cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5 在 detectorron2 中做什么？

Question

希望你做得很好！

我不太明白 detectorron2 colab 笔记本教程中的这两行，我尝试查看官方文档，但我不太明白，有人可以向我解释一下吗：

cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5  # set threshold for this model
# Find a model from detectron2's model zoo. You can use the https://dl.fbaipublicfiles... url as well
cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")

我预先感谢您并祝您度过愉快的一天！

Answer 1

该值是用于在推理/测试时间过滤掉模型的Fast R-CNNcfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST组件预测的低分边界框的阈值。

基本上，任何置信度得分高于阈值的预测都会被保留，而其余的则被丢弃。

此阈值可以在此处的Detectron2 代码中看到。

def fast_rcnn_inference_single_image(
    boxes,
    scores,
    image_shape: Tuple[int, int],
    score_thresh: float,
    nms_thresh: float,
    topk_per_image: int,
):

    ### clipped code ###

    # 1. Filter results based on detection scores. It can make NMS more efficient
    #    by filtering out low-confidence detections.
    filter_mask = scores > score_thresh  # R x K

    ### clipped code ###

您还可以在此处查看以确认该参数值来自配置。

class FastRCNNOutputLayers(nn.Module):
    """
    Two linear layers for predicting Fast R-CNN outputs:
    1. proposal-to-detection box regression deltas
    2. classification scores
    """
    
    ### clipped code ###

    @classmethod
    def from_config(cls, cfg, input_shape):
        return {
            "input_shape": input_shape,
            "box2box_transform": Box2BoxTransform(weights=cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS),
            # fmt: off
            "num_classes"           : cfg.MODEL.ROI_HEADS.NUM_CLASSES,
            "cls_agnostic_bbox_reg" : cfg.MODEL.ROI_BOX_HEAD.CLS_AGNOSTIC_BBOX_REG,
            "smooth_l1_beta"        : cfg.MODEL.ROI_BOX_HEAD.SMOOTH_L1_BETA,
            "test_score_thresh"     : cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST,
            "test_nms_thresh"       : cfg.MODEL.ROI_HEADS.NMS_THRESH_TEST,
            "test_topk_per_image"   : cfg.TEST.DETECTIONS_PER_IMAGE,
            "box_reg_loss_type"     : cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_LOSS_TYPE,
            "loss_weight"           : {"loss_box_reg": cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_LOSS_WEIGHT},
            # fmt: on
        }

    ### clipped code ###