models/cvpr2023.yaml

CUDNN_BENCHMARK: false
DATALOADER:
  ASPECT_RATIO_GROUPING: true
  AUGMENTATION: true
  AUGMENTATION_FUN: default
  AUGMENTATION_TYPE: geometry
  FILTER_EMPTY_ANNOTATIONS: true
  NUM_WORKERS: 8
  REPEAT_THRESHOLD: 0.0
  RESIZE:
  - 320
  - 320
  SAMPLER_TRAIN: TrainingSampler
DATASETS:
  PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
  PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
  PROPOSAL_FILES_TEST: []
  PROPOSAL_FILES_TRAIN: []
  TEST:
  - stanford2d3d_test
  - tartanair_test
  TRAIN:
  - cities360_train
  - rgbdpano_train
DEBUG_ON: false
GLOBAL:
  HACK: 1.0
INPUT:
  CROP:
    ENABLED: false
    SIZE:
    - 0.9
    - 0.9
    TYPE: relative_range
  FORMAT: BGR
  MASK_FORMAT: polygon
  MAX_SIZE_TEST: 1333
  MAX_SIZE_TRAIN: 1333
  MIN_SIZE_TEST: 800
  MIN_SIZE_TRAIN:
  - 800
  MIN_SIZE_TRAIN_SAMPLING: choice
  ONLINE_CROP: false
  RANDOM_FLIP: horizontal
MODEL:
  ANCHOR_GENERATOR:
    ANGLES:
    - - -90
      - 0
      - 90
    ASPECT_RATIOS:
    - - 0.5
      - 1.0
      - 2.0
    NAME: DefaultAnchorGenerator
    OFFSET: 0.0
    SIZES:
    - - 32
      - 64
      - 128
      - 256
      - 512
  BACKBONE:
    FREEZE_AT: 2
    NAME: build_mit_backbone
  CENTER_ON: false
  DEVICE: cuda
  FPN:
    FUSE_TYPE: sum
    IN_FEATURES: []
    NORM: ''
    OUT_CHANNELS: 256
  FPN_CENTER_HEAD:
    COMMON_STRIDE: 4
    CONVS_DIM: 128
    IGNORE_VALUE: 360
    IN_FEATURES:
    - p2
    - p3
    - p4
    - p5
    LOSS_WEIGHT: 1.0
    NAME: CenterFPNHead
    NORM: GN
    NUM_CLASSES: 30
  FPN_GRAVITY_HEAD:
    COMMON_STRIDE: 4
    CONVS_DIM: 128
    IGNORE_VALUE: 360
    IN_FEATURES:
    - p2
    - p3
    - p4
    - p5
    LOSS_WEIGHT: 1.0
    NAME: GravityFPNHead
    NORM: GN
    NUM_CLASSES: 361
  FPN_HEADS:
    NAME: StandardFPNHeads
  FPN_LATITUDE_HEAD:
    COMMON_STRIDE: 4
    CONVS_DIM: 128
    IGNORE_VALUE: -1
    IN_FEATURES:
    - p2
    - p3
    - p4
    - p5
    LOSS_WEIGHT: 1.0
    NAME: LatitudeFPNHead
    NORM: GN
    NUM_CLASSES: 9
  FREEZE: []
  GRAVITY_DECODER:
    IGNORE_VALUE: 72
    LOSS_TYPE: classification
    LOSS_WEIGHT: 1.0
    NAME: GravityDecoder
    NUM_CLASSES: 73
  GRAVITY_ON: true
  HEIGHT_DECODER:
    LOSS_WEIGHT: 1.0
    NAME: HeightDecoder
  HEIGHT_ON: false
  KEYPOINT_ON: false
  LATITUDE_DECODER:
    IGNORE_VALUE: -1
    LOSS_TYPE: classification
    LOSS_WEIGHT: 1.0
    NAME: LatitudeDecoder
    NUM_CLASSES: 180
  LATITUDE_ON: true
  LOAD_PROPOSALS: false
  MASK_ON: false
  META_ARCHITECTURE: PersFormer
  PANOPTIC_FPN:
    COMBINE:
      ENABLED: true
      INSTANCES_CONFIDENCE_THRESH: 0.5
      OVERLAP_THRESH: 0.5
      STUFF_AREA_LIMIT: 4096
    INSTANCE_LOSS_WEIGHT: 1.0
  PARAM_DECODER:
    DEBUG_LAT: false
    DEBUG_UP: false
    INPUT_SIZE: 320
    LOSS_TYPE: regression
    LOSS_WEIGHT: 1.0
    NAME: ParamNet
    PREDICT_PARAMS:
    - roll
    - pitch
    - rel_focal
    - rel_cx
    - rel_cy
    SYNTHETIC_PRETRAIN: false
  PERSFORMER_HEADS:
    NAME: StandardPersformerHeads
  PIXEL_MEAN:
  - 103.53
  - 116.28
  - 123.675
  PIXEL_STD:
  - 1.0
  - 1.0
  - 1.0
  PROPOSAL_GENERATOR:
    MIN_SIZE: 0
    NAME: RPN
  RECOVER_PP: false
  RECOVER_RPF: false
  RESNETS:
    DEFORM_MODULATED: false
    DEFORM_NUM_GROUPS: 1
    DEFORM_ON_PER_STAGE:
    - false
    - false
    - false
    - false
    DEPTH: 50
    NORM: FrozenBN
    NUM_GROUPS: 1
    OUT_FEATURES:
    - res4
    RES2_OUT_CHANNELS: 256
    RES5_DILATION: 1
    STEM_OUT_CHANNELS: 64
    STRIDE_IN_1X1: true
    WIDTH_PER_GROUP: 64
  RETINANET:
    BBOX_REG_LOSS_TYPE: smooth_l1
    BBOX_REG_WEIGHTS: &id002
    - 1.0
    - 1.0
    - 1.0
    - 1.0
    FOCAL_LOSS_ALPHA: 0.25
    FOCAL_LOSS_GAMMA: 2.0
    IN_FEATURES:
    - p3
    - p4
    - p5
    - p6
    - p7
    IOU_LABELS:
    - 0
    - -1
    - 1
    IOU_THRESHOLDS:
    - 0.4
    - 0.5
    NMS_THRESH_TEST: 0.5
    NORM: ''
    NUM_CLASSES: 80
    NUM_CONVS: 4
    PRIOR_PROB: 0.01
    SCORE_THRESH_TEST: 0.05
    SMOOTH_L1_LOSS_BETA: 0.1
    TOPK_CANDIDATES_TEST: 1000
  ROI_BOX_CASCADE_HEAD:
    BBOX_REG_WEIGHTS:
    - &id001
      - 10.0
      - 10.0
      - 5.0
      - 5.0
    - - 20.0
      - 20.0
      - 10.0
      - 10.0
    - - 30.0
      - 30.0
      - 15.0
      - 15.0
    IOUS:
    - 0.5
    - 0.6
    - 0.7
  ROI_BOX_HEAD:
    BBOX_REG_LOSS_TYPE: smooth_l1
    BBOX_REG_LOSS_WEIGHT: 1.0
    BBOX_REG_WEIGHTS: *id001
    CLS_AGNOSTIC_BBOX_REG: false
    CONV_DIM: 256
    FC_DIM: 1024
    NAME: ''
    NORM: ''
    NUM_CONV: 0
    NUM_FC: 0
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_TYPE: ROIAlignV2
    SMOOTH_L1_BETA: 0.0
    TRAIN_ON_PRED_BOXES: false
  ROI_HEADS:
    BATCH_SIZE_PER_IMAGE: 512
    IN_FEATURES:
    - res4
    IOU_LABELS:
    - 0
    - 1
    IOU_THRESHOLDS:
    - 0.5
    NAME: Res5ROIHeads
    NMS_THRESH_TEST: 0.5
    NUM_CLASSES: 80
    POSITIVE_FRACTION: 0.25
    PROPOSAL_APPEND_GT: true
    SCORE_THRESH_TEST: 0.05
  ROI_KEYPOINT_HEAD:
    CONV_DIMS:
    - 512
    - 512
    - 512
    - 512
    - 512
    - 512
    - 512
    - 512
    LOSS_WEIGHT: 1.0
    MIN_KEYPOINTS_PER_IMAGE: 1
    NAME: KRCNNConvDeconvUpsampleHead
    NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: true
    NUM_KEYPOINTS: 17
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_TYPE: ROIAlignV2
  ROI_MASK_HEAD:
    CLS_AGNOSTIC_MASK: false
    CONV_DIM: 256
    NAME: MaskRCNNConvUpsampleHead
    NORM: ''
    NUM_CONV: 0
    POOLER_RESOLUTION: 14
    POOLER_SAMPLING_RATIO: 0
    POOLER_TYPE: ROIAlignV2
  RPN:
    BATCH_SIZE_PER_IMAGE: 256
    BBOX_REG_LOSS_TYPE: smooth_l1
    BBOX_REG_LOSS_WEIGHT: 1.0
    BBOX_REG_WEIGHTS: *id002
    BOUNDARY_THRESH: -1
    CONV_DIMS:
    - -1
    HEAD_NAME: StandardRPNHead
    IN_FEATURES:
    - res4
    IOU_LABELS:
    - 0
    - -1
    - 1
    IOU_THRESHOLDS:
    - 0.3
    - 0.7
    LOSS_WEIGHT: 1.0
    NMS_THRESH: 0.7
    POSITIVE_FRACTION: 0.5
    POST_NMS_TOPK_TEST: 1000
    POST_NMS_TOPK_TRAIN: 2000
    PRE_NMS_TOPK_TEST: 6000
    PRE_NMS_TOPK_TRAIN: 12000
    SMOOTH_L1_BETA: 0.0
  SEM_SEG_HEAD:
    COMMON_STRIDE: 4
    CONVS_DIM: 128
    IGNORE_VALUE: 255
    IN_FEATURES:
    - p2
    - p3
    - p4
    - p5
    LOSS_WEIGHT: 1.0
    NAME: SemSegFPNHead
    NORM: GN
    NUM_CLASSES: 54
  WEIGHTS: init_model_weights/ade_pretrained.pth
OUTPUT_DIR: /home/jinlinyi/exp/densefield/e08_persformer/e15_latiup_mixed_v3
OVERFIT_ON: false
SEED: -1
SOLVER:
  AMP:
    ENABLED: false
  BASE_LR: 0.001
  BIAS_LR_FACTOR: 1.0
  CHECKPOINT_PERIOD: 2000
  CLIP_GRADIENTS:
    CLIP_TYPE: value
    CLIP_VALUE: 1.0
    ENABLED: false
    NORM_TYPE: 2.0
  GAMMA: 0.1
  IMS_PER_BATCH: 64
  LR_SCHEDULER_NAME: WarmupMultiStepLR
  MAX_ITER: 90000
  MOMENTUM: 0.9
  NESTEROV: false
  REFERENCE_WORLD_SIZE: 0
  STEPS:
  - 40000
  - 60000
  WARMUP_FACTOR: 0.001
  WARMUP_ITERS: 1000
  WARMUP_METHOD: linear
  WEIGHT_DECAY: 0.0001
  WEIGHT_DECAY_BIAS: null
  WEIGHT_DECAY_NORM: 0.0
TEST:
  AUG:
    ENABLED: false
    FLIP: true
    MAX_SIZE: 4000
    MIN_SIZES:
    - 400
    - 500
    - 600
    - 700
    - 800
    - 900
    - 1000
    - 1100
    - 1200
  DETECTIONS_PER_IMAGE: 100
  EVAL_PERIOD: 2000
  EXPECTED_RESULTS: []
  KEYPOINT_OKS_SIGMAS: []
  PRECISE_BN:
    ENABLED: false
    NUM_ITER: 200
VERSION: 2
VIS_PERIOD: 200