data generation

data_generation/grit/third_party/CenterNet2/configs/COCO-Detection/retinanet_R_50_FPN_1x.yaml

+_BASE_: "../Base-RetinaNet.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50

data_generation/grit/third_party/CenterNet2/configs/COCO-Detection/retinanet_R_50_FPN_3x.yaml

+_BASE_: "../Base-RetinaNet.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

data_generation/grit/third_party/CenterNet2/configs/COCO-Detection/rpn_R_50_C4_1x.yaml

+_BASE_: "../Base-RCNN-C4.yaml"
+MODEL:
+  META_ARCHITECTURE: "ProposalNetwork"
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50
+  RPN:
+    PRE_NMS_TOPK_TEST: 12000
+    POST_NMS_TOPK_TEST: 2000

data_generation/grit/third_party/CenterNet2/configs/COCO-Detection/rpn_R_50_FPN_1x.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  META_ARCHITECTURE: "ProposalNetwork"
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50
+  RPN:
+    POST_NMS_TOPK_TEST: 2000

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x.yaml

+_BASE_: "../Base-RCNN-C4.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x.yaml

+_BASE_: "../Base-RCNN-DilatedC5.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.py

+from ..common.train import train
+from ..common.optim import SGD as optimizer
+from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
+from ..common.data.coco import dataloader
+from ..common.models.mask_rcnn_c4 import model
+
+model.backbone.freeze_at = 2
+train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl"

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.yaml

+_BASE_: "../Base-RCNN-C4.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x.yaml

+_BASE_: "../Base-RCNN-C4.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x.yaml

+_BASE_: "../Base-RCNN-DilatedC5.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x.yaml

+_BASE_: "../Base-RCNN-DilatedC5.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.py

+from ..common.optim import SGD as optimizer
+from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
+from ..common.data.coco import dataloader
+from ..common.models.mask_rcnn_fpn import model
+from ..common.train import train
+
+model.backbone.bottom_up.freeze_at = 2
+train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl"

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x_giou.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50
+  RPN:
+    BBOX_REG_LOSS_TYPE: "giou"
+    BBOX_REG_LOSS_WEIGHT: 2.0
+  ROI_BOX_HEAD:
+    BBOX_REG_LOSS_TYPE: "giou"
+    BBOX_REG_LOSS_WEIGHT: 10.0

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  MASK_ON: True
+  WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl"
+  PIXEL_STD: [57.375, 57.120, 58.395]
+  RESNETS:
+    STRIDE_IN_1X1: False  # this is a C2 model
+    NUM_GROUPS: 32
+    WIDTH_PER_GROUP: 8
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_regnetx_4gf_dds_fpn_1x.py

+from ..common.optim import SGD as optimizer
+from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
+from ..common.data.coco import dataloader
+from ..common.models.mask_rcnn_fpn import model
+from ..common.train import train
+
+from detectron2.config import LazyCall as L
+from detectron2.modeling.backbone import RegNet
+from detectron2.modeling.backbone.regnet import SimpleStem, ResBottleneckBlock
+
+
+# Replace default ResNet with RegNetX-4GF from the DDS paper. Config source:
+# https://github.com/facebookresearch/pycls/blob/2c152a6e5d913e898cca4f0a758f41e6b976714d/configs/dds_baselines/regnetx/RegNetX-4.0GF_dds_8gpu.yaml#L4-L9  # noqa
+model.backbone.bottom_up = L(RegNet)(
+    stem_class=SimpleStem,
+    stem_width=32,
+    block_class=ResBottleneckBlock,
+    depth=23,
+    w_a=38.65,
+    w_0=96,
+    w_m=2.43,
+    group_width=40,
+    freeze_at=2,
+    norm="FrozenBN",
+    out_features=["s1", "s2", "s3", "s4"],
+)
+model.pixel_std = [57.375, 57.120, 58.395]
+
+optimizer.weight_decay = 5e-5
+train.init_checkpoint = (
+    "https://dl.fbaipublicfiles.com/pycls/dds_baselines/160906383/RegNetX-4.0GF_dds_8gpu.pyth"
+)
+# RegNets benefit from enabling cudnn benchmark mode
+train.cudnn_benchmark = True

data_generation/grit/third_party/CenterNet2/configs/COCO-InstanceSegmentation/mask_rcnn_regnety_4gf_dds_fpn_1x.py

+from ..common.optim import SGD as optimizer
+from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
+from ..common.data.coco import dataloader
+from ..common.models.mask_rcnn_fpn import model
+from ..common.train import train
+
+from detectron2.config import LazyCall as L
+from detectron2.modeling.backbone import RegNet
+from detectron2.modeling.backbone.regnet import SimpleStem, ResBottleneckBlock
+
+
+# Replace default ResNet with RegNetY-4GF from the DDS paper. Config source:
+# https://github.com/facebookresearch/pycls/blob/2c152a6e5d913e898cca4f0a758f41e6b976714d/configs/dds_baselines/regnety/RegNetY-4.0GF_dds_8gpu.yaml#L4-L10  # noqa
+model.backbone.bottom_up = L(RegNet)(
+    stem_class=SimpleStem,
+    stem_width=32,
+    block_class=ResBottleneckBlock,
+    depth=22,
+    w_a=31.41,
+    w_0=96,
+    w_m=2.24,
+    group_width=64,
+    se_ratio=0.25,
+    freeze_at=2,
+    norm="FrozenBN",
+    out_features=["s1", "s2", "s3", "s4"],
+)
+model.pixel_std = [57.375, 57.120, 58.395]
+
+optimizer.weight_decay = 5e-5
+train.init_checkpoint = (
+    "https://dl.fbaipublicfiles.com/pycls/dds_baselines/160906838/RegNetY-4.0GF_dds_8gpu.pyth"
+)
+# RegNets benefit from enabling cudnn benchmark mode
+train.cudnn_benchmark = True

data_generation/grit/third_party/CenterNet2/configs/COCO-Keypoints/Base-Keypoint-RCNN-FPN.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  KEYPOINT_ON: True
+  ROI_HEADS:
+    NUM_CLASSES: 1
+  ROI_BOX_HEAD:
+    SMOOTH_L1_BETA: 0.5  # Keypoint AP degrades (though box AP improves) when using plain L1 loss
+  RPN:
+    # Detectron1 uses 2000 proposals per-batch, but this option is per-image in detectron2.
+    # 1000 proposals per-image is found to hurt box AP.
+    # Therefore we increase it to 1500 per-image.
+    POST_NMS_TOPK_TRAIN: 1500
+DATASETS:
+  TRAIN: ("keypoints_coco_2017_train",)
+  TEST: ("keypoints_coco_2017_val",)