my_metricv2.py

# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""TODO: Add a description here."""

import evaluate
import datasets
import motmetrics as mm
import numpy as np

# TODO: Add BibTeX citation
_CITATION = """\
@InProceedings{huggingface:module,
title = {A great new module},
authors={huggingface, Inc.},
year={2020}
}
"""

# TODO: Add description of the module here
_DESCRIPTION = """\
This new module is designed to solve this great ML task and is crafted with a lot of care.
"""


# TODO: Add description of the arguments of the module here
_KWARGS_DESCRIPTION = """

Calculates how good are predictions given some references, using certain scores
Args:
    predictions: list of predictions to score. Each predictions
        should be a string with tokens separated by spaces.
    references: list of reference for each prediction. Each
        reference should be a string with tokens separated by spaces.
Returns:
    accuracy: description of the first score,
    another_score: description of the second score,
Examples:
    >>> import numpy as np
    >>> mean_iou = evaluate.load("mean_iou")

    >>> # suppose one has 3 different segmentation maps predicted
    >>> predicted_1 = np.array([[1, 2], [3, 4], [5, 255]])
    >>> actual_1 = np.array([[0, 3], [5, 4], [6, 255]])

    >>> predicted_2 = np.array([[2, 7], [9, 2], [3, 6]])
    >>> actual_2 = np.array([[1, 7], [9, 2], [3, 6]])

    >>> predicted_3 = np.array([[2, 2, 3], [8, 2, 4], [3, 255, 2]])
    >>> actual_3 = np.array([[1, 2, 2], [8, 2, 1], [3, 255, 1]])

    >>> predicted = [predicted_1, predicted_2, predicted_3]
    >>> ground_truth = [actual_1, actual_2, actual_3]

    >>> results = mean_iou.compute(predictions=predicted, references=ground_truth, num_labels=10, ignore_index=255, reduce_labels=False)
    >>> print(results) # doctest: +NORMALIZE_WHITESPACE
    {'mean_iou': 0.47750000000000004, 'mean_accuracy': 0.5916666666666666, 'overall_accuracy': 0.5263157894736842, 'per_category_iou': array([0.   , 0.   , 0.375, 0.4  , 0.5  , 0.   , 0.5  , 1.   , 1.   , 1.   ]), 'per_category_accuracy': array([0.        , 0.        , 0.75      , 0.66666667, 1.        , 0.        , 0.5       , 1.        , 1.        , 1.        ])}

"""

# TODO: Define external resources urls if needed
BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class MyMetricv2(evaluate.Metric):
    """TODO: Short description of my evaluation module."""

    def _info(self):
        # TODO: Specifies the evaluate.EvaluationModuleInfo object
        return evaluate.MetricInfo(
            # This is the description that will appear on the modules page.
            module_type="metric",
            description=_DESCRIPTION,
            citation=_CITATION,
            inputs_description=_KWARGS_DESCRIPTION,
            # This defines the format of each prediction and reference
            features=datasets.Features({
                "predictions": datasets.Sequence(
                                datasets.Sequence(datasets.Value("float"))
                            ),
                "references": datasets.Sequence(
                                datasets.Sequence(datasets.Value("float"))
                            )
            }),
            # Homepage of the module for documentation
            homepage="http://module.homepage",
            # Additional links to the codebase or references
            codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
            reference_urls=["http://path.to.reference.url/new_module"]
        )

    def _download_and_prepare(self, dl_manager):
        """Optional: download external resources useful to compute the scores"""
        # TODO: Download external resources if needed
        pass

    def _compute(self, predictions, references):
        """Returns the scores"""
        # TODO: Compute the different scores of the module

        # <frame number>, <object id>, <bb_left>, <bb_top>, <bb_width>, <bb_height>, <confidence>, <x>, <y>, <z>

        return calculate(predictions, references)

def calculate(predictions, references):
    """Returns the scores"""
    try: 
        np_predictions = np.array(predictions)
        np_references = np.array(references)
    except:
        raise ValueError("The predictions and references should be lists of floats in the correct format [frame number, object id, bb_left, bb_top, bb_width, bb_height, confidence]")
    
    print(predictions)
    print(references)

    return {
        
            "predictions": predictions,
            "references": references
    
        }