Python datasets.voc_dataset_evaluator.evaluate_boxes() Examples

The following are 24 code examples of datasets.voc_dataset_evaluator.evaluate_boxes(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module datasets.voc_dataset_evaluator , or try the search function .
Example #1
Source File: task_evaluation.py    From Detectron.pytorch with MIT License 6 votes vote down vote up 
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
Example #2
Source File: task_evaluation.py    From FPN-Pytorch with MIT License 6 votes vote down vote up 
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
Example #3
Source File: task_evaluation.py    From NucleiDetectron with Apache License 2.0 6 votes vote down vote up 
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
Example #4
Source File: task_evaluation.py    From pcl.pytorch with MIT License 6 votes vote down vote up 
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)])
Example #5
Source File: task_evaluation.py    From Detectron.pytorch with MIT License 6 votes vote down vote up 
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
Example #6
Source File: task_evaluation.py    From DIoU-pytorch-detectron with GNU General Public License v3.0 6 votes vote down vote up 
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
Example #7
Source File: task_evaluation.py    From Context-aware-ZSR with MIT License 6 votes vote down vote up 
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
Example #8
Source File: task_evaluation.py    From PANet with MIT License 6 votes vote down vote up 
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
Example #9
Source File: task_evaluation.py    From detectron-self-train with MIT License 6 votes vote down vote up 
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
Example #10
Source File: task_evaluation.py    From seg_every_thing with Apache License 2.0 6 votes vote down vote up 
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
Example #11
Source File: task_evaluation.py    From masktextspotter.caffe2 with Apache License 2.0 6 votes vote down vote up 
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
Example #12
Source File: task_evaluation.py    From NucleiDetectron with Apache License 2.0 5 votes vote down vote up 
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)])
Example #13
Source File: task_evaluation.py    From DIoU-pytorch-detectron with GNU General Public License v3.0 5 votes vote down vote up 
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)])
Example #14
Source File: task_evaluation.py    From detectron-self-train with MIT License 5 votes vote down vote up 
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)])
Example #15
Source File: task_evaluation.py    From masktextspotter.caffe2 with Apache License 2.0 5 votes vote down vote up 
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)])
Example #16
Source File: task_evaluation.py    From PMFNet with MIT License 5 votes vote down vote up 
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)])
Example #17
Source File: task_evaluation.py    From PMFNet with MIT License 5 votes vote down vote up 
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
Example #18
Source File: task_evaluation.py    From seg_every_thing with Apache License 2.0 5 votes vote down vote up 
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)])
Example #19
Source File: task_evaluation.py    From PANet with MIT License 5 votes vote down vote up 
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)])
Example #20
Source File: task_evaluation.py    From Context-aware-ZSR with MIT License 5 votes vote down vote up 
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)])
Example #21
Source File: task_evaluation.py    From Detectron.pytorch with MIT License 5 votes vote down vote up 
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)])
Example #22
Source File: task_evaluation.py    From pcl.pytorch with MIT License 5 votes vote down vote up 
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
Example #23
Source File: task_evaluation.py    From FPN-Pytorch with MIT License 5 votes vote down vote up 
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)])
Example #24
Source File: task_evaluation.py    From Detectron.pytorch with MIT License 5 votes vote down vote up 
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)])