Python json_dataset_evaluator.evaluate_boxes方法代码示例

# 需要导入模块: from datasets import json_dataset_evaluator [as 别名]
# 或者: from datasets.json_dataset_evaluator import evaluate_boxes [as 别名]
def evaluate_all(
    dataset, all_boxes, all_segms, all_keyps, output_dir, use_matlab=False
):
    """Evaluate "all" tasks, where "all" includes box detection, instance
    segmentation, and keypoint detection.
    """
    all_results = evaluate_boxes(
        dataset, all_boxes, output_dir, use_matlab=use_matlab
    )
    logger.info('Evaluating bounding boxes is done!')
    if cfg.MODEL.MASK_ON:
        results = evaluate_masks(dataset, all_boxes, all_segms, output_dir)
        all_results[dataset.name].update(results[dataset.name])
        logger.info('Evaluating segmentations is done!')
    if cfg.MODEL.KEYPOINTS_ON:
        results = evaluate_keypoints(dataset, all_boxes, all_keyps, output_dir)
        all_results[dataset.name].update(results[dataset.name])
        logger.info('Evaluating keypoints is done!')
    return all_results 

# 需要导入模块: from datasets import json_dataset_evaluator [as 别名]
# 或者: from datasets.json_dataset_evaluator import evaluate_boxes [as 别名]
def evaluate_boxes(dataset, all_boxes, output_dir, test_corloc=False, use_matlab=False):
    """Evaluate bounding box detection."""
    logger.info('Evaluating detections')
    not_comp = not cfg.TEST.COMPETITION_MODE
    if _use_json_dataset_evaluator(dataset):
        coco_eval = json_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, use_salt=not_comp, cleanup=not_comp
        )
        box_results = _coco_eval_to_box_results(coco_eval)
    elif _use_voc_evaluator(dataset):
        # For VOC, always use salt and always cleanup because results are
        # written to the shared VOCdevkit results directory
        voc_eval = voc_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, test_corloc=test_corloc,
            use_matlab=use_matlab
        )
        box_results = _voc_eval_to_box_results(voc_eval)
    else:
        raise NotImplementedError(
            'No evaluator for dataset: {}'.format(dataset.name)
        )
    return OrderedDict([(dataset.name, box_results)]) 

# 需要导入模块: from datasets import json_dataset_evaluator [as 别名]
# 或者: from datasets.json_dataset_evaluator import evaluate_boxes [as 别名]
def evaluate_all(
    dataset, all_boxes, all_segms, all_keyps, output_dir, use_matlab=False
):
    """Evaluate "all" tasks, where "all" includes box detection, instance
    segmentation.
    """
    all_results = evaluate_boxes(
        dataset, all_boxes, output_dir, use_matlab=use_matlab
    )
    logger.info('Evaluating bounding boxes is done!')
    if cfg.MODEL.MASK_ON:
        results = evaluate_masks(dataset, all_boxes, all_segms, output_dir)
        all_results[dataset.name].update(results[dataset.name])
        logger.info('Evaluating segmentations is done!')
    
    return all_results 

# 需要导入模块: from datasets import json_dataset_evaluator [as 别名]
# 或者: from datasets.json_dataset_evaluator import evaluate_boxes [as 别名]
def evaluate_boxes(dataset, all_boxes, output_dir, use_matlab=False):
    """Evaluate bounding box detection."""
    logger.info('Evaluating detections')
    not_comp = not cfg.TEST.COMPETITION_MODE
    if _use_json_dataset_evaluator(dataset):
        coco_eval = json_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, use_salt=not_comp, cleanup=not_comp
        )
        box_results = _coco_eval_to_box_results(coco_eval)
    elif _use_cityscapes_evaluator(dataset):
        logger.warn('Cityscapes bbox evaluated using COCO metrics/conversions')
        coco_eval = json_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, use_salt=not_comp, cleanup=not_comp
        )
        box_results = _coco_eval_to_box_results(coco_eval)
    elif _use_voc_evaluator(dataset):
        # For VOC, always use salt and always cleanup because results are
        # written to the shared VOCdevkit results directory
        voc_eval = voc_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, use_matlab=use_matlab
        )
        box_results = _voc_eval_to_box_results(voc_eval)
    else:
        raise NotImplementedError(
            'No evaluator for dataset: {}'.format(dataset.name)
        )
    return OrderedDict([(dataset.name, box_results)]) 

# 需要导入模块: from datasets import json_dataset_evaluator [as 别名]
# 或者: from datasets.json_dataset_evaluator import evaluate_boxes [as 别名]
def evaluate_all(
    dataset, all_boxes, output_dir, test_corloc=False, use_matlab=False
):
    """Evaluate "all" tasks, where "all" includes box detection, instance
    segmentation, and keypoint detection.
    """
    all_results = evaluate_boxes(
        dataset, all_boxes, output_dir, test_corloc=test_corloc,
        use_matlab=use_matlab
    )
    logger.info('Evaluating bounding boxes is done!')
    return all_results 

# 需要导入模块: from datasets import json_dataset_evaluator [as 别名]
# 或者: from datasets.json_dataset_evaluator import evaluate_boxes [as 别名]
def evaluate_boxes(dataset, all_boxes, output_dir, use_matlab=False):
    """Evaluate bounding box detection."""
    logger.info('Evaluating detections')
    not_comp = not cfg.TEST.COMPETITION_MODE
    if _use_json_dataset_evaluator(dataset):
        coco_eval = json_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, use_salt=not_comp, cleanup=not_comp
        )
        box_results = _coco_eval_to_box_results(coco_eval)
    elif _use_cityscapes_evaluator(dataset):
        logger.warn('Cityscapes bbox evaluated using COCO metrics/conversions')
        coco_eval = json_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, use_salt=not_comp, cleanup=not_comp
        )
        box_results = _coco_eval_to_box_results(coco_eval)
    elif _use_vg_evaluator(dataset):
        logger.warn('Visual Genome bbox evaluated using COCO metrics/conversions')
        coco_eval = json_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, use_salt=not_comp, cleanup=not_comp
        )
        box_results = _coco_eval_to_box_results(coco_eval)
    elif _use_voc_evaluator(dataset):
        # For VOC, always use salt and always cleanup because results are
        # written to the shared VOCdevkit results directory
        voc_eval = voc_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, use_matlab=use_matlab
        )
        box_results = _voc_eval_to_box_results(voc_eval)
    else:
        raise NotImplementedError(
            'No evaluator for dataset: {}'.format(dataset.name)
        )
    return OrderedDict([(dataset.name, box_results)]) 

# 需要导入模块: from datasets import json_dataset_evaluator [as 别名]
# 或者: from datasets.json_dataset_evaluator import evaluate_boxes [as 别名]
def evaluate_boxes(dataset, all_boxes, output_dir, use_matlab=False):
    """Evaluate bounding box detection."""
    logger.info('Evaluating detections')
    not_comp = not cfg.TEST.COMPETITION_MODE
    if _use_json_dataset_evaluator(dataset):
        coco_eval = json_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, use_salt=not_comp, cleanup=not_comp
        )
        box_results = _coco_eval_to_box_results(coco_eval)
    elif _use_cityscapes_evaluator(dataset):
        logger.warn('Cityscapes bbox evaluated using COCO metrics/conversions')
        coco_eval = json_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, use_salt=not_comp, cleanup=not_comp
        )
        box_results = _coco_eval_to_box_results(coco_eval)
    elif _use_voc_evaluator(dataset):
        # For VOC, always use salt and always cleanup because results are
        # written to the shared VOCdevkit results directory
        voc_eval = voc_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, use_matlab=use_matlab
        )
        box_results = _voc_eval_to_box_results(voc_eval)
    elif _use_no_evaluator(dataset):
        box_results = _empty_box_results()
    else:
        raise NotImplementedError(
            'No evaluator for dataset: {}'.format(dataset.name)
        )
    return OrderedDict([(dataset.name, box_results)]) 

# 需要导入模块: from datasets import json_dataset_evaluator [as 别名]
# 或者: from datasets.json_dataset_evaluator import evaluate_boxes [as 别名]
def evaluate_all(
    dataset, all_boxes, all_segms, all_keyps, all_hois, all_keyps_vcoco, output_dir, use_matlab=False
):
    """Evaluate "all" tasks, where "all" includes box detection, instance
    segmentation, and keypoint detection.
    """
    all_results = evaluate_boxes(
        dataset, all_boxes, output_dir, use_matlab=use_matlab
    )
    logger.info('Evaluating bounding boxes is done!')
    if cfg.MODEL.MASK_ON:
        results = evaluate_masks(dataset, all_boxes, all_segms, output_dir)
        all_results[dataset.name].update(results[dataset.name])
        logger.info('Evaluating segmentations is done!')
    if cfg.MODEL.KEYPOINTS_ON:
        results = evaluate_keypoints(dataset, all_boxes, all_keyps, output_dir)
        all_results[dataset.name].update(results[dataset.name])
        logger.info('Evaluating keypoints is done!')
    if cfg.MODEL.VCOCO_ON:
        results = evaluate_hoi_vcoco(dataset, all_hois, output_dir)
        #all_results[dataset.name].update(results[dataset.name])
        # if cfg.VCOCO.KEYPOINTS_ON:
            # results = evaluate_keypoints(dataset, all_boxes, all_keyps_vcoco, output_dir)
            # all_results[dataset.name].update(results[dataset.name])
        logger.info('Evaluating hois is done!')
    return all_results 

# 需要导入模块: from datasets import json_dataset_evaluator [as 别名]
# 或者: from datasets.json_dataset_evaluator import evaluate_boxes [as 别名]
def evaluate_boxes(dataset, all_boxes, output_dir, use_matlab=False):
    """Evaluate bounding box detection."""
    logger.info('Evaluating detections')
    not_comp = not cfg.TEST.COMPETITION_MODE
    if _use_json_dataset_evaluator(dataset):
        coco_eval = json_dataset_evaluator.evaluate_boxes(
            dataset, all_boxes, output_dir, use_salt=not_comp, cleanup=not_comp
        )
        box_results = _coco_eval_to_box_results(coco_eval)
    else:
        raise NotImplementedError(
            'No evaluator for dataset: {}'.format(dataset.name)
        )
    return OrderedDict([(dataset.name, box_results)]) 

# 需要导入模块: from datasets import json_dataset_evaluator [as 别名]
# 或者: from datasets.json_dataset_evaluator import evaluate_boxes [as 别名]
def eval_json(det_json,gt_json):
    json_dataset = JsonDataset(gt_dataset_name)
    gt_json = dataset_catalog.DATASETS[gt_dataset_name]['annotation_file']
    with open(det_json,'rb') as f:
        det = json.load(f)
    f.close()
    with open(gt_json,'rb') as f:
        gt = json.load(f)
    f.close()

    # convert det to the all_boxes list
    num_images = len(gt['images'])
    num_classes = 2
    print('Total number of images:',len(det['images']))
    all_boxes, all_segms, all_keyps = empty_results(num_classes,num_images)
    for cls in range(num_classes):
        for image in range(num_images):
            filename = gt['images'][image]['file_name']
            fid = gt['images'][image]['id']
            img_prop = get_by_filename(det,filename)
            if not (img_prop is None):
                img_id,det_prop = img_prop
                boxes = get_boxes_by_img_id(det,img_id)
                if image%100 == 0:
                    print('Reading detections for:',filename,'--',det_prop['file_name'])
                    print('Det json:',det_json)
                if 'score' in boxes[0]:
                    boxes = np.array([b['bbox']+[b['score']] for b in boxes])
                else:
                    boxes = np.array([b['bbox'] for b in boxes])
                if len(boxes) > 0:
                    # add w, h to get (x2,y2)
                    boxes[:,2] += boxes[:,0]
                    boxes[:,3] += boxes[:,1]
                    all_boxes[cls][image] = boxes
            else:
                all_boxes[cls][image] = []
    # save detections
    with open(os.path.join(output_dir,'detections.pkl'),'wb') as f:
        pickle.dump(dict(all_boxes=all_boxes,all_segms=all_segms,all_keyps=all_keyps),f)
    f.close()
    #input(len(all_boxes[0]))
    coco_eval = evaluate_boxes(json_dataset,all_boxes,output_dir)
    #coco_eval = task_evaluation.evaluate_all(json_dataset,all_boxes,all_segms,all_keyps,output_dir)

    disp_detection_eval_metrics(json_dataset, coco_eval, iou_low=0.5, iou_high=0.5, output_dir=output_dir)
    disp_detection_eval_metrics(json_dataset, coco_eval, iou_low=0.75, iou_high=0.75, output_dir=output_dir)
    disp_detection_eval_metrics(json_dataset, coco_eval, iou_low=0.5, iou_high=0.95, output_dir=output_dir)