Python cfg.DEDUP_BOXES属性代码示例

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import DEDUP_BOXES [as 别名]
def get_det_boxes(self, boxes, scores, box_deltas, h_and_w):

        if cfg.TEST.BBOX_REG:
            if cfg.MODEL.CLS_AGNOSTIC_BBOX_REG:
                # Remove predictions for bg class (compat with MSRA code)
                box_deltas = box_deltas[:, -4:]
            if cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED:
                # (legacy) Optionally normalize targets by a precomputed mean and stdev
                box_deltas = box_deltas.view(-1, 4) * cfg.TRAIN.BBOX_NORMALIZE_STDS \
                             + cfg.TRAIN.BBOX_NORMALIZE_MEANS
            pred_boxes = box_utils.bbox_transform(boxes, box_deltas, cfg.MODEL.BBOX_REG_WEIGHTS)
            pred_boxes = box_utils.clip_tiled_boxes(pred_boxes, h_and_w)
            if cfg.MODEL.CLS_AGNOSTIC_BBOX_REG:
                pred_boxes = np.tile(pred_boxes, (1, scores.shape[1]))
        else:
            # Simply repeat the boxes, once for each class
            pred_boxes = np.tile(boxes, (1, scores.shape[1]))

        if cfg.DEDUP_BOXES > 0 and not cfg.MODEL.FASTER_RCNN:
            # Map scores and predictions back to the original set of boxes
            scores = scores[inv_index, :]
            pred_boxes = pred_boxes[inv_index, :]
            
        return scores, pred_boxes 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import DEDUP_BOXES [as 别名]
def get_minibatch(roidb, num_classes):
    """Given a roidb, construct a minibatch sampled from it."""
    # We collect blobs from each image onto a list and then concat them into a
    # single tensor, hence we initialize each blob to an empty list
    blobs = {k: [] for k in get_minibatch_blob_names()}

    # Get the input image blob
    im_blob, im_scales = _get_image_blob(roidb)

    assert len(im_scales) == 1, "Single batch only"
    assert len(roidb) == 1, "Single batch only"

    blobs['data'] = im_blob
    rois_blob = np.zeros((0, 5), dtype=np.float32)
    labels_blob = np.zeros((0, num_classes), dtype=np.float32)

    num_images = len(roidb)
    for im_i in range(num_images):
        labels, im_rois = _sample_rois(roidb[im_i], num_classes)

        # Add to RoIs blob
        rois = _project_im_rois(im_rois, im_scales[im_i])
        batch_ind = im_i * np.ones((rois.shape[0], 1))
        rois_blob_this_image = np.hstack((batch_ind, rois))

        if cfg.DEDUP_BOXES > 0:
            v = np.array([1, 1e3, 1e6, 1e9, 1e12])
            hashes = np.round(rois_blob_this_image * cfg.DEDUP_BOXES).dot(v)
            _, index, inv_index = np.unique(hashes, return_index=True,
                                            return_inverse=True)
            rois_blob_this_image = rois_blob_this_image[index, :]

        rois_blob = np.vstack((rois_blob, rois_blob_this_image))

        # Add to labels blob
        labels_blob = np.vstack((labels_blob, labels))

    blobs['rois'] = rois_blob
    blobs['labels'] = labels_blob

    return blobs, True 

# 需要导入模块: from core.config import cfg [as 别名]
# 或者: from core.config.cfg import DEDUP_BOXES [as 别名]
def im_detect_bbox(model, im, target_scale, target_max_size, boxes=None):
    """Prepare the bbox for testing"""

    inputs, im_scale = _get_blobs(im, boxes, target_scale, target_max_size)

    if cfg.DEDUP_BOXES > 0:
        v = np.array([1, 1e3, 1e6, 1e9, 1e12])
        hashes = np.round(inputs['rois'] * cfg.DEDUP_BOXES).dot(v)
        _, index, inv_index = np.unique(
            hashes, return_index=True, return_inverse=True
        )
        inputs['rois'] = inputs['rois'][index, :]
        boxes = boxes[index, :]

    if cfg.PYTORCH_VERSION_LESS_THAN_040:
        inputs['data'] = [Variable(torch.from_numpy(inputs['data']), volatile=True)]
        inputs['rois'] = [Variable(torch.from_numpy(inputs['rois']), volatile=True)]
        inputs['labels'] = [Variable(torch.from_numpy(inputs['labels']), volatile=True)]
    else:
        inputs['data'] = [torch.from_numpy(inputs['data'])]
        inputs['rois'] = [torch.from_numpy(inputs['rois'])]
        inputs['labels'] = [torch.from_numpy(inputs['labels'])]

    return_dict = model(**inputs)

    # cls prob (activations after softmax)
    scores = return_dict['refine_score'][0].data.cpu().numpy().squeeze()
    for i in range(1, cfg.REFINE_TIMES):
        scores += return_dict['refine_score'][i].data.cpu().numpy().squeeze()
    scores /= cfg.REFINE_TIMES
    # In case there is 1 proposal
    scores = scores.reshape([-1, scores.shape[-1]])
    pred_boxes = boxes

    if cfg.DEDUP_BOXES > 0:
        # Map scores and predictions back to the original set of boxes
        scores = scores[inv_index, :]
        pred_boxes = pred_boxes[inv_index, :]

    return scores, pred_boxes, im_scale, return_dict['blob_conv']