Shortcuts

mmdet.core.evaluation.mean_ap 源代码

# Copyright (c) OpenMMLab. All rights reserved.
from multiprocessing import Pool

import mmcv
import numpy as np
from mmcv.utils import print_log
from terminaltables import AsciiTable

from .bbox_overlaps import bbox_overlaps
from .class_names import get_classes


[文档]def average_precision(recalls, precisions, mode='area'): """Calculate average precision (for single or multiple scales). Args: recalls (ndarray): shape (num_scales, num_dets) or (num_dets, ) precisions (ndarray): shape (num_scales, num_dets) or (num_dets, ) mode (str): 'area' or '11points', 'area' means calculating the area under precision-recall curve, '11points' means calculating the average precision of recalls at [0, 0.1, ..., 1] Returns: float or ndarray: calculated average precision """ no_scale = False if recalls.ndim == 1: no_scale = True recalls = recalls[np.newaxis, :] precisions = precisions[np.newaxis, :] assert recalls.shape == precisions.shape and recalls.ndim == 2 num_scales = recalls.shape[0] ap = np.zeros(num_scales, dtype=np.float32) if mode == 'area': zeros = np.zeros((num_scales, 1), dtype=recalls.dtype) ones = np.ones((num_scales, 1), dtype=recalls.dtype) mrec = np.hstack((zeros, recalls, ones)) mpre = np.hstack((zeros, precisions, zeros)) for i in range(mpre.shape[1] - 1, 0, -1): mpre[:, i - 1] = np.maximum(mpre[:, i - 1], mpre[:, i]) for i in range(num_scales): ind = np.where(mrec[i, 1:] != mrec[i, :-1])[0] ap[i] = np.sum( (mrec[i, ind + 1] - mrec[i, ind]) * mpre[i, ind + 1]) elif mode == '11points': for i in range(num_scales): for thr in np.arange(0, 1 + 1e-3, 0.1): precs = precisions[i, recalls[i, :] >= thr] prec = precs.max() if precs.size > 0 else 0 ap[i] += prec ap /= 11 else: raise ValueError( 'Unrecognized mode, only "area" and "11points" are supported') if no_scale: ap = ap[0] return ap
def tpfp_imagenet(det_bboxes, gt_bboxes, gt_bboxes_ignore=None, default_iou_thr=0.5, area_ranges=None, use_legacy_coordinate=False): """Check if detected bboxes are true positive or false positive. Args: det_bbox (ndarray): Detected bboxes of this image, of shape (m, 5). gt_bboxes (ndarray): GT bboxes of this image, of shape (n, 4). gt_bboxes_ignore (ndarray): Ignored gt bboxes of this image, of shape (k, 4). Default: None default_iou_thr (float): IoU threshold to be considered as matched for medium and large bboxes (small ones have special rules). Default: 0.5. area_ranges (list[tuple] | None): Range of bbox areas to be evaluated, in the format [(min1, max1), (min2, max2), ...]. Default: None. use_legacy_coordinate (bool): Whether to use coordinate system in mmdet v1.x. which means width, height should be calculated as 'x2 - x1 + 1` and 'y2 - y1 + 1' respectively. Default: False. Returns: tuple[np.ndarray]: (tp, fp) whose elements are 0 and 1. The shape of each array is (num_scales, m). """ if not use_legacy_coordinate: extra_length = 0. else: extra_length = 1. # an indicator of ignored gts gt_ignore_inds = np.concatenate( (np.zeros(gt_bboxes.shape[0], dtype=np.bool), np.ones(gt_bboxes_ignore.shape[0], dtype=np.bool))) # stack gt_bboxes and gt_bboxes_ignore for convenience gt_bboxes = np.vstack((gt_bboxes, gt_bboxes_ignore)) num_dets = det_bboxes.shape[0] num_gts = gt_bboxes.shape[0] if area_ranges is None: area_ranges = [(None, None)] num_scales = len(area_ranges) # tp and fp are of shape (num_scales, num_gts), each row is tp or fp # of a certain scale. tp = np.zeros((num_scales, num_dets), dtype=np.float32) fp = np.zeros((num_scales, num_dets), dtype=np.float32) if gt_bboxes.shape[0] == 0: if area_ranges == [(None, None)]: fp[...] = 1 else: det_areas = ( det_bboxes[:, 2] - det_bboxes[:, 0] + extra_length) * ( det_bboxes[:, 3] - det_bboxes[:, 1] + extra_length) for i, (min_area, max_area) in enumerate(area_ranges): fp[i, (det_areas >= min_area) & (det_areas < max_area)] = 1 return tp, fp ious = bbox_overlaps( det_bboxes, gt_bboxes - 1, use_legacy_coordinate=use_legacy_coordinate) gt_w = gt_bboxes[:, 2] - gt_bboxes[:, 0] + extra_length gt_h = gt_bboxes[:, 3] - gt_bboxes[:, 1] + extra_length iou_thrs = np.minimum((gt_w * gt_h) / ((gt_w + 10.0) * (gt_h + 10.0)), default_iou_thr) # sort all detections by scores in descending order sort_inds = np.argsort(-det_bboxes[:, -1]) for k, (min_area, max_area) in enumerate(area_ranges): gt_covered = np.zeros(num_gts, dtype=bool) # if no area range is specified, gt_area_ignore is all False if min_area is None: gt_area_ignore = np.zeros_like(gt_ignore_inds, dtype=bool) else: gt_areas = gt_w * gt_h gt_area_ignore = (gt_areas < min_area) | (gt_areas >= max_area) for i in sort_inds: max_iou = -1 matched_gt = -1 # find best overlapped available gt for j in range(num_gts): # different from PASCAL VOC: allow finding other gts if the # best overlapped ones are already matched by other det bboxes if gt_covered[j]: continue elif ious[i, j] >= iou_thrs[j] and ious[i, j] > max_iou: max_iou = ious[i, j] matched_gt = j # there are 4 cases for a det bbox: # 1. it matches a gt, tp = 1, fp = 0 # 2. it matches an ignored gt, tp = 0, fp = 0 # 3. it matches no gt and within area range, tp = 0, fp = 1 # 4. it matches no gt but is beyond area range, tp = 0, fp = 0 if matched_gt >= 0: gt_covered[matched_gt] = 1 if not (gt_ignore_inds[matched_gt] or gt_area_ignore[matched_gt]): tp[k, i] = 1 elif min_area is None: fp[k, i] = 1 else: bbox = det_bboxes[i, :4] area = (bbox[2] - bbox[0] + extra_length) * ( bbox[3] - bbox[1] + extra_length) if area >= min_area and area < max_area: fp[k, i] = 1 return tp, fp def tpfp_default(det_bboxes, gt_bboxes, gt_bboxes_ignore=None, iou_thr=0.5, area_ranges=None, use_legacy_coordinate=False): """Check if detected bboxes are true positive or false positive. Args: det_bbox (ndarray): Detected bboxes of this image, of shape (m, 5). gt_bboxes (ndarray): GT bboxes of this image, of shape (n, 4). gt_bboxes_ignore (ndarray): Ignored gt bboxes of this image, of shape (k, 4). Default: None iou_thr (float): IoU threshold to be considered as matched. Default: 0.5. area_ranges (list[tuple] | None): Range of bbox areas to be evaluated, in the format [(min1, max1), (min2, max2), ...]. Default: None. use_legacy_coordinate (bool): Whether to use coordinate system in mmdet v1.x. which means width, height should be calculated as 'x2 - x1 + 1` and 'y2 - y1 + 1' respectively. Default: False. Returns: tuple[np.ndarray]: (tp, fp) whose elements are 0 and 1. The shape of each array is (num_scales, m). """ if not use_legacy_coordinate: extra_length = 0. else: extra_length = 1. # an indicator of ignored gts gt_ignore_inds = np.concatenate( (np.zeros(gt_bboxes.shape[0], dtype=np.bool), np.ones(gt_bboxes_ignore.shape[0], dtype=np.bool))) # stack gt_bboxes and gt_bboxes_ignore for convenience gt_bboxes = np.vstack((gt_bboxes, gt_bboxes_ignore)) num_dets = det_bboxes.shape[0] num_gts = gt_bboxes.shape[0] if area_ranges is None: area_ranges = [(None, None)] num_scales = len(area_ranges) # tp and fp are of shape (num_scales, num_gts), each row is tp or fp of # a certain scale tp = np.zeros((num_scales, num_dets), dtype=np.float32) fp = np.zeros((num_scales, num_dets), dtype=np.float32) # if there is no gt bboxes in this image, then all det bboxes # within area range are false positives if gt_bboxes.shape[0] == 0: if area_ranges == [(None, None)]: fp[...] = 1 else: det_areas = ( det_bboxes[:, 2] - det_bboxes[:, 0] + extra_length) * ( det_bboxes[:, 3] - det_bboxes[:, 1] + extra_length) for i, (min_area, max_area) in enumerate(area_ranges): fp[i, (det_areas >= min_area) & (det_areas < max_area)] = 1 return tp, fp ious = bbox_overlaps( det_bboxes, gt_bboxes, use_legacy_coordinate=use_legacy_coordinate) # for each det, the max iou with all gts ious_max = ious.max(axis=1) # for each det, which gt overlaps most with it ious_argmax = ious.argmax(axis=1) # sort all dets in descending order by scores sort_inds = np.argsort(-det_bboxes[:, -1]) for k, (min_area, max_area) in enumerate(area_ranges): gt_covered = np.zeros(num_gts, dtype=bool) # if no area range is specified, gt_area_ignore is all False if min_area is None: gt_area_ignore = np.zeros_like(gt_ignore_inds, dtype=bool) else: gt_areas = (gt_bboxes[:, 2] - gt_bboxes[:, 0] + extra_length) * ( gt_bboxes[:, 3] - gt_bboxes[:, 1] + extra_length) gt_area_ignore = (gt_areas < min_area) | (gt_areas >= max_area) for i in sort_inds: if ious_max[i] >= iou_thr: matched_gt = ious_argmax[i] if not (gt_ignore_inds[matched_gt] or gt_area_ignore[matched_gt]): if not gt_covered[matched_gt]: gt_covered[matched_gt] = True tp[k, i] = 1 else: fp[k, i] = 1 # otherwise ignore this detected bbox, tp = 0, fp = 0 elif min_area is None: fp[k, i] = 1 else: bbox = det_bboxes[i, :4] area = (bbox[2] - bbox[0] + extra_length) * ( bbox[3] - bbox[1] + extra_length) if area >= min_area and area < max_area: fp[k, i] = 1 return tp, fp def get_cls_results(det_results, annotations, class_id): """Get det results and gt information of a certain class. Args: det_results (list[list]): Same as `eval_map()`. annotations (list[dict]): Same as `eval_map()`. class_id (int): ID of a specific class. Returns: tuple[list[np.ndarray]]: detected bboxes, gt bboxes, ignored gt bboxes """ cls_dets = [img_res[class_id] for img_res in det_results] cls_gts = [] cls_gts_ignore = [] for ann in annotations: gt_inds = ann['labels'] == class_id cls_gts.append(ann['bboxes'][gt_inds, :]) if ann.get('labels_ignore', None) is not None: ignore_inds = ann['labels_ignore'] == class_id cls_gts_ignore.append(ann['bboxes_ignore'][ignore_inds, :]) else: cls_gts_ignore.append(np.empty((0, 4), dtype=np.float32)) return cls_dets, cls_gts, cls_gts_ignore
[文档]def eval_map(det_results, annotations, scale_ranges=None, iou_thr=0.5, dataset=None, logger=None, tpfp_fn=None, nproc=4, use_legacy_coordinate=False): """Evaluate mAP of a dataset. Args: det_results (list[list]): [[cls1_det, cls2_det, ...], ...]. The outer list indicates images, and the inner list indicates per-class detected bboxes. annotations (list[dict]): Ground truth annotations where each item of the list indicates an image. Keys of annotations are: - `bboxes`: numpy array of shape (n, 4) - `labels`: numpy array of shape (n, ) - `bboxes_ignore` (optional): numpy array of shape (k, 4) - `labels_ignore` (optional): numpy array of shape (k, ) scale_ranges (list[tuple] | None): Range of scales to be evaluated, in the format [(min1, max1), (min2, max2), ...]. A range of (32, 64) means the area range between (32**2, 64**2). Default: None. iou_thr (float): IoU threshold to be considered as matched. Default: 0.5. dataset (list[str] | str | None): Dataset name or dataset classes, there are minor differences in metrics for different datasets, e.g. "voc07", "imagenet_det", etc. Default: None. logger (logging.Logger | str | None): The way to print the mAP summary. See `mmcv.utils.print_log()` for details. Default: None. tpfp_fn (callable | None): The function used to determine true/ false positives. If None, :func:`tpfp_default` is used as default unless dataset is 'det' or 'vid' (:func:`tpfp_imagenet` in this case). If it is given as a function, then this function is used to evaluate tp & fp. Default None. nproc (int): Processes used for computing TP and FP. Default: 4. use_legacy_coordinate (bool): Whether to use coordinate system in mmdet v1.x. which means width, height should be calculated as 'x2 - x1 + 1` and 'y2 - y1 + 1' respectively. Default: False. Returns: tuple: (mAP, [dict, dict, ...]) """ assert len(det_results) == len(annotations) if not use_legacy_coordinate: extra_length = 0. else: extra_length = 1. num_imgs = len(det_results) num_scales = len(scale_ranges) if scale_ranges is not None else 1 num_classes = len(det_results[0]) # positive class num area_ranges = ([(rg[0]**2, rg[1]**2) for rg in scale_ranges] if scale_ranges is not None else None) pool = Pool(nproc) eval_results = [] for i in range(num_classes): # get gt and det bboxes of this class cls_dets, cls_gts, cls_gts_ignore = get_cls_results( det_results, annotations, i) # choose proper function according to datasets to compute tp and fp if tpfp_fn is None: if dataset in ['det', 'vid']: tpfp_fn = tpfp_imagenet else: tpfp_fn = tpfp_default if not callable(tpfp_fn): raise ValueError( f'tpfp_fn has to be a function or None, but got {tpfp_fn}') # compute tp and fp for each image with multiple processes tpfp = pool.starmap( tpfp_fn, zip(cls_dets, cls_gts, cls_gts_ignore, [iou_thr for _ in range(num_imgs)], [area_ranges for _ in range(num_imgs)], [use_legacy_coordinate for _ in range(num_imgs)])) tp, fp = tuple(zip(*tpfp)) # calculate gt number of each scale # ignored gts or gts beyond the specific scale are not counted num_gts = np.zeros(num_scales, dtype=int) for j, bbox in enumerate(cls_gts): if area_ranges is None: num_gts[0] += bbox.shape[0] else: gt_areas = (bbox[:, 2] - bbox[:, 0] + extra_length) * ( bbox[:, 3] - bbox[:, 1] + extra_length) for k, (min_area, max_area) in enumerate(area_ranges): num_gts[k] += np.sum((gt_areas >= min_area) & (gt_areas < max_area)) # sort all det bboxes by score, also sort tp and fp cls_dets = np.vstack(cls_dets) num_dets = cls_dets.shape[0] sort_inds = np.argsort(-cls_dets[:, -1]) tp = np.hstack(tp)[:, sort_inds] fp = np.hstack(fp)[:, sort_inds] # calculate recall and precision with tp and fp tp = np.cumsum(tp, axis=1) fp = np.cumsum(fp, axis=1) eps = np.finfo(np.float32).eps recalls = tp / np.maximum(num_gts[:, np.newaxis], eps) precisions = tp / np.maximum((tp + fp), eps) # calculate AP if scale_ranges is None: recalls = recalls[0, :] precisions = precisions[0, :] num_gts = num_gts.item() mode = 'area' if dataset != 'voc07' else '11points' ap = average_precision(recalls, precisions, mode) eval_results.append({ 'num_gts': num_gts, 'num_dets': num_dets, 'recall': recalls, 'precision': precisions, 'ap': ap }) pool.close() if scale_ranges is not None: # shape (num_classes, num_scales) all_ap = np.vstack([cls_result['ap'] for cls_result in eval_results]) all_num_gts = np.vstack( [cls_result['num_gts'] for cls_result in eval_results]) mean_ap = [] for i in range(num_scales): if np.any(all_num_gts[:, i] > 0): mean_ap.append(all_ap[all_num_gts[:, i] > 0, i].mean()) else: mean_ap.append(0.0) else: aps = [] for cls_result in eval_results: if cls_result['num_gts'] > 0: aps.append(cls_result['ap']) mean_ap = np.array(aps).mean().item() if aps else 0.0 print_map_summary( mean_ap, eval_results, dataset, area_ranges, logger=logger) return mean_ap, eval_results
Read the Docs v: latest
Versions
latest
stable
v2.19.1
v2.19.0
v2.18.1
v2.18.0
v2.17.0
v2.16.0
v2.15.1
v2.15.0
v2.14.0
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.