support v0.6

projects/DensePose/configs/densepose_rcnn_R_50_FPN_s1x_legacy.yaml

+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NUM_COARSE_SEGM_CHANNELS: 15
+    POOLER_RESOLUTION: 14
+    HEATMAP_SIZE: 56
+    INDEX_WEIGHTS: 2.0
+    PART_WEIGHTS: 0.3
+    POINT_REGRESSION_WEIGHTS: 0.1
+    DECODER_ON: False
+SOLVER:
+  BASE_LR: 0.002
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

projects/DensePose/configs/evolution/Base-RCNN-FPN-Atop10P_CA.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"]
+    NUM_CLASSES: 1
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+  ROI_MASK_HEAD:
+    NAME: "MaskRCNNConvUpsampleHead"
+    NUM_CONV: 4
+    POOLER_RESOLUTION: 14
+DATASETS:
+  TRAIN: ("base_coco_2017_train", "densepose_coco_2014_train")
+  TEST: ("densepose_chimps",)
+  CATEGORY_MAPS:
+    "base_coco_2017_train":
+      "16": 1 # bird -> person
+      "17": 1 # cat -> person
+      "18": 1 # dog -> person
+      "19": 1 # horse -> person
+      "20": 1 # sheep -> person
+      "21": 1 # cow -> person
+      "22": 1 # elephant -> person
+      "23": 1 # bear -> person
+      "24": 1 # zebra -> person
+      "25": 1 # girafe -> person
+    "base_coco_2017_val":
+      "16": 1 # bird -> person
+      "17": 1 # cat -> person
+      "18": 1 # dog -> person
+      "19": 1 # horse -> person
+      "20": 1 # sheep -> person
+      "21": 1 # cow -> person
+      "22": 1 # elephant -> person
+      "23": 1 # bear -> person
+      "24": 1 # zebra -> person
+      "25": 1 # girafe -> person
+  WHITELISTED_CATEGORIES:
+    "base_coco_2017_train":
+      - 1  # person
+      - 16 # bird
+      - 17 # cat
+      - 18 # dog
+      - 19 # horse
+      - 20 # sheep
+      - 21 # cow
+      - 22 # elephant
+      - 23 # bear
+      - 24 # zebra
+      - 25 # girafe
+    "base_coco_2017_val":
+      - 1  # person
+      - 16 # bird
+      - 17 # cat
+      - 18 # dog
+      - 19 # horse
+      - 20 # sheep
+      - 21 # cow
+      - 22 # elephant
+      - 23 # bear
+      - 24 # zebra
+      - 25 # girafe
+SOLVER:
+  IMS_PER_BATCH: 16
+  BASE_LR: 0.02
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
+VERSION: 2

projects/DensePose/configs/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA.yaml

+_BASE_: "Base-RCNN-FPN-Atop10P_CA.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  DENSEPOSE_ON: True
+  ROI_HEADS:
+    NAME: "DensePoseROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+    NUM_CLASSES: 1
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+    POOLER_TYPE: "ROIAlign"
+    NUM_COARSE_SEGM_CHANNELS: 2
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    INDEX_WEIGHTS: 1.0
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  WARMUP_FACTOR: 0.025
+  MAX_ITER: 270000
+  STEPS: (210000, 250000)

projects/DensePose/configs/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA_B_coarsesegm.yaml

+_BASE_: "Base-RCNN-FPN-Atop10P_CA.yaml"
+MODEL:
+  WEIGHTS: https://dl.fbaipublicfiles.com/densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA/217578784/model_final_9fe1cc.pkl
+  RESNETS:
+    DEPTH: 50
+  DENSEPOSE_ON: True
+  ROI_HEADS:
+    NAME: "DensePoseROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+    NUM_CLASSES: 1
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+    POOLER_TYPE: "ROIAlign"
+    NUM_COARSE_SEGM_CHANNELS: 2
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+BOOTSTRAP_DATASETS:
+  - DATASET: "chimpnsee"
+    RATIO: 1.0
+    IMAGE_LOADER:
+      TYPE: "video_keyframe"
+      SELECT:
+        STRATEGY: "random_k"
+        NUM_IMAGES: 4
+      TRANSFORM:
+        TYPE: "resize"
+        MIN_SIZE: 800
+        MAX_SIZE: 1333
+      BATCH_SIZE: 8
+      NUM_WORKERS: 1
+    INFERENCE:
+      INPUT_BATCH_SIZE: 1
+      OUTPUT_BATCH_SIZE: 1
+    DATA_SAMPLER:
+      # supported types:
+      #   densepose_uniform
+      #   densepose_UV_confidence
+      #   densepose_fine_segm_confidence
+      #   densepose_coarse_segm_confidence
+      TYPE: "densepose_coarse_segm_confidence"
+      COUNT_PER_CLASS: 8
+    FILTER:
+      TYPE: "detection_score"
+      MIN_VALUE: 0.8
+BOOTSTRAP_MODEL:
+  WEIGHTS: https://dl.fbaipublicfiles.com/densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA/217578784/model_final_9fe1cc.pkl
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 270000
+  STEPS: (210000, 250000)

projects/DensePose/configs/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA_B_finesegm.yaml

+_BASE_: "Base-RCNN-FPN-Atop10P_CA.yaml"
+MODEL:
+  WEIGHTS: https://dl.fbaipublicfiles.com/densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA/217578784/model_final_9fe1cc.pkl
+  RESNETS:
+    DEPTH: 50
+  DENSEPOSE_ON: True
+  ROI_HEADS:
+    NAME: "DensePoseROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+    NUM_CLASSES: 1
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+    POOLER_TYPE: "ROIAlign"
+    NUM_COARSE_SEGM_CHANNELS: 2
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+BOOTSTRAP_DATASETS:
+  - DATASET: "chimpnsee"
+    RATIO: 1.0
+    IMAGE_LOADER:
+      TYPE: "video_keyframe"
+      SELECT:
+        STRATEGY: "random_k"
+        NUM_IMAGES: 4
+      TRANSFORM:
+        TYPE: "resize"
+        MIN_SIZE: 800
+        MAX_SIZE: 1333
+      BATCH_SIZE: 8
+      NUM_WORKERS: 1
+    INFERENCE:
+      INPUT_BATCH_SIZE: 1
+      OUTPUT_BATCH_SIZE: 1
+    DATA_SAMPLER:
+      # supported types:
+      #   densepose_uniform
+      #   densepose_UV_confidence
+      #   densepose_fine_segm_confidence
+      #   densepose_coarse_segm_confidence
+      TYPE: "densepose_fine_segm_confidence"
+      COUNT_PER_CLASS: 8
+    FILTER:
+      TYPE: "detection_score"
+      MIN_VALUE: 0.8
+BOOTSTRAP_MODEL:
+  WEIGHTS: https://dl.fbaipublicfiles.com/densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA/217578784/model_final_9fe1cc.pkl
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 270000
+  STEPS: (210000, 250000)

projects/DensePose/configs/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA_B_uniform.yaml

+_BASE_: "Base-RCNN-FPN-Atop10P_CA.yaml"
+MODEL:
+  WEIGHTS: https://dl.fbaipublicfiles.com/densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA/217578784/model_final_9fe1cc.pkl
+  RESNETS:
+    DEPTH: 50
+  DENSEPOSE_ON: True
+  ROI_HEADS:
+    NAME: "DensePoseROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+    NUM_CLASSES: 1
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+    POOLER_TYPE: "ROIAlign"
+    NUM_COARSE_SEGM_CHANNELS: 2
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+BOOTSTRAP_DATASETS:
+  - DATASET: "chimpnsee"
+    RATIO: 1.0
+    IMAGE_LOADER:
+      TYPE: "video_keyframe"
+      SELECT:
+        STRATEGY: "random_k"
+        NUM_IMAGES: 4
+      TRANSFORM:
+        TYPE: "resize"
+        MIN_SIZE: 800
+        MAX_SIZE: 1333
+      BATCH_SIZE: 8
+      NUM_WORKERS: 1
+    INFERENCE:
+      INPUT_BATCH_SIZE: 1
+      OUTPUT_BATCH_SIZE: 1
+    DATA_SAMPLER:
+      # supported types:
+      #   densepose_uniform
+      #   densepose_UV_confidence
+      #   densepose_fine_segm_confidence
+      #   densepose_coarse_segm_confidence
+      TYPE: "densepose_uniform"
+      COUNT_PER_CLASS: 8
+    FILTER:
+      TYPE: "detection_score"
+      MIN_VALUE: 0.8
+BOOTSTRAP_MODEL:
+  WEIGHTS: https://dl.fbaipublicfiles.com/densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA/217578784/model_final_9fe1cc.pkl
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 270000
+  STEPS: (210000, 250000)

projects/DensePose/configs/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA_B_uv.yaml

+_BASE_: "Base-RCNN-FPN-Atop10P_CA.yaml"
+MODEL:
+  WEIGHTS: https://dl.fbaipublicfiles.com/densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA/217578784/model_final_9fe1cc.pkl
+  RESNETS:
+    DEPTH: 50
+  DENSEPOSE_ON: True
+  ROI_HEADS:
+    NAME: "DensePoseROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+    NUM_CLASSES: 1
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+    POOLER_TYPE: "ROIAlign"
+    NUM_COARSE_SEGM_CHANNELS: 2
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+BOOTSTRAP_DATASETS:
+  - DATASET: "chimpnsee"
+    RATIO: 1.0
+    IMAGE_LOADER:
+      TYPE: "video_keyframe"
+      SELECT:
+        STRATEGY: "random_k"
+        NUM_IMAGES: 4
+      TRANSFORM:
+        TYPE: "resize"
+        MIN_SIZE: 800
+        MAX_SIZE: 1333
+      BATCH_SIZE: 8
+      NUM_WORKERS: 1
+    INFERENCE:
+      INPUT_BATCH_SIZE: 1
+      OUTPUT_BATCH_SIZE: 1
+    DATA_SAMPLER:
+      # supported types:
+      #   densepose_uniform
+      #   densepose_UV_confidence
+      #   densepose_fine_segm_confidence
+      #   densepose_coarse_segm_confidence
+      TYPE: "densepose_UV_confidence"
+      COUNT_PER_CLASS: 8
+    FILTER:
+      TYPE: "detection_score"
+      MIN_VALUE: 0.8
+BOOTSTRAP_MODEL:
+  WEIGHTS: https://dl.fbaipublicfiles.com/densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA/217578784/model_final_9fe1cc.pkl
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 270000
+  STEPS: (210000, 250000)

projects/DensePose/configs/quick_schedules/cse/densepose_rcnn_R_50_FPN_DL_instant_test.yaml

+_BASE_: "../../cse/Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+DATASETS:
+  TRAIN: ("densepose_coco_2014_minival_100_cse",)
+  TEST: ("densepose_coco_2014_minival_100_cse",)
+SOLVER:
+  MAX_ITER: 40
+  STEPS: (30,)

projects/DensePose/configs/quick_schedules/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_instant_test.yaml

+_BASE_: "../../cse/Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_5001":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5001
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_5001_256.pkl"
+        "dog_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_5002_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_train1"
+    - "densepose_lvis_v1_train2"
+  TEST:
+    - "densepose_lvis_v1_val_animals_100"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_train1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_train2":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_val_animals_100":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_5001"
+    "3": "dog_5002"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 40
+  STEPS: (30,)

projects/DensePose/configs/quick_schedules/densepose_rcnn_HRFPN_HRNet_w32_instant_test.yaml

+_BASE_: "../HRNet/densepose_rcnn_HRFPN_HRNet_w32_s1x.yaml"
+DATASETS:
+  TRAIN: ("densepose_coco_2014_minival_100",)
+  TEST: ("densepose_coco_2014_minival_100",)
+SOLVER:
+  MAX_ITER: 40
+  STEPS: (30,)
+  IMS_PER_BATCH: 2

projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_DL_instant_test.yaml

+_BASE_: "../Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+DATASETS:
+  TRAIN: ("densepose_coco_2014_minival_100",)
+  TEST: ("densepose_coco_2014_minival_100",)
+SOLVER:
+  MAX_ITER: 40
+  STEPS: (30,)

projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_TTA_inference_acc_test.yaml

+_BASE_: "../densepose_rcnn_R_50_FPN_s1x.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/densepose_rcnn_R_50_FPN_s1x/165712039/model_final_162be9.pkl"
+DATASETS:
+  TRAIN: ()
+  TEST: ("densepose_coco_2014_minival_100",)
+TEST:
+  AUG:
+    ENABLED: True
+    MIN_SIZES: (400, 500, 600, 700, 800, 900, 1000, 1100, 1200)
+    MAX_SIZE: 4000
+    FLIP: True
+  EXPECTED_RESULTS: [["bbox_TTA", "AP", 61.74, 0.03], ["densepose_gps_TTA", "AP",  60.22, 0.03], ["densepose_gpsm_TTA", "AP", 63.59, 0.03]]

projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_WC1_instant_test.yaml

+_BASE_: "../Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+DATASETS:
+  TRAIN: ("densepose_coco_2014_minival_100",)
+  TEST: ("densepose_coco_2014_minival_100",)
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 40
+  STEPS: (30,)
+  WARMUP_FACTOR: 0.025

projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_WC2_instant_test.yaml

+_BASE_: "../Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+DATASETS:
+  TRAIN: ("densepose_coco_2014_minival_100",)
+  TEST: ("densepose_coco_2014_minival_100",)
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 40 
+  STEPS: (30,)
+  WARMUP_FACTOR: 0.025

projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_inference_acc_test.yaml

+_BASE_: "../densepose_rcnn_R_50_FPN_s1x.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/densepose_rcnn_R_50_FPN_s1x/165712039/model_final_162be9.pkl"
+DATASETS:
+  TRAIN: ()
+  TEST: ("densepose_coco_2014_minival_100",)
+TEST:
+  EXPECTED_RESULTS: [["bbox", "AP", 59.27, 0.025], ["densepose_gps", "AP",  60.11, 0.02], ["densepose_gpsm", "AP", 64.09, 0.02]]

projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_instant_test.yaml

+_BASE_: "../Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+DATASETS:
+  TRAIN: ("densepose_coco_2014_minival_100",)
+  TEST: ("densepose_coco_2014_minival_100",)
+SOLVER:
+  MAX_ITER: 40
+  STEPS: (30,)

projects/DensePose/configs/quick_schedules/densepose_rcnn_R_50_FPN_training_acc_test.yaml

+_BASE_: "../Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  ROI_HEADS:
+    NUM_CLASSES: 1
+DATASETS:
+  TRAIN: ("densepose_coco_2014_minival",)
+  TEST: ("densepose_coco_2014_minival",)
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+    CLIP_TYPE: norm
+    CLIP_VALUE: 1.0
+  MAX_ITER: 6000
+  STEPS: (5500, 5800)
+TEST:
+  EXPECTED_RESULTS: [["bbox", "AP", 76.2477, 1.0], ["densepose_gps", "AP", 79.6090, 1.5], ["densepose_gpsm", "AP", 80.0061, 1.5]]
+

projects/DensePose/densepose/__init__.py

+# Copyright (c) Facebook, Inc. and its affiliates.
+from .data.datasets import builtin  # just to register data
+from .converters import builtin as builtin_converters  # register converters
+from .config import (
+    add_densepose_config,
+    add_densepose_head_config,
+    add_hrnet_config,
+    add_dataset_category_config,
+    add_bootstrap_config,
+    load_bootstrap_config,
+)
+from .structures import DensePoseDataRelative, DensePoseList, DensePoseTransformData
+from .evaluation import DensePoseCOCOEvaluator
+from .modeling.roi_heads import DensePoseROIHeads
+from .modeling.test_time_augmentation import (
+    DensePoseGeneralizedRCNNWithTTA,
+    DensePoseDatasetMapperTTA,
+)
+from .utils.transform import load_from_cfg
+from .modeling.hrfpn import build_hrfpn_backbone

projects/DensePose/densepose/config.py

+# -*- coding = utf-8 -*-
+# Copyright (c) Facebook, Inc. and its affiliates.
+# pyre-ignore-all-errors
+
+from detectron2.config import CfgNode as CN
+
+
+def add_dataset_category_config(cfg: CN):
+    """
+    Add config for additional category-related dataset options
+     - category whitelisting
+     - category mapping
+    """
+    _C = cfg
+    _C.DATASETS.CATEGORY_MAPS = CN(new_allowed=True)
+    _C.DATASETS.WHITELISTED_CATEGORIES = CN(new_allowed=True)
+    # class to mesh mapping
+    _C.DATASETS.CLASS_TO_MESH_NAME_MAPPING = CN(new_allowed=True)
+
+
+def add_evaluation_config(cfg: CN):
+    _C = cfg
+    _C.DENSEPOSE_EVALUATION = CN()
+    # evaluator type, possible values:
+    #  - "iou": evaluator for models that produce iou data
+    #  - "cse": evaluator for models that produce cse data
+    _C.DENSEPOSE_EVALUATION.TYPE = "iou"
+    # storage for DensePose results, possible values:
+    #  - "none": no explicit storage, all the results are stored in the
+    #            dictionary with predictions, memory intensive;
+    #            historically the default storage type
+    #  - "ram": RAM storage, uses per-process RAM storage, which is
+    #           reduced to a single process storage on later stages,
+    #           less memory intensive
+    #  - "file": file storage, uses per-process file-based storage,
+    #            the least memory intensive, but may create bottlenecks
+    #            on file system accesses
+    _C.DENSEPOSE_EVALUATION.STORAGE = "none"
+    # minimum threshold for IOU values: the lower its values is,
+    # the more matches are produced (and the higher the AP score)
+    _C.DENSEPOSE_EVALUATION.MIN_IOU_THRESHOLD = 0.5
+    # Non-distributed inference is slower (at inference time) but can avoid RAM OOM
+    _C.DENSEPOSE_EVALUATION.DISTRIBUTED_INFERENCE = True
+    # evaluate mesh alignment based on vertex embeddings, only makes sense in CSE context
+    _C.DENSEPOSE_EVALUATION.EVALUATE_MESH_ALIGNMENT = False
+    # meshes to compute mesh alignment for
+    _C.DENSEPOSE_EVALUATION.MESH_ALIGNMENT_MESH_NAMES = []
+
+
+def add_bootstrap_config(cfg: CN):
+    """ """
+    _C = cfg
+    _C.BOOTSTRAP_DATASETS = []
+    _C.BOOTSTRAP_MODEL = CN()
+    _C.BOOTSTRAP_MODEL.WEIGHTS = ""
+    _C.BOOTSTRAP_MODEL.DEVICE = "cuda"
+
+
+def get_bootstrap_dataset_config() -> CN:
+    _C = CN()
+    _C.DATASET = ""
+    # ratio used to mix data loaders
+    _C.RATIO = 0.1
+    # image loader
+    _C.IMAGE_LOADER = CN(new_allowed=True)
+    _C.IMAGE_LOADER.TYPE = ""
+    _C.IMAGE_LOADER.BATCH_SIZE = 4
+    _C.IMAGE_LOADER.NUM_WORKERS = 4
+    _C.IMAGE_LOADER.CATEGORIES = []
+    _C.IMAGE_LOADER.MAX_COUNT_PER_CATEGORY = 1_000_000
+    _C.IMAGE_LOADER.CATEGORY_TO_CLASS_MAPPING = CN(new_allowed=True)
+    # inference
+    _C.INFERENCE = CN()
+    # batch size for model inputs
+    _C.INFERENCE.INPUT_BATCH_SIZE = 4
+    # batch size to group model outputs
+    _C.INFERENCE.OUTPUT_BATCH_SIZE = 2
+    # sampled data
+    _C.DATA_SAMPLER = CN(new_allowed=True)
+    _C.DATA_SAMPLER.TYPE = ""
+    _C.DATA_SAMPLER.USE_GROUND_TRUTH_CATEGORIES = False
+    # filter
+    _C.FILTER = CN(new_allowed=True)
+    _C.FILTER.TYPE = ""
+    return _C
+
+
+def load_bootstrap_config(cfg: CN):
+    """
+    Bootstrap datasets are given as a list of `dict` that are not automatically
+    converted into CfgNode. This method processes all bootstrap dataset entries
+    and ensures that they are in CfgNode format and comply with the specification
+    """
+    if not cfg.BOOTSTRAP_DATASETS:
+        return
+
+    bootstrap_datasets_cfgnodes = []
+    for dataset_cfg in cfg.BOOTSTRAP_DATASETS:
+        _C = get_bootstrap_dataset_config().clone()
+        _C.merge_from_other_cfg(CN(dataset_cfg))
+        bootstrap_datasets_cfgnodes.append(_C)
+    cfg.BOOTSTRAP_DATASETS = bootstrap_datasets_cfgnodes
+
+
+def add_densepose_head_cse_config(cfg: CN):
+    """
+    Add configuration options for Continuous Surface Embeddings (CSE)
+    """
+    _C = cfg
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE = CN()
+    # Dimensionality D of the embedding space
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.EMBED_SIZE = 16
+    # Embedder specifications for various mesh IDs
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.EMBEDDERS = CN(new_allowed=True)
+    # normalization coefficient for embedding distances
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.EMBEDDING_DIST_GAUSS_SIGMA = 0.01
+    # normalization coefficient for geodesic distances
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.GEODESIC_DIST_GAUSS_SIGMA = 0.01
+    # embedding loss weight
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.EMBED_LOSS_WEIGHT = 0.6
+    # embedding loss name, currently the following options are supported:
+    # - EmbeddingLoss: cross-entropy on vertex labels
+    # - SoftEmbeddingLoss: cross-entropy on vertex label combined with
+    #    Gaussian penalty on distance between vertices
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.EMBED_LOSS_NAME = "EmbeddingLoss"
+    # optimizer hyperparameters
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.FEATURES_LR_FACTOR = 1.0
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.EMBEDDING_LR_FACTOR = 1.0
+    # Shape to shape cycle consistency loss parameters:
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.SHAPE_TO_SHAPE_CYCLE_LOSS = CN({"ENABLED": False})
+    # shape to shape cycle consistency loss weight
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.SHAPE_TO_SHAPE_CYCLE_LOSS.WEIGHT = 0.025
+    # norm type used for loss computation
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.SHAPE_TO_SHAPE_CYCLE_LOSS.NORM_P = 2
+    # normalization term for embedding similarity matrices
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.SHAPE_TO_SHAPE_CYCLE_LOSS.TEMPERATURE = 0.05
+    # maximum number of vertices to include into shape to shape cycle loss
+    # if negative or zero, all vertices are considered
+    # if positive, random subset of vertices of given size is considered
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.SHAPE_TO_SHAPE_CYCLE_LOSS.MAX_NUM_VERTICES = 4936
+    # Pixel to shape cycle consistency loss parameters:
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.PIX_TO_SHAPE_CYCLE_LOSS = CN({"ENABLED": False})
+    # pixel to shape cycle consistency loss weight
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.PIX_TO_SHAPE_CYCLE_LOSS.WEIGHT = 0.0001
+    # norm type used for loss computation
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.PIX_TO_SHAPE_CYCLE_LOSS.NORM_P = 2
+    # map images to all meshes and back (if false, use only gt meshes from the batch)
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.PIX_TO_SHAPE_CYCLE_LOSS.USE_ALL_MESHES_NOT_GT_ONLY = False
+    # Randomly select at most this number of pixels from every instance
+    # if negative or zero, all vertices are considered
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.PIX_TO_SHAPE_CYCLE_LOSS.NUM_PIXELS_TO_SAMPLE = 100
+    # normalization factor for pixel to pixel distances (higher value = smoother distribution)
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.PIX_TO_SHAPE_CYCLE_LOSS.PIXEL_SIGMA = 5.0
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.PIX_TO_SHAPE_CYCLE_LOSS.TEMPERATURE_PIXEL_TO_VERTEX = 0.05
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CSE.PIX_TO_SHAPE_CYCLE_LOSS.TEMPERATURE_VERTEX_TO_PIXEL = 0.05
+
+
+def add_densepose_head_config(cfg: CN):
+    """
+    Add config for densepose head.
+    """
+    _C = cfg
+
+    _C.MODEL.DENSEPOSE_ON = True
+
+    _C.MODEL.ROI_DENSEPOSE_HEAD = CN()
+    _C.MODEL.ROI_DENSEPOSE_HEAD.NAME = ""
+    _C.MODEL.ROI_DENSEPOSE_HEAD.NUM_STACKED_CONVS = 8
+    # Number of parts used for point labels
+    _C.MODEL.ROI_DENSEPOSE_HEAD.NUM_PATCHES = 24
+    _C.MODEL.ROI_DENSEPOSE_HEAD.DECONV_KERNEL = 4
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CONV_HEAD_DIM = 512
+    _C.MODEL.ROI_DENSEPOSE_HEAD.CONV_HEAD_KERNEL = 3
+    _C.MODEL.ROI_DENSEPOSE_HEAD.UP_SCALE = 2
+    _C.MODEL.ROI_DENSEPOSE_HEAD.HEATMAP_SIZE = 112
+    _C.MODEL.ROI_DENSEPOSE_HEAD.POOLER_TYPE = "ROIAlignV2"
+    _C.MODEL.ROI_DENSEPOSE_HEAD.POOLER_RESOLUTION = 28
+    _C.MODEL.ROI_DENSEPOSE_HEAD.POOLER_SAMPLING_RATIO = 2
+    _C.MODEL.ROI_DENSEPOSE_HEAD.NUM_COARSE_SEGM_CHANNELS = 2  # 15 or 2
+    # Overlap threshold for an RoI to be considered foreground (if >= FG_IOU_THRESHOLD)
+    _C.MODEL.ROI_DENSEPOSE_HEAD.FG_IOU_THRESHOLD = 0.7
+    # Loss weights for annotation masks.(14 Parts)
+    _C.MODEL.ROI_DENSEPOSE_HEAD.INDEX_WEIGHTS = 5.0
+    # Loss weights for surface parts. (24 Parts)
+    _C.MODEL.ROI_DENSEPOSE_HEAD.PART_WEIGHTS = 1.0
+    # Loss weights for UV regression.
+    _C.MODEL.ROI_DENSEPOSE_HEAD.POINT_REGRESSION_WEIGHTS = 0.01
+    # Coarse segmentation is trained using instance segmentation task data
+    _C.MODEL.ROI_DENSEPOSE_HEAD.COARSE_SEGM_TRAINED_BY_MASKS = False
+    # For Decoder
+    _C.MODEL.ROI_DENSEPOSE_HEAD.DECODER_ON = True
+    _C.MODEL.ROI_DENSEPOSE_HEAD.DECODER_NUM_CLASSES = 256
+    _C.MODEL.ROI_DENSEPOSE_HEAD.DECODER_CONV_DIMS = 256
+    _C.MODEL.ROI_DENSEPOSE_HEAD.DECODER_NORM = ""
+    _C.MODEL.ROI_DENSEPOSE_HEAD.DECODER_COMMON_STRIDE = 4
+    # For DeepLab head
+    _C.MODEL.ROI_DENSEPOSE_HEAD.DEEPLAB = CN()
+    _C.MODEL.ROI_DENSEPOSE_HEAD.DEEPLAB.NORM = "GN"
+    _C.MODEL.ROI_DENSEPOSE_HEAD.DEEPLAB.NONLOCAL_ON = 0
+    # Predictor class name, must be registered in DENSEPOSE_PREDICTOR_REGISTRY
+    # Some registered predictors:
+    #   "DensePoseChartPredictor": predicts segmentation and UV coordinates for predefined charts
+    #   "DensePoseChartWithConfidencePredictor": predicts segmentation, UV coordinates
+    #       and associated confidences for predefined charts (default)
+    #   "DensePoseEmbeddingWithConfidencePredictor": predicts segmentation, embeddings
+    #       and associated confidences for CSE
+    _C.MODEL.ROI_DENSEPOSE_HEAD.PREDICTOR_NAME = "DensePoseChartWithConfidencePredictor"
+    # Loss class name, must be registered in DENSEPOSE_LOSS_REGISTRY
+    # Some registered losses:
+    #   "DensePoseChartLoss": loss for chart-based models that estimate
+    #      segmentation and UV coordinates
+    #   "DensePoseChartWithConfidenceLoss": loss for chart-based models that estimate
+    #      segmentation, UV coordinates and the corresponding confidences (default)
+    _C.MODEL.ROI_DENSEPOSE_HEAD.LOSS_NAME = "DensePoseChartWithConfidenceLoss"
+    # Confidences
+    # Enable learning UV confidences (variances) along with the actual values
+    _C.MODEL.ROI_DENSEPOSE_HEAD.UV_CONFIDENCE = CN({"ENABLED": False})
+    # UV confidence lower bound
+    _C.MODEL.ROI_DENSEPOSE_HEAD.UV_CONFIDENCE.EPSILON = 0.01
+    # Enable learning segmentation confidences (variances) along with the actual values
+    _C.MODEL.ROI_DENSEPOSE_HEAD.SEGM_CONFIDENCE = CN({"ENABLED": False})
+    # Segmentation confidence lower bound
+    _C.MODEL.ROI_DENSEPOSE_HEAD.SEGM_CONFIDENCE.EPSILON = 0.01
+    # Statistical model type for confidence learning, possible values:
+    # - "iid_iso": statistically independent identically distributed residuals
+    #    with isotropic covariance
+    # - "indep_aniso": statistically independent residuals with anisotropic
+    #    covariances
+    _C.MODEL.ROI_DENSEPOSE_HEAD.UV_CONFIDENCE.TYPE = "iid_iso"
+    # List of angles for rotation in data augmentation during training
+    _C.INPUT.ROTATION_ANGLES = [0]
+    _C.TEST.AUG.ROTATION_ANGLES = ()  # Rotation TTA
+
+    add_densepose_head_cse_config(cfg)
+
+
+def add_hrnet_config(cfg: CN):
+    """
+    Add config for HRNet backbone.
+    """
+    _C = cfg
+
+    # For HigherHRNet w32
+    _C.MODEL.HRNET = CN()
+    _C.MODEL.HRNET.STEM_INPLANES = 64
+    _C.MODEL.HRNET.STAGE2 = CN()
+    _C.MODEL.HRNET.STAGE2.NUM_MODULES = 1
+    _C.MODEL.HRNET.STAGE2.NUM_BRANCHES = 2
+    _C.MODEL.HRNET.STAGE2.BLOCK = "BASIC"
+    _C.MODEL.HRNET.STAGE2.NUM_BLOCKS = [4, 4]
+    _C.MODEL.HRNET.STAGE2.NUM_CHANNELS = [32, 64]
+    _C.MODEL.HRNET.STAGE2.FUSE_METHOD = "SUM"
+    _C.MODEL.HRNET.STAGE3 = CN()
+    _C.MODEL.HRNET.STAGE3.NUM_MODULES = 4
+    _C.MODEL.HRNET.STAGE3.NUM_BRANCHES = 3
+    _C.MODEL.HRNET.STAGE3.BLOCK = "BASIC"
+    _C.MODEL.HRNET.STAGE3.NUM_BLOCKS = [4, 4, 4]
+    _C.MODEL.HRNET.STAGE3.NUM_CHANNELS = [32, 64, 128]
+    _C.MODEL.HRNET.STAGE3.FUSE_METHOD = "SUM"
+    _C.MODEL.HRNET.STAGE4 = CN()
+    _C.MODEL.HRNET.STAGE4.NUM_MODULES = 3
+    _C.MODEL.HRNET.STAGE4.NUM_BRANCHES = 4
+    _C.MODEL.HRNET.STAGE4.BLOCK = "BASIC"
+    _C.MODEL.HRNET.STAGE4.NUM_BLOCKS = [4, 4, 4, 4]
+    _C.MODEL.HRNET.STAGE4.NUM_CHANNELS = [32, 64, 128, 256]
+    _C.MODEL.HRNET.STAGE4.FUSE_METHOD = "SUM"
+
+    _C.MODEL.HRNET.HRFPN = CN()
+    _C.MODEL.HRNET.HRFPN.OUT_CHANNELS = 256
+
+
+def add_densepose_config(cfg: CN):
+    add_densepose_head_config(cfg)
+    add_hrnet_config(cfg)
+    add_bootstrap_config(cfg)
+    add_dataset_category_config(cfg)
+    add_evaluation_config(cfg)

projects/DensePose/densepose/converters/__init__.py

+# Copyright (c) Facebook, Inc. and its affiliates.
+
+from .hflip import HFlipConverter
+from .to_mask import ToMaskConverter
+from .to_chart_result import ToChartResultConverter, ToChartResultConverterWithConfidences
+from .segm_to_mask import (
+    predictor_output_with_fine_and_coarse_segm_to_mask,
+    predictor_output_with_coarse_segm_to_mask,
+    resample_fine_and_coarse_segm_to_bbox,
+)
+from .chart_output_to_chart_result import (
+    densepose_chart_predictor_output_to_result,
+    densepose_chart_predictor_output_to_result_with_confidences,
+)
+from .chart_output_hflip import densepose_chart_predictor_output_hflip