mask_model.json

{
    "type": "MaskRCNN",
    "backbone": {
        "type": "ResNet",
        "depth": 50,
        "num_stages": 4,
        "out_indices": [
            0,
            1,
            2,
            3
        ],
        "frozen_stages": 1,
        "norm_cfg": {
            "type": "BN",
            "requires_grad": true
        },
        "norm_eval": true,
        "style": "pytorch",
        "init_cfg": {
            "type": "Pretrained",
            "checkpoint": "torchvision://resnet50"
        }
    },
    "neck": {
        "type": "FPN",
        "in_channels": [
            256,
            512,
            1024,
            2048
        ],
        "out_channels": 256,
        "num_outs": 5
    },
    "rpn_head": {
        "type": "RPNHead",
        "in_channels": 256,
        "feat_channels": 256,
        "anchor_generator": {
            "type": "AnchorGenerator",
            "scales": [
                8
            ],
            "ratios": [
                0.5,
                1.0,
                2.0
            ],
            "strides": [
                4,
                8,
                16,
                32,
                64
            ]
        },
        "bbox_coder": {
            "type": "DeltaXYWHBBoxCoder",
            "target_means": [
                0.0,
                0.0,
                0.0,
                0.0
            ],
            "target_stds": [
                1.0,
                1.0,
                1.0,
                1.0
            ]
        },
        "loss_cls": {
            "type": "CrossEntropyLoss",
            "use_sigmoid": true,
            "loss_weight": 1.0
        },
        "loss_bbox": {
            "type": "L1Loss",
            "loss_weight": 1.0
        }
    },
    "roi_head": {
        "type": "StandardRoIHead",
        "bbox_roi_extractor": {
            "type": "SingleRoIExtractor",
            "roi_layer": {
                "type": "RoIAlign",
                "output_size": 7,
                "sampling_ratio": 0
            },
            "out_channels": 256,
            "featmap_strides": [
                4,
                8,
                16,
                32
            ]
        },
        "bbox_head": {
            "type": "Shared2FCBBoxHead",
            "in_channels": 256,
            "fc_out_channels": 1024,
            "roi_feat_size": 7,
            "num_classes": 80,
            "bbox_coder": {
                "type": "DeltaXYWHBBoxCoder",
                "target_means": [
                    0.0,
                    0.0,
                    0.0,
                    0.0
                ],
                "target_stds": [
                    0.1,
                    0.1,
                    0.2,
                    0.2
                ]
            },
            "reg_class_agnostic": false,
            "loss_cls": {
                "type": "CrossEntropyLoss",
                "use_sigmoid": false,
                "loss_weight": 1.0
            },
            "loss_bbox": {
                "type": "L1Loss",
                "loss_weight": 1.0
            }
        },
        "mask_roi_extractor": {
            "type": "SingleRoIExtractor",
            "roi_layer": {
                "type": "RoIAlign",
                "output_size": 14,
                "sampling_ratio": 0
            },
            "out_channels": 256,
            "featmap_strides": [
                4,
                8,
                16,
                32
            ]
        },
        "mask_head": {
            "type": "FCNMaskHead",
            "num_convs": 4,
            "in_channels": 256,
            "conv_out_channels": 256,
            "num_classes": 80,
            "loss_mask": {
                "type": "CrossEntropyLoss",
                "use_mask": true,
                "loss_weight": 1.0
            }
        }
    },
    "train_cfg": {
        "rpn": {
            "assigner": {
                "type": "MaxIoUAssigner",
                "pos_iou_thr": 0.7,
                "neg_iou_thr": 0.3,
                "min_pos_iou": 0.3,
                "match_low_quality": true,
                "ignore_iof_thr": -1
            },
            "sampler": {
                "type": "RandomSampler",
                "num": 256,
                "pos_fraction": 0.5,
                "neg_pos_ub": -1,
                "add_gt_as_proposals": false
            },
            "allowed_border": -1,
            "pos_weight": -1,
            "debug": false
        },
        "rpn_proposal": {
            "nms_pre": 2000,
            "max_per_img": 1000,
            "nms": {
                "type": "nms",
                "iou_threshold": 0.7
            },
            "min_bbox_size": 0
        },
        "rcnn": {
            "assigner": {
                "type": "MaxIoUAssigner",
                "pos_iou_thr": 0.5,
                "neg_iou_thr": 0.5,
                "min_pos_iou": 0.5,
                "match_low_quality": true,
                "ignore_iof_thr": -1
            },
            "sampler": {
                "type": "RandomSampler",
                "num": 512,
                "pos_fraction": 0.25,
                "neg_pos_ub": -1,
                "add_gt_as_proposals": true
            },
            "mask_size": 28,
            "pos_weight": -1,
            "debug": false
        }
    },
    "test_cfg": {
        "rpn": {
            "nms_pre": 1000,
            "max_per_img": 1000,
            "nms": {
                "type": "nms",
                "iou_threshold": 0.7
            },
            "min_bbox_size": 0
        },
        "rcnn": {
            "score_thr": 0.05,
            "nms": {
                "type": "nms",
                "iou_threshold": 0.5
            },
            "max_per_img": 100,
            "mask_thr_binary": 0.5
        }
    }
}