ootdiffusion

preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/mask_rcnn_R_50_FPN_1x_cls_agnostic.yaml

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

preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/mask_rcnn_R_50_FPN_1x_dconv_c3-c5.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50
+    DEFORM_ON_PER_STAGE: [False, True, True, True] # on Res3,Res4,Res5
+    DEFORM_MODULATED: False

preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/mask_rcnn_R_50_FPN_3x_dconv_c3-c5.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50
+    DEFORM_ON_PER_STAGE: [False, True, True, True] # on Res3,Res4,Res5
+    DEFORM_MODULATED: False
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/mask_rcnn_R_50_FPN_3x_gn.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "catalog://ImageNetPretrained/FAIR/R-50-GN"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50
+    NORM: "GN"
+    STRIDE_IN_1X1: False
+  FPN:
+    NORM: "GN"
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_CONV: 4
+    NUM_FC: 1
+    NORM: "GN"
+  ROI_MASK_HEAD:
+    NORM: "GN"
+SOLVER:
+  # 3x schedule
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/mask_rcnn_R_50_FPN_3x_syncbn.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50
+    NORM: "SyncBN"
+    STRIDE_IN_1X1: True
+  FPN:
+    NORM: "SyncBN"
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_CONV: 4
+    NUM_FC: 1
+    NORM: "SyncBN"
+  ROI_MASK_HEAD:
+    NORM: "SyncBN"
+SOLVER:
+  # 3x schedule
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000
+TEST:
+  PRECISE_BN:
+    ENABLED: True

preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/panoptic_fpn_R_101_dconv_cascade_gn_3x.yaml

+# A large PanopticFPN for demo purposes.
+# Use GN on backbone to support semantic seg.
+# Use Cascade + Deform Conv to improve localization.
+_BASE_: "../COCO-PanopticSegmentation/Base-Panoptic-FPN.yaml"
+MODEL:
+  WEIGHTS: "catalog://ImageNetPretrained/FAIR/R-101-GN"
+  RESNETS:
+    DEPTH: 101
+    NORM: "GN"
+    DEFORM_ON_PER_STAGE: [False, True, True, True]
+    STRIDE_IN_1X1: False
+  FPN:
+    NORM: "GN"
+  ROI_HEADS:
+    NAME: CascadeROIHeads
+  ROI_BOX_HEAD:
+    CLS_AGNOSTIC_BBOX_REG: True
+  ROI_MASK_HEAD:
+    NORM: "GN"
+  RPN:
+    POST_NMS_TOPK_TRAIN: 2000
+SOLVER:
+  STEPS: (105000, 125000)
+  MAX_ITER: 135000
+  IMS_PER_BATCH: 32
+  BASE_LR: 0.04

preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/parsing_finetune_cihp.yaml

+_BASE_: "cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv.yaml"
+MODEL:
+  MASK_ON: True
+  WEIGHTS: "model_0039999_e76410.pkl"
+  ROI_HEADS:
+    NUM_CLASSES: 1
+SOLVER:
+  IMS_PER_BATCH: 16
+  STEPS: (140000, 180000)
+  MAX_ITER: 200000
+  BASE_LR: 0.02
+INPUT:
+  MIN_SIZE_TRAIN: (640, 864)
+  MIN_SIZE_TRAIN_SAMPLING: "range"
+  MAX_SIZE_TRAIN: 1440
+  CROP:
+    ENABLED: True
+TEST:
+  EVAL_PERIOD: 0
+DATASETS:
+  TRAIN: ("CIHP_train")
+  TEST: ("CIHP_val",)
+OUTPUT_DIR: "./finetune_output"
+

preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/parsing_inference.yaml

+_BASE_: "cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv.yaml"
+MODEL:
+  MASK_ON: True
+  WEIGHTS: "./finetune_ouput/model_final.pth"
+  ROI_HEADS:
+    NMS_THRESH_TEST: 0.95
+    SCORE_THRESH_TEST: 0.5
+    NUM_CLASSES: 1
+SOLVER:
+  IMS_PER_BATCH: 1
+  STEPS: (30000, 45000)
+  MAX_ITER: 50000
+  BASE_LR: 0.02
+INPUT:
+  MIN_SIZE_TRAIN: (640, 864)
+  MIN_SIZE_TRAIN_SAMPLING: "range"
+  MAX_SIZE_TRAIN: 1440
+  CROP:
+    ENABLED: True
+TEST:
+  AUG:
+    ENABLED: True
+DATASETS:
+  TRAIN: ("CIHP_trainval",)
+  TEST: ("CIHP_test",)
+OUTPUT_DIR: "./inference_output"

preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/scratch_mask_rcnn_R_50_FPN_3x_gn.yaml

+_BASE_: "mask_rcnn_R_50_FPN_3x_gn.yaml"
+MODEL:
+  # Train from random initialization.
+  WEIGHTS: ""
+  # It makes sense to divide by STD when training from scratch
+  # But it seems to make no difference on the results and C2's models didn't do this.
+  # So we keep things consistent with C2.
+  # PIXEL_STD: [57.375, 57.12, 58.395]
+  MASK_ON: True
+  BACKBONE:
+    FREEZE_AT: 0
+# NOTE: Please refer to Rethinking ImageNet Pre-training https://arxiv.org/abs/1811.08883
+# to learn what you need for training from scratch.

preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/scratch_mask_rcnn_R_50_FPN_9x_gn.yaml

+_BASE_: "mask_rcnn_R_50_FPN_3x_gn.yaml"
+MODEL:
+  PIXEL_STD: [57.375, 57.12, 58.395]
+  WEIGHTS: ""
+  MASK_ON: True
+  RESNETS:
+    STRIDE_IN_1X1: False
+  BACKBONE:
+    FREEZE_AT: 0
+SOLVER:
+  # 9x schedule
+  IMS_PER_BATCH: 64  # 4x the standard
+  STEPS: (187500, 197500)  # last 60/4==15k and last 20/4==5k
+  MAX_ITER: 202500   # 90k * 9 / 4
+  BASE_LR: 0.08
+TEST:
+  EVAL_PERIOD: 2500
+# NOTE: Please refer to Rethinking ImageNet Pre-training https://arxiv.org/abs/1811.08883
+# to learn what you need for training from scratch.

preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/scratch_mask_rcnn_R_50_FPN_9x_syncbn.yaml

+_BASE_: "mask_rcnn_R_50_FPN_3x_syncbn.yaml"
+MODEL:
+  PIXEL_STD: [57.375, 57.12, 58.395]
+  WEIGHTS: ""
+  MASK_ON: True
+  RESNETS:
+    STRIDE_IN_1X1: False
+  BACKBONE:
+    FREEZE_AT: 0
+SOLVER:
+  # 9x schedule
+  IMS_PER_BATCH: 64  # 4x the standard
+  STEPS: (187500, 197500)  # last 60/4==15k and last 20/4==5k
+  MAX_ITER: 202500   # 90k * 9 / 4
+  BASE_LR: 0.08
+TEST:
+  EVAL_PERIOD: 2500
+# NOTE: Please refer to Rethinking ImageNet Pre-training https://arxiv.org/abs/1811.08883
+# to learn what you need for training from scratch.

preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/semantic_R_50_FPN_1x.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  META_ARCHITECTURE: "SemanticSegmentor"
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+DATASETS:
+  TRAIN: ("coco_2017_train_panoptic_stuffonly",)
+  TEST: ("coco_2017_val_panoptic_stuffonly",)
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)

preprocess/humanparsing/mhp_extension/detectron2/configs/PascalVOC-Detection/faster_rcnn_R_50_C4.yaml

+_BASE_: "../Base-RCNN-C4.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 20
+INPUT:
+  MIN_SIZE_TRAIN: (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800)
+  MIN_SIZE_TEST: 800
+DATASETS:
+  TRAIN: ('voc_2007_trainval', 'voc_2012_trainval')
+  TEST: ('voc_2007_test',)
+SOLVER:
+  STEPS: (12000, 16000)
+  MAX_ITER: 18000  # 17.4 epochs
+  WARMUP_ITERS: 100

preprocess/humanparsing/mhp_extension/detectron2/configs/PascalVOC-Detection/faster_rcnn_R_50_FPN.yaml

+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 20
+INPUT:
+  MIN_SIZE_TRAIN: (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800)
+  MIN_SIZE_TEST: 800
+DATASETS:
+  TRAIN: ('voc_2007_trainval', 'voc_2012_trainval')
+  TEST: ('voc_2007_test',)
+SOLVER:
+  STEPS: (12000, 16000)
+  MAX_ITER: 18000  # 17.4 epochs
+  WARMUP_ITERS: 100

preprocess/humanparsing/mhp_extension/detectron2/configs/my_Base-RCNN-FPN.yaml

+MODEL:
+  META_ARCHITECTURE: "GeneralizedRCNN"
+  BACKBONE:
+    NAME: "build_resnet_fpn_backbone"
+  RESNETS:
+    OUT_FEATURES: ["res2", "res3", "res4", "res5"]
+  FPN:
+    IN_FEATURES: ["res2", "res3", "res4", "res5"]
+  ANCHOR_GENERATOR:
+    SIZES: [[32], [64], [128], [256], [512]]  # One size for each in feature map
+    ASPECT_RATIOS: [[0.5, 1.0, 2.0]]  # Three aspect ratios (same for all in feature maps)
+  RPN:
+    IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
+    PRE_NMS_TOPK_TRAIN: 2000  # Per FPN level
+    PRE_NMS_TOPK_TEST: 1000  # Per FPN level
+    # Detectron1 uses 2000 proposals per-batch,
+    # (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
+    # which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
+    POST_NMS_TOPK_TRAIN: 1000
+    POST_NMS_TOPK_TEST: 1000
+  ROI_HEADS:
+    NAME: "StandardROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+  ROI_MASK_HEAD:
+    NAME: "MaskRCNNConvUpsampleHead"
+    NUM_CONV: 4
+    POOLER_RESOLUTION: 14
+DATASETS:
+  TRAIN: ("coco_2017_train",)
+  TEST: ("coco_2017_val",)
+SOLVER:
+  IMS_PER_BATCH: 2
+  BASE_LR: 0.02
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
+VERSION: 2

preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/README.md

+These are quick configs for performance or accuracy regression tracking purposes.

preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/cascade_mask_rcnn_R_50_FPN_inference_acc_test.yaml

+_BASE_: "../Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml"
+MODEL:
+  WEIGHTS: "detectron2://Misc/cascade_mask_rcnn_R_50_FPN_3x/144998488/model_final_480dd8.pkl"
+DATASETS:
+  TEST: ("coco_2017_val_100",)
+TEST:
+  EXPECTED_RESULTS: [["bbox", "AP", 50.18, 0.02], ["segm", "AP",  43.87, 0.02]]

preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/cascade_mask_rcnn_R_50_FPN_instant_test.yaml

+_BASE_: "../Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml"
+DATASETS:
+  TRAIN: ("coco_2017_val_100",)
+  TEST: ("coco_2017_val_100",)
+SOLVER:
+  BASE_LR: 0.005
+  STEPS: (30,)
+  MAX_ITER: 40
+  IMS_PER_BATCH: 4
+DATALOADER:
+  NUM_WORKERS: 2

preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/fast_rcnn_R_50_FPN_inference_acc_test.yaml

+_BASE_: "../COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml"
+MODEL:
+  WEIGHTS: "detectron2://COCO-Detection/fast_rcnn_R_50_FPN_1x/137635226/model_final_e5f7ce.pkl"
+DATASETS:
+  TEST: ("coco_2017_val_100",)
+TEST:
+  EXPECTED_RESULTS: [["bbox", "AP", 45.70, 0.02]]

preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/fast_rcnn_R_50_FPN_instant_test.yaml

+_BASE_: "../COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+DATASETS:
+  TRAIN: ("coco_2017_val_100",)
+  PROPOSAL_FILES_TRAIN: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_val_box_proposals_ee0dad.pkl", )
+  TEST: ("coco_2017_val_100",)
+  PROPOSAL_FILES_TEST: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_val_box_proposals_ee0dad.pkl", )
+SOLVER:
+  BASE_LR: 0.005
+  STEPS: (30,)
+  MAX_ITER: 40
+  IMS_PER_BATCH: 4
+DATALOADER:
+  NUM_WORKERS: 2