Python mmdet.core.get_classes() Examples

The following are 30 code examples of mmdet.core.get_classes(). 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 mmdet.core , or try the search function .
Example #1
Source File: inference.py    From hrnet with MIT License 6 votes vote down vote up
def re_result(result, dataset='coco', score_thr=0.5):
    '''
    返回human boxes and scores
    '''
    class_names = get_classes(dataset)
    if isinstance(result, tuple):
        bbox_result, segm_result = result
    else:
        bbox_result, segm_result = result, None
    bboxes = np.vstack(bbox_result)
    # bounding boxes
    labels = [
        np.full(bbox.shape[0], i, dtype=np.int32)
        for i, bbox in enumerate(bbox_result)
    ]
    labels = np.concatenate(labels)

    # only for human class
    re_bboxes, re_scores = det_bboxes(bboxes, labels, score_thr=score_thr)

    return re_bboxes, re_scores 
Example #2
Source File: inference.py    From AerialDetection with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #3
Source File: inference.py    From AugFPN with Apache License 2.0 5 votes vote down vote up
def show_result(img, result, dataset='coco', score_thr=0.3, out_file=None):
    img = mmcv.imread(img)
    class_names = get_classes(dataset)
    if isinstance(result, tuple):
        bbox_result, segm_result = result
    else:
        bbox_result, segm_result = result, None
    bboxes = np.vstack(bbox_result)
    # draw segmentation masks
    if segm_result is not None:
        segms = mmcv.concat_list(segm_result)
        inds = np.where(bboxes[:, -1] > score_thr)[0]
        for i in inds:
            color_mask = np.random.randint(
                0, 256, (1, 3), dtype=np.uint8)
            mask = maskUtils.decode(segms[i]).astype(np.bool)
            img[mask] = img[mask] * 0.5 + color_mask * 0.5
    # draw bounding boxes
    labels = [
        np.full(bbox.shape[0], i, dtype=np.int32)
        for i, bbox in enumerate(bbox_result)
    ]
    labels = np.concatenate(labels)
    mmcv.imshow_det_bboxes(
        img.copy(),
        bboxes,
        labels,
        class_names=class_names,
        score_thr=score_thr,
        show=out_file is None) 
Example #4
Source File: inference.py    From ttfnet with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #5
Source File: inference.py    From CenterNet with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #6
Source File: inference.py    From hrnet with MIT License 5 votes vote down vote up
def show_result(img, result, dataset='coco', score_thr=0.5, out_file=None, wait_time=0):
    img = mmcv.imread(img)
    class_names = get_classes(dataset)
    if isinstance(result, tuple):
        bbox_result, segm_result = result
    else:
        bbox_result, segm_result = result, None
    bboxes = np.vstack(bbox_result)
    # draw segmentation masks
    if segm_result is not None:
        segms = mmcv.concat_list(segm_result)
        inds = np.where(bboxes[:, -1] > score_thr)[0]
        for i in inds:
            color_mask = np.random.randint(
                0, 256, (1, 3), dtype=np.uint8)
            mask = maskUtils.decode(segms[i]).astype(np.bool)
            img[mask] = img[mask] * 0.5 + color_mask * 0.5
    # draw bounding boxes
    labels = [
        np.full(bbox.shape[0], i, dtype=np.int32)
        for i, bbox in enumerate(bbox_result)
    ]
    labels = np.concatenate(labels)

    mmcv.imshow_det_bboxes(
        img.copy(),
        bboxes,
        labels,
        class_names=class_names,
        score_thr=score_thr,
        show=out_file is None,
        wait_time=wait_time)

    return re_bboxes, re_scores 
Example #7
Source File: inference.py    From kaggle-imaterialist with MIT License 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['classes']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #8
Source File: inference.py    From Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #9
Source File: inference.py    From Cascade-RPN with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #10
Source File: inference.py    From FoveaBox with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #11
Source File: inference.py    From Libra_R-CNN with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #12
Source File: inference.py    From Reasoning-RCNN with Apache License 2.0 5 votes vote down vote up
def show_result(img, result, dataset='coco', score_thr=0.3):
    class_names = get_classes(dataset)
    labels = [
        np.full(bbox.shape[0], i, dtype=np.int32)
        for i, bbox in enumerate(result)
    ]
    labels = np.concatenate(labels)
    bboxes = np.vstack(result)
    img = mmcv.imread(img)
    mmcv.imshow_det_bboxes(
        img.copy(),
        bboxes,
        labels,
        class_names=class_names,
        score_thr=score_thr) 
Example #13
Source File: inference.py    From IoU-Uniform-R-CNN with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #14
Source File: inference.py    From RDSNet with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #15
Source File: inference.py    From Grid-R-CNN with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['classes']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #16
Source File: inference.py    From kaggle-kuzushiji-recognition with MIT License 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #17
Source File: inference.py    From mmdetection with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        f'but got {type(config)}')
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.simplefilter('once')
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #18
Source File: inference.py    From PolarMask with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #19
Source File: inference.py    From mmdetection_with_SENet154 with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #20
Source File: inference.py    From GCNet with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #21
Source File: inference.py    From mmfashion with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #22
Source File: inference.py    From mmdetection-annotated with Apache License 2.0 5 votes vote down vote up
def init_detector(config, checkpoint=None, device='cuda:0'):
    """Initialize a detector from config file.

    Args:
        config (str or :obj:`mmcv.Config`): Config file path or the config
            object.
        checkpoint (str, optional): Checkpoint path. If left as None, the model
            will not load any weights.

    Returns:
        nn.Module: The constructed detector.
    """
    if isinstance(config, str):
        config = mmcv.Config.fromfile(config)
    elif not isinstance(config, mmcv.Config):
        raise TypeError('config must be a filename or Config object, '
                        'but got {}'.format(type(config)))
    config.model.pretrained = None
    model = build_detector(config.model, test_cfg=config.test_cfg)
    if checkpoint is not None:
        checkpoint = load_checkpoint(model, checkpoint)
        if 'CLASSES' in checkpoint['meta']:
            model.CLASSES = checkpoint['meta']['CLASSES']
        else:
            warnings.warn('Class names are not saved in the checkpoint\'s '
                          'meta data, use COCO classes by default.')
            model.CLASSES = get_classes('coco')
    model.cfg = config  # save the config in the model for convenience
    model.to(device)
    model.eval()
    return model 
Example #23
Source File: base.py    From Cascade-RPN with Apache License 2.0 4 votes vote down vote up
def show_result(self, data, result, dataset=None, score_thr=0.3):
        if isinstance(result, tuple):
            bbox_result, segm_result = result
        else:
            bbox_result, segm_result = result, None

        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_metas[0]['img_norm_cfg'])
        assert len(imgs) == len(img_metas)

        if dataset is None:
            class_names = self.CLASSES
        elif isinstance(dataset, str):
            class_names = get_classes(dataset)
        elif isinstance(dataset, (list, tuple)):
            class_names = dataset
        else:
            raise TypeError(
                'dataset must be a valid dataset name or a sequence'
                ' of class names, not {}'.format(type(dataset)))

        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]

            bboxes = np.vstack(bbox_result)
            # draw segmentation masks
            if segm_result is not None:
                segms = mmcv.concat_list(segm_result)
                inds = np.where(bboxes[:, -1] > score_thr)[0]
                for i in inds:
                    color_mask = np.random.randint(
                        0, 256, (1, 3), dtype=np.uint8)
                    mask = maskUtils.decode(segms[i]).astype(np.bool)
                    img_show[mask] = img_show[mask] * 0.5 + color_mask * 0.5
            # draw bounding boxes
            labels = [
                np.full(bbox.shape[0], i, dtype=np.int32)
                for i, bbox in enumerate(bbox_result)
            ]
            labels = np.concatenate(labels)
            mmcv.imshow_det_bboxes(
                img_show,
                bboxes,
                labels,
                class_names=class_names,
                score_thr=score_thr) 
Example #24
Source File: base.py    From AugFPN with Apache License 2.0 4 votes vote down vote up
def show_result(self,
                    data,
                    result,
                    img_norm_cfg,
                    dataset='coco',
                    score_thr=0.3):
        if isinstance(result, tuple):
            bbox_result, segm_result = result
        else:
            bbox_result, segm_result = result, None

        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)

        if isinstance(dataset, str):
            class_names = get_classes(dataset)
        elif isinstance(dataset, (list, tuple)) or dataset is None:
            class_names = dataset
        else:
            raise TypeError(
                'dataset must be a valid dataset name or a sequence'
                ' of class names, not {}'.format(type(dataset)))

        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]

            bboxes = np.vstack(bbox_result)
            # draw segmentation masks
            if segm_result is not None:
                segms = mmcv.concat_list(segm_result)
                inds = np.where(bboxes[:, -1] > score_thr)[0]
                for i in inds:
                    color_mask = np.random.randint(
                        0, 256, (1, 3), dtype=np.uint8)
                    mask = maskUtils.decode(segms[i]).astype(np.bool)
                    img_show[mask] = img_show[mask] * 0.5 + color_mask * 0.5
            # draw bounding boxes
            labels = [
                np.full(bbox.shape[0], i, dtype=np.int32)
                for i, bbox in enumerate(bbox_result)
            ]
            labels = np.concatenate(labels)
            mmcv.imshow_det_bboxes(
                img_show,
                bboxes,
                labels,
                class_names=class_names,
                score_thr=score_thr) 
Example #25
Source File: base.py    From ttfnet with Apache License 2.0 4 votes vote down vote up
def show_result(self, data, result, dataset=None, score_thr=0.3):
        if isinstance(result, tuple):
            bbox_result, segm_result = result
        else:
            bbox_result, segm_result = result, None

        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_metas[0]['img_norm_cfg'])
        assert len(imgs) == len(img_metas)

        if dataset is None:
            class_names = self.CLASSES
        elif isinstance(dataset, str):
            class_names = get_classes(dataset)
        elif isinstance(dataset, (list, tuple)):
            class_names = dataset
        else:
            raise TypeError(
                'dataset must be a valid dataset name or a sequence'
                ' of class names, not {}'.format(type(dataset)))

        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]

            bboxes = np.vstack(bbox_result)
            # draw segmentation masks
            if segm_result is not None:
                segms = mmcv.concat_list(segm_result)
                inds = np.where(bboxes[:, -1] > score_thr)[0]
                for i in inds:
                    color_mask = np.random.randint(
                        0, 256, (1, 3), dtype=np.uint8)
                    mask = maskUtils.decode(segms[i]).astype(np.bool)
                    img_show[mask] = img_show[mask] * 0.5 + color_mask * 0.5
            # draw bounding boxes
            labels = [
                np.full(bbox.shape[0], i, dtype=np.int32)
                for i, bbox in enumerate(bbox_result)
            ]
            labels = np.concatenate(labels)
            mmcv.imshow_det_bboxes(
                img_show,
                bboxes,
                labels,
                class_names=class_names,
                score_thr=score_thr) 
Example #26
Source File: base.py    From AerialDetection with Apache License 2.0 4 votes vote down vote up
def show_result(self,
                    data,
                    result,
                    img_norm_cfg,
                    dataset=None,
                    score_thr=0.3):
        if isinstance(result, tuple):
            bbox_result, segm_result = result
        else:
            bbox_result, segm_result = result, None

        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)

        if dataset is None:
            class_names = self.CLASSES
        elif isinstance(dataset, str):
            class_names = get_classes(dataset)
        elif isinstance(dataset, (list, tuple)):
            class_names = dataset
        else:
            raise TypeError(
                'dataset must be a valid dataset name or a sequence'
                ' of class names, not {}'.format(type(dataset)))

        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]

            bboxes = np.vstack(bbox_result)
            # draw segmentation masks
            if segm_result is not None:
                segms = mmcv.concat_list(segm_result)
                inds = np.where(bboxes[:, -1] > score_thr)[0]
                for i in inds:
                    color_mask = np.random.randint(
                        0, 256, (1, 3), dtype=np.uint8)
                    mask = maskUtils.decode(segms[i]).astype(np.bool)
                    img_show[mask] = img_show[mask] * 0.5 + color_mask * 0.5
            # draw bounding boxes
            labels = [
                np.full(bbox.shape[0], i, dtype=np.int32)
                for i, bbox in enumerate(bbox_result)
            ]
            labels = np.concatenate(labels)
            mmcv.imshow_det_bboxes(
                img_show,
                bboxes,
                labels,
                class_names=class_names,
                score_thr=score_thr) 
Example #27
Source File: base.py    From CenterNet with Apache License 2.0 4 votes vote down vote up
def show_result(self,
                    data,
                    result,
                    img_norm_cfg,
                    dataset=None,
                    score_thr=0.3):
        if isinstance(result, tuple):
            bbox_result, segm_result = result
        else:
            bbox_result, segm_result = result, None

        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)

        if dataset is None:
            class_names = self.CLASSES
        elif isinstance(dataset, str):
            class_names = get_classes(dataset)
        elif isinstance(dataset, (list, tuple)):
            class_names = dataset
        else:
            raise TypeError(
                'dataset must be a valid dataset name or a sequence'
                ' of class names, not {}'.format(type(dataset)))

        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]

            bboxes = np.vstack(bbox_result)
            # draw segmentation masks
            if segm_result is not None:
                segms = mmcv.concat_list(segm_result)
                inds = np.where(bboxes[:, -1] > score_thr)[0]
                for i in inds:
                    color_mask = np.random.randint(
                        0, 256, (1, 3), dtype=np.uint8)
                    mask = maskUtils.decode(segms[i]).astype(np.bool)
                    img_show[mask] = img_show[mask] * 0.5 + color_mask * 0.5
            # draw bounding boxes
            labels = [
                np.full(bbox.shape[0], i, dtype=np.int32)
                for i, bbox in enumerate(bbox_result)
            ]
            labels = np.concatenate(labels)
            mmcv.imshow_det_bboxes(
                img_show,
                bboxes,
                labels,
                class_names=class_names,
                score_thr=score_thr) 
Example #28
Source File: base_new.py    From AerialDetection with Apache License 2.0 4 votes vote down vote up
def show_result(self,
                    data,
                    result,
                    img_norm_cfg,
                    dataset=None,
                    score_thr=0.3):
        if isinstance(result, tuple):
            bbox_result, segm_result = result
        else:
            bbox_result, segm_result = result, None

        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)

        if dataset is None:
            class_names = self.CLASSES
        elif isinstance(dataset, str):
            class_names = get_classes(dataset)
        elif isinstance(dataset, (list, tuple)):
            class_names = dataset
        else:
            raise TypeError(
                'dataset must be a valid dataset name or a sequence'
                ' of class names, not {}'.format(type(dataset)))

        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]

            bboxes = np.vstack(bbox_result)
            # draw segmentation masks
            if segm_result is not None:
                segms = mmcv.concat_list(segm_result)
                inds = np.where(bboxes[:, -1] > score_thr)[0]
                for i in inds:
                    color_mask = np.random.randint(
                        0, 256, (1, 3), dtype=np.uint8)
                    mask = maskUtils.decode(segms[i]).astype(np.bool)
                    img_show[mask] = img_show[mask] * 0.5 + color_mask * 0.5
            # draw bounding boxes
            labels = [
                np.full(bbox.shape[0], i, dtype=np.int32)
                for i, bbox in enumerate(bbox_result)
            ]
            labels = np.concatenate(labels)
            mmcv.imshow_det_bboxes(
                img_show,
                bboxes,
                labels,
                class_names=class_names,
                score_thr=score_thr) 
Example #29
Source File: base.py    From hrnet with MIT License 4 votes vote down vote up
def show_result(self,
                    data,
                    result,
                    img_norm_cfg,
                    dataset='coco',
                    score_thr=0.3):
        if isinstance(result, tuple):
            bbox_result, segm_result = result
        else:
            bbox_result, segm_result = result, None

        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)

        if isinstance(dataset, str):
            class_names = get_classes(dataset)
        elif isinstance(dataset, (list, tuple)) or dataset is None:
            class_names = dataset
        else:
            raise TypeError(
                'dataset must be a valid dataset name or a sequence'
                ' of class names, not {}'.format(type(dataset)))

        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]

            bboxes = np.vstack(bbox_result)
            # draw segmentation masks
            if segm_result is not None:
                segms = mmcv.concat_list(segm_result)
                inds = np.where(bboxes[:, -1] > score_thr)[0]
                for i in inds:
                    color_mask = np.random.randint(
                        0, 256, (1, 3), dtype=np.uint8)
                    mask = maskUtils.decode(segms[i]).astype(np.bool)
                    img_show[mask] = img_show[mask] * 0.5 + color_mask * 0.5
            # draw bounding boxes
            labels = [
                np.full(bbox.shape[0], i, dtype=np.int32)
                for i, bbox in enumerate(bbox_result)
            ]
            labels = np.concatenate(labels)
            mmcv.imshow_det_bboxes(
                img_show,
                bboxes,
                labels,
                class_names=class_names,
                score_thr=score_thr) 
Example #30
Source File: base.py    From GCNet with Apache License 2.0 4 votes vote down vote up
def show_result(self,
                    data,
                    result,
                    img_norm_cfg,
                    dataset=None,
                    score_thr=0.3):
        if isinstance(result, tuple):
            bbox_result, segm_result = result
        else:
            bbox_result, segm_result = result, None

        img_tensor = data['img'][0]
        img_metas = data['img_meta'][0].data[0]
        imgs = tensor2imgs(img_tensor, **img_norm_cfg)
        assert len(imgs) == len(img_metas)

        if dataset is None:
            class_names = self.CLASSES
        elif isinstance(dataset, str):
            class_names = get_classes(dataset)
        elif isinstance(dataset, (list, tuple)):
            class_names = dataset
        else:
            raise TypeError(
                'dataset must be a valid dataset name or a sequence'
                ' of class names, not {}'.format(type(dataset)))

        for img, img_meta in zip(imgs, img_metas):
            h, w, _ = img_meta['img_shape']
            img_show = img[:h, :w, :]

            bboxes = np.vstack(bbox_result)
            # draw segmentation masks
            if segm_result is not None:
                segms = mmcv.concat_list(segm_result)
                inds = np.where(bboxes[:, -1] > score_thr)[0]
                for i in inds:
                    color_mask = np.random.randint(
                        0, 256, (1, 3), dtype=np.uint8)
                    mask = maskUtils.decode(segms[i]).astype(np.bool)
                    img_show[mask] = img_show[mask] * 0.5 + color_mask * 0.5
            # draw bounding boxes
            labels = [
                np.full(bbox.shape[0], i, dtype=np.int32)
                for i, bbox in enumerate(bbox_result)
            ]
            labels = np.concatenate(labels)
            mmcv.imshow_det_bboxes(
                img_show,
                bboxes,
                labels,
                class_names=class_names,
                score_thr=score_thr)