def _unmold_single_detection(self, detections, img_meta):
zero_ix = tf.where(tf.not_equal(detections[:, 4], 0))
detections = tf.gather_nd(detections, zero_ix)
# Extract boxes, class_ids, scores, and class-specific masks
boxes = detections[:, :4]
class_ids = tf.cast(detections[:, 4], tf.int32)
scores = detections[:, 5]
boxes = transforms.bbox_mapping_back(boxes, img_meta)
return {'rois': boxes.numpy(),
'class_ids': class_ids.numpy(),
'scores': scores.numpy()}
def _unmold_single_detection(self, detections, img_meta):
# detections: [最终保留的框的个数, [y1, x1, y2, x2, class_id, score]]
zero_ix = tf.where(tf.not_equal(detections[:, 4], 0))
# detections: [分类结果为前景的框的个数, [y1, x1, y2, x2, class_id, score]]
detections = tf.gather_nd(detections, zero_ix)
# boxes: [分类结果为前景的框的个数, [y1, x1, y2, x2]]
# class_ids: [分类结果为前景的框的个数,]
# scores: [分类结果为前景的框的个数,]
boxes = detections[:, :4]
class_ids = tf.cast(detections[:, 4], tf.int32)
scores = detections[:, 5]
boxes = transforms.bbox_mapping_back(boxes, img_meta)
return {'rois': boxes.numpy(),
'class_ids': class_ids.numpy(),
'scores': scores.numpy()}