How to use the mmdet.models.registry.DETECTORS function in mmdet

import torch
import torch.nn.functional as F

from mmdet.core import (bbox2result, bbox2roi, bbox_mapping, build_assigner,
                        build_sampler, merge_aug_bboxes, merge_aug_masks,
                        multiclass_nms)
from .. import builder
from ..registry import DETECTORS
from .cascade_rcnn import CascadeRCNN


@DETECTORS.register_module
class HybridTaskCascade(CascadeRCNN):

    def __init__(self,
                 num_stages,
                 backbone,
                 semantic_roi_extractor=None,
                 semantic_head=None,
                 semantic_fusion=('bbox', 'mask'),
                 interleaved=True,
                 mask_info_flow=True,
                 **kwargs):
        super(HybridTaskCascade, self).__init__(num_stages, backbone, **kwargs)
        assert self.with_bbox and self.with_mask
        assert not self.with_shared_head  # shared head not supported
        if semantic_head is not None:
            self.semantic_roi_extractor = builder.build_roi_extractor(

import torch

from mmdet.core import bbox2result, bbox_mapping_back, multiclass_nms
from ..registry import DETECTORS
from .single_stage import SingleStageDetector


@DETECTORS.register_module
class RepPointsDetector(SingleStageDetector):
    """RepPoints: Point Set Representation for Object Detection.

        This detector is the implementation of:
        - RepPoints detector (https://arxiv.org/pdf/1904.11490)
    """

    def __init__(self,
                 backbone,
                 neck,
                 bbox_head,
                 train_cfg=None,
                 test_cfg=None,
                 pretrained=None):
        super(RepPointsDetector,
              self).__init__(backbone, neck, bbox_head, train_cfg, test_cfg,

import mmcv

from mmdet.core import tensor2imgs, bbox_mapping
from .base import BaseDetector
from .test_mixins import RPNTestMixin
from .. import builder
from ..registry import DETECTORS


@DETECTORS.register_module
class RPN(BaseDetector, RPNTestMixin):

    def __init__(self,
                 backbone,
                 neck,
                 rpn_head,
                 train_cfg,
                 test_cfg,
                 pretrained=None):
        super(RPN, self).__init__()
        self.backbone = builder.build_backbone(backbone)
        self.neck = builder.build_neck(neck) if neck is not None else None
        self.rpn_head = builder.build_head(rpn_head)
        self.train_cfg = train_cfg
        self.test_cfg = test_cfg
        self.init_weights(pretrained=pretrained)

import torch
import torch.nn as nn

from mmdet.core import bbox2result, bbox2roi, build_assigner, build_sampler
from .. import builder
from ..registry import DETECTORS
from .base import BaseDetector
from .test_mixins import BBoxTestMixin, MaskTestMixin, RPNTestMixin


@DETECTORS.register_module
class TwoStageDetector(BaseDetector, RPNTestMixin, BBoxTestMixin,
                       MaskTestMixin):
    """Base class for two-stage detectors.

    Two-stage detectors typically consisting of a region proposal network and a
    task-specific regression head.
    """

    def __init__(self,
                 backbone,
                 neck=None,
                 shared_head=None,
                 rpn_head=None,
                 bbox_roi_extractor=None,
                 bbox_head=None,
                 mask_roi_extractor=None,

def build_detector(cfg, train_cfg=None, test_cfg=None):
    return build(cfg, DETECTORS, dict(train_cfg=train_cfg, test_cfg=test_cfg))

import torch.nn as nn

from mmdet.core import bbox2result
from .. import builder
from ..registry import DETECTORS
from .base import BaseDetector


@DETECTORS.register_module
class SingleStageDetector(BaseDetector):
    """Base class for single-stage detectors.

    Single-stage detectors directly and densely predict bounding boxes on the
    output features of the backbone+neck.
    """

    def __init__(self,
                 backbone,
                 neck=None,
                 bbox_head=None,
                 train_cfg=None,
                 test_cfg=None,
                 pretrained=None):
        super(SingleStageDetector, self).__init__()
        self.backbone = builder.build_backbone(backbone)

import torch.nn as nn

from mmdet.core import bbox2result, bbox_mask2result
from .. import builder
from ..registry import DETECTORS
from .base import BaseDetector
from IPython import embed
import time
import torch

@DETECTORS.register_module
class SingleStageDetector(BaseDetector):

    def __init__(self,
                 backbone,
                 neck=None,
                 bbox_head=None,
                 train_cfg=None,
                 test_cfg=None,
                 pretrained=None):
        super(SingleStageDetector, self).__init__()
        self.backbone = builder.build_backbone(backbone)
        if neck is not None:
            self.neck = builder.build_neck(neck)
        self.bbox_head = builder.build_head(bbox_head)
        self.train_cfg = train_cfg
        self.test_cfg = test_cfg

import torch

from mmdet.core import bbox2roi, build_assigner, build_sampler
from .. import builder
from ..registry import DETECTORS
from .two_stage import TwoStageDetector


@DETECTORS.register_module
class MaskScoringRCNN(TwoStageDetector):
    """Mask Scoring RCNN.

    https://arxiv.org/abs/1903.00241
    """

    def __init__(self,
                 backbone,
                 rpn_head,
                 bbox_roi_extractor,
                 bbox_head,
                 mask_roi_extractor,
                 mask_head,
                 train_cfg,
                 test_cfg,
                 neck=None,

from .two_stage import TwoStageDetector
from ..registry import DETECTORS

import ipdb

# 利用super的构造函数继承，递归地搭建了计算图！

@DETECTORS.register_module  
class FasterRCNN(TwoStageDetector):

    def __init__(self,
                 backbone,
                 rpn_head,
                 bbox_roi_extractor,
                 bbox_head,
                 train_cfg,
                 test_cfg,
                 neck=None,
                 shared_head=None,
                 pretrained=None):
        super(FasterRCNN, self).__init__(
            backbone=backbone,
            neck=neck,
            shared_head=shared_head,