cvtools.evaluation package

Submodules

• cvtools.evaluation.bbox_overlaps module
• cvtools.evaluation.class_names module
• cvtools.evaluation.coco_utils module
• cvtools.evaluation.eval_crop module
• cvtools.evaluation.f1_score module
• cvtools.evaluation.mean_ap module
• cvtools.evaluation.merge_dets module
• cvtools.evaluation.recall module

Module contents

cvtools.evaluation.voc_classes()

cvtools.evaluation.imagenet_det_classes()

cvtools.evaluation.imagenet_vid_classes()

cvtools.evaluation.coco_classes()

cvtools.evaluation.get_classes(dataset)

Get class names of a dataset.

cvtools.evaluation.coco_eval(result_files, result_types, coco, max_dets=(100, 300, 1000))

cvtools.evaluation.fast_eval_recall(results, coco, max_dets, iou_thrs=array([0.5, 0.55, 0.6, 0.65, 0.7, 0.75, 0.8, 0.85, 0.9, 0.95]))

cvtools.evaluation.results2json(dataset, results, out_file)

cvtools.evaluation.average_precision(recalls, precisions, mode='area')

Calculate average precision (for single or multiple scales).

参数:

• 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]

返回:

calculated average precision

返回类型:

float or ndarray

cvtools.evaluation.eval_map(det_results, gt_bboxes, gt_labels, gt_ignore=None, scale_ranges=None, iou_thr=0.5, dataset=None, print_summary=True, calc_ious=<function bbox_overlaps>)

Evaluate mAP of a dataset.

参数:

• det_results (list) -- a list of list, [[cls1_det, cls2_det, ...], ...] cls1_det为np.array，包含K*5，包含得分, x1y1x2y2形式
• gt_bboxes (list) -- ground truth bboxes of each image, a list of K*4 array. x1y1x2y2形式
• gt_labels (list) -- ground truth labels of each image, a list of K array
• gt_ignore (list) -- gt ignore indicators of each image, a list of K array
• scale_ranges (list, optional) -- [(min1, max1), (min2, max2), ...]
• iou_thr (float) -- IoU threshold，目前还不支持polyiou
• dataset (None or str or list) -- dataset name or dataset classes, there are minor differences in metrics for different datsets, e.g. "voc07", "imagenet_det", etc.
• print_summary (bool) -- whether to print the mAP summary

返回:

(mAP, [dict, dict, ...])

返回类型:

tuple

cvtools.evaluation.print_map_summary(mean_ap, results, dataset=None)

Print mAP and results of each class.

参数:

• mean_ap (float) -- calculated from eval_map
• results (list) -- calculated from eval_map
• dataset (None or str or list) -- dataset name or dataset classes.

cvtools.evaluation.eval_recalls(gts, proposals, proposal_nums=None, iou_thrs=None, print_summary=True)

Calculate recalls.

参数:

• gts (list or ndarray) -- a list of arrays of shape (n, 4)
• proposals (list or ndarray) -- a list of arrays of shape (k, 4) or (k, 5)
• proposal_nums (int or list of int or ndarray) -- top N proposals
• thrs (float or list or ndarray) -- iou thresholds

返回:

recalls of different ious and proposal nums

返回类型:

ndarray

cvtools.evaluation.print_recall_summary(recalls, proposal_nums, iou_thrs, row_idxs=None, col_idxs=None)

Print recalls in a table.

参数:

• recalls (ndarray) -- calculated from bbox_recalls
• proposal_nums (ndarray or list) -- top N proposals
• iou_thrs (ndarray or list) -- iou thresholds
• row_idxs (ndarray) -- which rows(proposal nums) to print
• col_idxs (ndarray) -- which cols(iou thresholds) to print

cvtools.evaluation.plot_num_recall(recalls, proposal_nums)

Plot Proposal_num-Recalls curve.

参数:

• recalls (ndarray or list) -- shape (k,)
• proposal_nums (ndarray or list) -- same shape as recalls

cvtools.evaluation.plot_iou_recall(recalls, iou_thrs)

Plot IoU-Recalls curve.

参数:

• recalls (ndarray or list) -- shape (k,)
• iou_thrs (ndarray or list) -- same shape as recalls

class cvtools.evaluation.MergeCropDetResults(gts, results, num_coors=4)

基类：object

crop_bbox_map_back(bb, crop_start)

子图检测坐标转换为相对于整图的坐标

img_results_to_cat_results(img_results)

match_part_img_results(results)

结合子图的结果，映射回原图，应用nms, 生成一张整图的结果

merge(nms_method=<function py_cpu_nms>, nms_th=0.15)

参数:

• nms_method -- nms方法必须与bbox表示方式对应， 默认是左上角右下角表示的水平矩形框
• nms_th -- nms阈值

Returns: 合并后的检测结果

{

filename: [bboxes, labels, scores], filename: [bboxes, labels, scores], ...

}

save_dota_det_format(save_path)

class cvtools.evaluation.EvalCropQuality(ann_file, crop_ann_file, results=None, num_coors=4)

基类：object

此类设计目前不够完善，convert_crop_gt应隐藏在内部

eval()

handel_ann(ann)