:py:mod:`kwcoco.metrics.detect_metrics` ======================================= .. py:module:: kwcoco.metrics.detect_metrics Module Contents --------------- Classes ~~~~~~~ .. autoapisummary:: kwcoco.metrics.detect_metrics.DetectionMetrics Functions ~~~~~~~~~ .. autoapisummary:: kwcoco.metrics.detect_metrics._demo_construct_probs kwcoco.metrics.detect_metrics.pycocotools_confusion_vectors kwcoco.metrics.detect_metrics.eval_detections_cli kwcoco.metrics.detect_metrics._summarize kwcoco.metrics.detect_metrics.pct_summarize2 .. py:class:: DetectionMetrics(dmet, classes=None) Bases: :py:obj:`ubelt.NiceRepr` Object that computes associations between detections and can convert them into sklearn-compatible representations for scoring. :ivar gid_to_true_dets: maps image ids to truth :vartype gid_to_true_dets: Dict :ivar gid_to_pred_dets: maps image ids to predictions :vartype gid_to_pred_dets: Dict :ivar classes: category coder :vartype classes: CategoryTree .. rubric:: Example >>> dmet = DetectionMetrics.demo( >>> nimgs=100, nboxes=(0, 3), n_fp=(0, 1), classes=8, score_noise=0.9, hacked=False) >>> print(dmet.score_kwcoco(bias=0, compat='mutex', prioritize='iou')['mAP']) ... >>> # NOTE: IN GENERAL NETHARN AND VOC ARE NOT THE SAME >>> print(dmet.score_voc(bias=0)['mAP']) 0.8582... >>> #print(dmet.score_coco()['mAP']) .. py:attribute:: score_coco .. py:method:: clear(dmet) .. py:method:: __nice__(dmet) .. py:method:: from_coco(DetectionMetrics, true_coco, pred_coco, gids=None, verbose=0) :classmethod: Create detection metrics from two coco files representing the truth and predictions. :Parameters: * **true_coco** (*kwcoco.CocoDataset*) * **pred_coco** (*kwcoco.CocoDataset*) .. rubric:: Example >>> import kwcoco >>> from kwcoco.demo.perterb import perterb_coco >>> true_coco = kwcoco.CocoDataset.demo('shapes') >>> perterbkw = dict(box_noise=0.5, cls_noise=0.5, score_noise=0.5) >>> pred_coco = perterb_coco(true_coco, **perterbkw) >>> self = DetectionMetrics.from_coco(true_coco, pred_coco) >>> self.score_voc() .. py:method:: _register_imagename(dmet, imgname, gid=None) .. py:method:: add_predictions(dmet, pred_dets, imgname=None, gid=None) Register/Add predicted detections for an image :Parameters: * **pred_dets** (*Detections*) -- predicted detections * **imgname** (*str*) -- a unique string to identify the image * **gid** (*int, optional*) -- the integer image id if known .. py:method:: add_truth(dmet, true_dets, imgname=None, gid=None) Register/Add groundtruth detections for an image :Parameters: * **true_dets** (*Detections*) -- groundtruth * **imgname** (*str*) -- a unique string to identify the image * **gid** (*int, optional*) -- the integer image id if known .. py:method:: true_detections(dmet, gid) gets Detections representation for groundtruth in an image .. py:method:: pred_detections(dmet, gid) gets Detections representation for predictions in an image .. py:method:: confusion_vectors(dmet, iou_thresh=0.5, bias=0, gids=None, compat='mutex', prioritize='iou', ignore_classes='ignore', background_class=ub.NoParam, verbose='auto', workers=0, track_probs='try', max_dets=None) Assigns predicted boxes to the true boxes so we can transform the detection problem into a classification problem for scoring. :Parameters: * **iou_thresh** (*float | List[float], default=0.5*) -- bounding box overlap iou threshold required for assignment if a list, then return type is a dict * **bias** (*float, default=0.0*) -- for computing bounding box overlap, either 1 or 0 * **gids** (*List[int], default=None*) -- which subset of images ids to compute confusion metrics on. If not specified all images are used. * **compat** (*str, default='all'*) -- can be ('ancestors' | 'mutex' | 'all'). determines which pred boxes are allowed to match which true boxes. If 'mutex', then pred boxes can only match true boxes of the same class. If 'ancestors', then pred boxes can match true boxes that match or have a coarser label. If 'all', then any pred can match any true, regardless of its category label. * **prioritize** (*str, default='iou'*) -- can be ('iou' | 'class' | 'correct') determines which box to assign to if mutiple true boxes overlap a predicted box. if prioritize is iou, then the true box with maximum iou (above iou_thresh) will be chosen. If prioritize is class, then it will prefer matching a compatible class above a higher iou. If prioritize is correct, then ancestors of the true class are preferred over descendents of the true class, over unreleated classes. * **ignore_classes** (*set, default={'ignore'}*) -- class names indicating ignore regions * **background_class** (*str, default=ub.NoParam*) -- Name of the background class. If unspecified we try to determine it with heuristics. A value of None means there is no background class. * **verbose** (*int, default='auto'*) -- verbosity flag. In auto mode, verbose=1 if len(gids) > 1000. * **workers** (*int, default=0*) -- number of parallel assignment processes * **track_probs** (*str, default='try'*) -- can be 'try', 'force', or False. if truthy, we assume probabilities for multiple classes are available. :returns: ConfusionVectors | Dict[float, ConfusionVectors] .. rubric:: Example >>> dmet = DetectionMetrics.demo(nimgs=30, classes=3, >>> nboxes=10, n_fp=3, box_noise=10, >>> with_probs=False) >>> iou_to_cfsn = dmet.confusion_vectors(iou_thresh=[0.3, 0.5, 0.9]) >>> for t, cfsn in iou_to_cfsn.items(): >>> print('t = {!r}'.format(t)) ... print(cfsn.binarize_ovr().measures()) ... print(cfsn.binarize_classless().measures()) .. py:method:: score_kwant(dmet, iou_thresh=0.5) Scores the detections using kwant .. py:method:: score_kwcoco(dmet, iou_thresh=0.5, bias=0, gids=None, compat='all', prioritize='iou') our scoring method .. py:method:: score_voc(dmet, iou_thresh=0.5, bias=1, method='voc2012', gids=None, ignore_classes='ignore') score using voc method .. rubric:: Example >>> dmet = DetectionMetrics.demo( >>> nimgs=100, nboxes=(0, 3), n_fp=(0, 1), classes=8, >>> score_noise=.5) >>> print(dmet.score_voc()['mAP']) 0.9399... .. py:method:: _to_coco(dmet) Convert to a coco representation of truth and predictions with inverse aid mappings .. py:method:: score_pycocotools(dmet, with_evaler=False, with_confusion=False, verbose=0, iou_thresholds=None) score using ms-coco method :returns: dictionary with pct info :rtype: Dict .. rubric:: Example >>> # xdoctest: +REQUIRES(module:pycocotools) >>> from kwcoco.metrics.detect_metrics import * >>> dmet = DetectionMetrics.demo( >>> nimgs=10, nboxes=(0, 3), n_fn=(0, 1), n_fp=(0, 1), classes=8, with_probs=False) >>> pct_info = dmet.score_pycocotools(verbose=1, >>> with_evaler=True, >>> with_confusion=True, >>> iou_thresholds=[0.5, 0.9]) >>> evaler = pct_info['evaler'] >>> iou_to_cfsn_vecs = pct_info['iou_to_cfsn_vecs'] >>> for iou_thresh in iou_to_cfsn_vecs.keys(): >>> print('iou_thresh = {!r}'.format(iou_thresh)) >>> cfsn_vecs = iou_to_cfsn_vecs[iou_thresh] >>> ovr_measures = cfsn_vecs.binarize_ovr().measures() >>> print('ovr_measures = {}'.format(ub.repr2(ovr_measures, nl=1, precision=4))) .. note:: by default pycocotools computes average precision as the literal average of computed precisions at 101 uniformly spaced recall thresholds. pycocoutils seems to only allow predictions with the same category as the truth to match those truth objects. This should be the same as calling dmet.confusion_vectors with compat = mutex pycocoutils does not take into account the fact that each box often has a score for each category. pycocoutils will be incorrect if any annotation has an id of 0 a major difference in the way kwcoco scores versus pycocoutils is the calculation of AP. The assignment between truth and predicted detections produces similar enough results. Given our confusion vectors we use the scikit-learn definition of AP, whereas pycocoutils seems to compute precision and recall --- more or less correctly --- but then it resamples the precision at various specified recall thresholds (in the `accumulate` function, specifically how `pr` is resampled into the `q` array). This can lead to a large difference in reported scores. pycocoutils also smooths out the precision such that it is monotonic decreasing, which might not be the best idea. pycocotools area ranges are inclusive on both ends, that means the "small" and "medium" truth selections do overlap somewhat. .. py:method:: demo(cls, **kwargs) :classmethod: Creates random true boxes and predicted boxes that have some noisy offset from the truth. Kwargs: classes (int, default=1): class list or the number of foreground classes. nimgs (int, default=1): number of images in the coco datasts. nboxes (int, default=1): boxes per image. n_fp (int, default=0): number of false positives. n_fn (int, default=0): number of false negatives. box_noise (float, default=0): std of a normal distribution used to perterb both box location and box size. cls_noise (float, default=0): probability that a class label will change. Must be within 0 and 1. anchors (ndarray, default=None): used to create random boxes null_pred (bool, default=0): if True, predicted classes are returned as null, which means only localization scoring is suitable. with_probs (bool, default=1): if True, includes per-class probabilities with predictions .. rubric:: CommandLine .. code-block:: bash xdoctest -m kwcoco.metrics.detect_metrics DetectionMetrics.demo:2 --show .. rubric:: Example >>> kwargs = {} >>> # Seed the RNG >>> kwargs['rng'] = 0 >>> # Size parameters determine how big the data is >>> kwargs['nimgs'] = 5 >>> kwargs['nboxes'] = 7 >>> kwargs['classes'] = 11 >>> # Noise parameters perterb predictions further from the truth >>> kwargs['n_fp'] = 3 >>> kwargs['box_noise'] = 0.1 >>> kwargs['cls_noise'] = 0.5 >>> dmet = DetectionMetrics.demo(**kwargs) >>> print('dmet.classes = {}'.format(dmet.classes)) dmet.classes = >>> # Can grab kwimage.Detection object for any image >>> print(dmet.true_detections(gid=0)) >>> print(dmet.pred_detections(gid=0)) .. rubric:: Example >>> # Test case with null predicted categories >>> dmet = DetectionMetrics.demo(nimgs=30, null_pred=1, classes=3, >>> nboxes=10, n_fp=3, box_noise=0.1, >>> with_probs=False) >>> dmet.gid_to_pred_dets[0].data >>> dmet.gid_to_true_dets[0].data >>> cfsn_vecs = dmet.confusion_vectors() >>> binvecs_ovr = cfsn_vecs.binarize_ovr() >>> binvecs_per = cfsn_vecs.binarize_classless() >>> measures_per = binvecs_per.measures() >>> measures_ovr = binvecs_ovr.measures() >>> print('measures_per = {!r}'.format(measures_per)) >>> print('measures_ovr = {!r}'.format(measures_ovr)) >>> # xdoctest: +REQUIRES(--show) >>> import kwplot >>> kwplot.autompl() >>> measures_ovr['perclass'].draw(key='pr', fnum=2) .. rubric:: Example >>> from kwcoco.metrics.confusion_vectors import * # NOQA >>> from kwcoco.metrics.detect_metrics import DetectionMetrics >>> dmet = DetectionMetrics.demo( >>> n_fp=(0, 1), n_fn=(0, 1), nimgs=32, nboxes=(0, 16), >>> classes=3, rng=0, newstyle=1, box_noise=0.5, cls_noise=0.0, score_noise=0.3, with_probs=False) >>> # xdoctest: +REQUIRES(--show) >>> import kwplot >>> kwplot.autompl() >>> summary = dmet.summarize(plot=True, title='DetectionMetrics summary demo', with_ovr=True, with_bin=False) >>> summary['bin_measures'] >>> kwplot.show_if_requested() .. py:method:: summarize(dmet, out_dpath=None, plot=False, title='', with_bin='auto', with_ovr='auto') .. rubric:: Example >>> from kwcoco.metrics.confusion_vectors import * # NOQA >>> from kwcoco.metrics.detect_metrics import DetectionMetrics >>> dmet = DetectionMetrics.demo( >>> n_fp=(0, 128), n_fn=(0, 4), nimgs=512, nboxes=(0, 32), >>> classes=3, rng=0) >>> # xdoctest: +REQUIRES(--show) >>> import kwplot >>> kwplot.autompl() >>> dmet.summarize(plot=True, title='DetectionMetrics summary demo') >>> kwplot.show_if_requested() .. py:function:: _demo_construct_probs(pred_cxs, pred_scores, classes, rng, hacked=1) Constructs random probabilities for demo data .. py:function:: pycocotools_confusion_vectors(dmet, evaler, iou_thresh=0.5, verbose=0) .. rubric:: Example >>> # xdoctest: +REQUIRES(module:pycocotools) >>> from kwcoco.metrics.detect_metrics import * >>> dmet = DetectionMetrics.demo( >>> nimgs=10, nboxes=(0, 3), n_fn=(0, 1), n_fp=(0, 1), classes=8, with_probs=False) >>> coco_scores = dmet.score_pycocotools(with_evaler=True) >>> evaler = coco_scores['evaler'] >>> cfsn_vecs = pycocotools_confusion_vectors(dmet, evaler, verbose=1) .. py:function:: eval_detections_cli(**kw) DEPRECATED USE `kwcoco eval` instead .. rubric:: CommandLine .. code-block:: bash xdoctest -m ~/code/kwcoco/kwcoco/metrics/detect_metrics.py eval_detections_cli .. py:function:: _summarize(self, ap=1, iouThr=None, areaRngLbl='all', maxDets=100) .. py:function:: pct_summarize2(self)