Python cfg.DEDUP_BOXES属性代码示例

# 需要导入模块: from fast_rcnn.config import cfg [as 别名]
# 或者: from fast_rcnn.config.cfg import DEDUP_BOXES [as 别名]
def get_minibatch(roidb, num_classes):
    """Given a roidb, construct a minibatch sampled from it."""
    num_images = len(roidb)
    assert num_images == 1, 'batch size should equal to 1!'
    # Sample random scales to use for each image in this batch
    random_scale_inds = npr.randint(0, high=len(cfg.TRAIN.SCALES),
                                    size=num_images)

    # Get the input image blob, formatted for caffe
    im_blob, im_scales, im_shapes = _get_image_blob(roidb, random_scale_inds)

    # Now, build the region of interest and label blobs
    rois_blob = np.zeros((0, 5), dtype=np.float32)
    labels_blob = np.zeros((0, 20), dtype=np.float32)
    
    for im_i in xrange(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 blobs
        labels_blob = np.vstack((labels_blob, labels))

    blobs = {'data': im_blob,
             'rois': rois_blob,
             'labels': labels_blob}

    return blobs 

# 需要导入模块: from fast_rcnn.config import cfg [as 别名]
# 或者: from fast_rcnn.config.cfg import DEDUP_BOXES [as 别名]
def im_detect(net, im, boxes):
    """Detect object classes in an image given object proposals.

    Arguments:
        net (caffe.Net): Fast R-CNN network to use
        im (ndarray): color image to test (in BGR order)
        boxes (ndarray): R x 4 array of object proposals

    Returns:
        scores (ndarray): R x K array of object class scores (K includes
            background as object category 0)
        boxes (ndarray): R x (4*K) array of predicted bounding boxes
    """
    blobs, unused_im_scale_factors = _get_blobs(im, boxes)

    # When mapping from image ROIs to feature map ROIs, there's some aliasing
    # (some distinct image ROIs get mapped to the same feature ROI).
    # Here, we identify duplicate feature ROIs, so we only compute features
    # on the unique subset.
    for i in xrange(len(blobs['data'])):
        if cfg.DEDUP_BOXES > 0:
            v = np.array([1, 1e3, 1e6, 1e9, 1e12])
            hashes = np.round(blobs['rois'][i] * cfg.DEDUP_BOXES).dot(v)
            _, index, inv_index = np.unique(hashes, return_index=True,
                                            return_inverse=True)
            blobs['rois'][i] = blobs['rois'][i][index, :]

        # reshape network inputs
        net.blobs['data'].reshape(*(blobs['data'][i].shape))
        net.blobs['rois'].reshape(*(blobs['rois'][i].shape))
        
        blobs_out = net.forward(data=blobs['data'][i].astype(np.float32, copy=False),
                                rois=blobs['rois'][i].astype(np.float32, copy=False))


        scores_tmp = blobs_out['cls_score_7_1']
        if cfg.DEDUP_BOXES > 0:
            # Map scores and predictions back to the original set of boxes
            scores_tmp = scores_tmp[inv_index, :]
            # pred_boxes = pred_boxes[inv_index, :]

        if i == 0:        
            scores = np.copy(scores_tmp)
        else:
            scores += scores_tmp

    pred_boxes = np.tile(boxes, (1, scores.shape[1]))
        
    return scores, pred_boxes 

# 需要导入模块: from fast_rcnn.config import cfg [as 别名]
# 或者: from fast_rcnn.config.cfg import DEDUP_BOXES [as 别名]
def im_cls(net, im, boxes):
    """Classify object classes in an image given object proposals.

    Arguments:
        net (caffe.Net): Fast R-CNN network to use
        im (ndarray): color image to test (in BGR order)
        boxes (ndarray): R x 4 array of object proposals

    Returns:
        scores (ndarray): 1 x K array of object class scores
    """
    blobs, unused_im_scale_factors = _get_blobs(im, boxes)

    # When mapping from image ROIs to feature map ROIs, there's some aliasing
    # (some distinct image ROIs get mapped to the same feature ROI).
    # Here, we identify duplicate feature ROIs, so we only compute features
    # on the unique subset.
    for i in xrange(len(blobs['data'])):
        if cfg.DEDUP_BOXES > 0:
            v = np.array([1, 1e3, 1e6, 1e9, 1e12])
            hashes = np.round(blobs['rois'][i] * cfg.DEDUP_BOXES).dot(v)
            _, index, inv_index = np.unique(hashes, return_index=True,
                                            return_inverse=True)
            blobs['rois'][i] = blobs['rois'][i][index, :]

        # reshape network inputs
        net.blobs['data'].reshape(*(blobs['data'][i].shape))
        net.blobs['rois'].reshape(*(blobs['rois'][i].shape))
        net.blobs['shapes'].reshape(*(blobs['shapes'][i].shape))
        
        blobs_out = net.forward(data=blobs['data'][i].astype(np.float32, copy=False),
                                rois=blobs['rois'][i].astype(np.float32, copy=False),
                                shapes=blobs['shapes'][i].astype(np.float32, copy=False))

        if i == 0:        
            scores = blobs_out['cls_score_7'] + blobs_out['SPMMax8_1']
            # scores = blobs_out['cls_score_7']
        else:
            scores = np.vstack((scores, blobs_out['cls_score_7'] + blobs_out['SPMMax8_1']))
            # scores = np.vstack((scores, blobs_out['cls_score_7']))

    return scores