module onnxrt.validate.validate_summary#

Short summary#

module mlprodict.onnxrt.validate.validate_summary

Summarizes results produces by function in validate.py.

source on GitHub

Classes#

class

truncated documentation

_MyEncoder

Functions#

function

truncated documentation

_clean_values_optim

_jsonify

_summary_report_indices

merge_benchmark

Merges several benchmarks run with command line validate_runtime.

summary_report

Finalizes the results computed by function enumerate_validated_operator_opsets().

Methods#

method

truncated documentation

default

Documentation#

Summarizes results produces by function in validate.py.

source on GitHub

class mlprodict.onnxrt.validate.validate_summary._MyEncoder(*, skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, sort_keys=False, indent=None, separators=None, default=None)#

Bases: JSONEncoder

Constructor for JSONEncoder, with sensible defaults.

If skipkeys is false, then it is a TypeError to attempt encoding of keys that are not str, int, float or None. If skipkeys is True, such items are simply skipped.

If ensure_ascii is true, the output is guaranteed to be str objects with all incoming non-ASCII characters escaped. If ensure_ascii is false, the output can contain non-ASCII characters.

If check_circular is true, then lists, dicts, and custom encoded objects will be checked for circular references during encoding to prevent an infinite recursion (which would cause an OverflowError). Otherwise, no such check takes place.

If allow_nan is true, then NaN, Infinity, and -Infinity will be encoded as such. This behavior is not JSON specification compliant, but is consistent with most JavaScript based encoders and decoders. Otherwise, it will be a ValueError to encode such floats.

If sort_keys is true, then the output of dictionaries will be sorted by key; this is useful for regression tests to ensure that JSON serializations can be compared on a day-to-day basis.

If indent is a non-negative integer, then JSON array elements and object members will be pretty-printed with that indent level. An indent level of 0 will only insert newlines. None is the most compact representation.

If specified, separators should be an (item_separator, key_separator) tuple. The default is (’, ‘, ‘: ‘) if indent is None and (‘,’, ‘: ‘) otherwise. To get the most compact JSON representation, you should specify (‘,’, ‘:’) to eliminate whitespace.

If specified, default is a function that gets called for objects that can’t otherwise be serialized. It should return a JSON encodable version of the object or raise a TypeError.

default(o)#

Implement this method in a subclass such that it returns a serializable object for o, or calls the base implementation (to raise a TypeError).

For example, to support arbitrary iterators, you could implement default like this:

def default(self, o):
    try:
        iterable = iter(o)
    except TypeError:
        pass
    else:
        return list(iterable)
    # Let the base class default method raise the TypeError
    return JSONEncoder.default(self, o)
mlprodict.onnxrt.validate.validate_summary._clean_values_optim(val)#
mlprodict.onnxrt.validate.validate_summary._jsonify(x)#
mlprodict.onnxrt.validate.validate_summary._summary_report_indices(df, add_cols=None, add_index=None)#
mlprodict.onnxrt.validate.validate_summary.merge_benchmark(dfs, column='runtime', baseline=None, suffix='-base')#

Merges several benchmarks run with command line validate_runtime.

Parameters:

  • dfs – dictionary {‘prefix’: dataframe}

  • column – every value from this column is prefixed by the given key in dfs

  • baseline – add baseline

  • suffix – suffix to add when comparing to the baseline

Returns:

merged dataframe

source on GitHub

mlprodict.onnxrt.validate.validate_summary.summary_report(df, add_cols=None, add_index=None)#

Finalizes the results computed by function enumerate_validated_operator_opsets.

Parameters:

  • df – dataframe

  • add_cols – additional columns to take into account as values

  • add_index – additional columns to take into accound as index

Returns:

pivoted dataframe

The outcome can be seen at page about ONNX, Runtime, Backends.

source on GitHub