ref-metrics / ref-metrics.py
hichem-abdellali's picture
Rename ref-metric.py to ref-metrics.py
23714de verified
raw
history blame
8.88 kB
# 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.
import datetime
import os
import datasets
import evaluate
from seametrics.user_friendly.utils import calculate_from_payload
import wandb
_CITATION = """\
@InProceedings{huggingface:module,
title = {A great new module},
authors={huggingface, Inc.},
year={2020}
}\
@article{milan2016mot16,
title={MOT16: A benchmark for multi-object tracking},
author={Milan, Anton and Leal-Taix{\'e}, Laura and Reid, Ian and Roth, Stefan and Schindler, Konrad},
journal={arXiv preprint arXiv:1603.00831},
year={2016}
}
"""
_DESCRIPTION = """\
The MOT Metrics module is designed to evaluate multi-object tracking (MOT)
algorithms by computing various metrics based on predicted and ground truth bounding
boxes. It serves as a crucial tool in assessing the performance of MOT systems,
aiding in the iterative improvement of tracking algorithms."""
_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.
max_iou (`float`, *optional*):
If specified, this is the minimum Intersection over Union (IoU) threshold to consider a detection as a true positive.
Default is 0.5.
"""
@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class UserFriendlyMetrics(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"))
),
}
),
# 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,
payload,
max_iou: float = 0.5,
filters={},
recognition_thresholds=[0.3, 0.5, 0.8],
debug: bool = False,
):
"""Returns the scores"""
# TODO: Compute the different scores of the module
return dummy_values()
# return calculate(predictions, references, max_iou)
def dummy_values():
return {
"model_1": {
"overall": {
"all": {
"tp": 50,
"fp": 20,
"fn": 10,
"precision": 0.71,
"recall": 0.83,
"f1": 0.76
},
"small": {
"tp": 15,
"fp": 5,
"fn": 2,
"precision": 0.75,
"recall": 0.88,
"f1": 0.81
},
"medium": {
"tp": 25,
"fp": 10,
"fn": 5,
"precision": 0.71,
"recall": 0.83,
"f1": 0.76
},
"large": {
"tp": 10,
"fp": 5,
"fn": 3,
"precision": 0.67,
"recall": 0.77,
"f1": 0.71
}
},
"per_sequence": {
"sequence_1": {
"all": {
"tp": 30,
"fp": 15,
"fn": 7,
"precision": 0.67,
"recall": 0.81,
"f1": 0.73
},
"small": {
"tp": 10,
"fp": 3,
"fn": 1,
"precision": 0.77,
"recall": 0.91,
"f1": 0.83
},
"medium": {
"tp": 15,
"fp": 7,
"fn": 2,
"precision": 0.68,
"recall": 0.88,
"f1": 0.77
},
"large": {
"tp": 5,
"fp": 2,
"fn": 1,
"precision": 0.71,
"recall": 0.83,
"f1": 0.76
}
}
}
},
"model_2": {
"overall": {
"all": {
"tp": 60,
"fp": 25,
"fn": 15,
"precision": 0.71,
"recall": 0.80,
"f1": 0.75
},
"small": {
"tp": 20,
"fp": 6,
"fn": 3,
"precision": 0.77,
"recall": 0.87,
"f1": 0.82
},
"medium": {
"tp": 30,
"fp": 12,
"fn": 5,
"precision": 0.71,
"recall": 0.86,
"f1": 0.78
},
"large": {
"tp": 10,
"fp": 7,
"fn": 5,
"precision": 0.59,
"recall": 0.67,
"f1": 0.63
}
},
"per_sequence": {
"sequence_1": {
"all": {
"tp": 40,
"fp": 18,
"fn": 8,
"precision": 0.69,
"recall": 0.83,
"f1": 0.75
},
"small": {
"tp": 12,
"fp": 4,
"fn": 2,
"precision": 0.75,
"recall": 0.86,
"f1": 0.80
},
"medium": {
"tp": 20,
"fp": 8,
"fn": 3,
"precision": 0.71,
"recall": 0.87,
"f1": 0.78
},
"large": {
"tp": 8,
"fp": 6,
"fn": 3,
"precision": 0.57,
"recall": 0.73,
"f1": 0.64
}
}
}
}
}