776611328125,
     'q0.2': 0.184375,
     'q0.3': 0.2864013671875,
     'q0.4': 0.38374023437500004,
     'q0.5': 0.483642578125,
     'q0.6': 0.5902343749999999,
     'q0.7': 0.701171875,
     'q0.8': 0.80712890625,
     'q0.9': 0.8995117187500001,
     'shape': '40x50',
     'size': 4000,
     'std': 0.292724609375,
     'stype': 'FLOAT16'}

onnx_diagnostic.helpers.onnx_helper.to_array_extended(proto: TensorProto) → Buffer | _SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | bool | int | float | complex | str | bytes | _NestedSequence[bool | int | float | complex | str | bytes][source][source]¶: Converts onnx.TensorProto into a numpy array.

onnx_diagnostic.helpers.onnx_helper.type_info(itype: int, att: str)[source][source]¶

Returns the minimum or maximum value for a type.

Parameters:

itype – onnx type
att – ‘min’ or ‘max’

Returns:

value