Why your test scale is larger than 600?

[facebookresearch]

Why your test scale is larger than 600?

[yujheli]

Yes, we do not revise the default test scale. I think the performance can be improved if the test scale is fixed.

[Yorionice1]

Thanks for your reply. But I still can't get the accuracy reported in your paper (50.9), my result is around 45.2 on 4 GPUs with IMG_PER_BATCH_LABEL: 8, IMG_PER_BATCH_UNLABEL: 8, BASE_LR: 0.04. Rest of the settings are same as original config file uploaded by you.

[Yorionice1]

MODEL:

META_ARCHITECTURE: "DAobjTwoStagePseudoLabGeneralizedRCNN"
BACKBONE:
NAME: "build_vgg_backbone"
MASK_ON: False
RESNETS:
DEPTH: 101
PROPOSAL_GENERATOR:
NAME: "PseudoLabRPN"

RPN:
IN_FEATURES: ["vgg4"]
ROI_HEADS:
NAME: "StandardROIHeadsPseudoLab"
LOSS: "CrossEntropy" # variant: "CrossEntropy"
NUM_CLASSES: 8
IN_FEATURES: ["vgg4"]
ROI_BOX_HEAD:
NAME: "FastRCNNConvFCHead"
NUM_FC: 2
POOLER_RESOLUTION: 7
SOLVER:
LR_SCHEDULER_NAME: "WarmupTwoStageMultiStepLR"
STEPS: (60000, 80000, 90000, 360000)
FACTOR_LIST: (1, 1, 1, 1, 1)
MAX_ITER: 100000
IMG_PER_BATCH_LABEL: 8
IMG_PER_BATCH_UNLABEL: 8
BASE_LR: 0.04
DATALOADER:
SUP_PERCENT: 100.0
DATASETS:
CROSS_DATASET: True
TRAIN_LABEL: ("cityscapes_train",)
TRAIN_UNLABEL: ("cityscapes_foggy_train",)
TEST: ("cityscapes_foggy_val",)
SEMISUPNET:
Trainer: "ateacher"
BBOX_THRESHOLD: 0.8
TEACHER_UPDATE_ITER: 1
BURN_UP_STEP: 20000
EMA_KEEP_RATE: 0.9996
UNSUP_LOSS_WEIGHT: 1.0
SUP_LOSS_WEIGHT: 0.5
DIS_TYPE: "vgg4" #["concate","p2","multi"]
TEST:
EVAL_PERIOD: 1000

[09/30 02:19:46] detectron2 INFO: Running with full config:
CUDNN_BENCHMARK: false
DATALOADER:
ASPECT_RATIO_GROUPING: true
FILTER_EMPTY_ANNOTATIONS: true
NUM_WORKERS: 4
RANDOM_DATA_SEED: 0
RANDOM_DATA_SEED_PATH: dataseed/COCO_supervision.txt
REPEAT_THRESHOLD: 0.0
SAMPLER_TRAIN: TrainingSampler
SUP_PERCENT: 100.0
DATASETS:
CROSS_DATASET: true
PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
PROPOSAL_FILES_TEST: []
PROPOSAL_FILES_TRAIN: []
TEST:

• cityscapes_foggy_val
  TRAIN:
• coco_2017_train
  TRAIN_LABEL:
• cityscapes_train
  TRAIN_UNLABEL:
• cityscapes_foggy_train
  EMAMODEL:
  SUP_CONSIST: true
  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:
• 600
  MIN_SIZE_TRAIN_SAMPLING: choice
  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_vgg_backbone
      DEVICE: cuda
      FPN:
      FUSE_TYPE: sum
      IN_FEATURES: []
      NORM: ''
      OUT_CHANNELS: 256
      KEYPOINT_ON: false
      LOAD_PROPOSALS: false
      MASK_ON: false
      META_ARCHITECTURE: DAobjTwoStagePseudoLabGeneralizedRCNN
      PANOPTIC_FPN:
      COMBINE:
      ENABLED: true
      INSTANCES_CONFIDENCE_THRESH: 0.5
      OVERLAP_THRESH: 0.5
      STUFF_AREA_LIMIT: 4096
      INSTANCE_LOSS_WEIGHT: 1.0
      PIXEL_MEAN:
• 103.53
• 116.28
• 123.675
  PIXEL_STD:
• 1.0
• 1.0
• 1.0
  PROPOSAL_GENERATOR:
  MIN_SIZE: 0
  NAME: PseudoLabRPN
  RESNETS:
  DEFORM_MODULATED: false
  DEFORM_NUM_GROUPS: 1
  DEFORM_ON_PER_STAGE:
  • false
  • false
  • false
  • false
    DEPTH: 101
    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:
  • 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:
  • • 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:
  • 10.0
  • 10.0
  • 5.0
  • 5.0
    CLS_AGNOSTIC_BBOX_REG: false
    CONV_DIM: 256
    FC_DIM: 1024
    NAME: FastRCNNConvFCHead
    NORM: ''
    NUM_CONV: 0
    NUM_FC: 2
    POOLER_RESOLUTION: 7
    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:
  • vgg4
    IOU_LABELS:
  • 0
  • 1
    IOU_THRESHOLDS:
  • 0.5
    LOSS: CrossEntropy
    NAME: StandardROIHeadsPseudoLab
    NMS_THRESH_TEST: 0.5
    NUM_CLASSES: 8
    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:
  • 1.0
  • 1.0
  • 1.0
  • 1.0
    BOUNDARY_THRESH: -1
    CONV_DIMS:
  • -1
    HEAD_NAME: StandardRPNHead
    IN_FEATURES:
  • vgg4
    IOU_LABELS:
  • 0
  • -1
  • 1
    IOU_THRESHOLDS:
  • 0.3
  • 0.7
    LOSS: CrossEntropy
    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
    UNSUP_LOSS_WEIGHT: 1.0
    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: ''
    OUTPUT_DIR: output/exp_city
    SEED: -1
    SEMISUPNET:
    BBOX_THRESHOLD: 0.8
    BURN_UP_STEP: 20000
    DIS_LOSS_WEIGHT: 0.1
    DIS_TYPE: vgg4
    EMA_KEEP_RATE: 0.9996
    LOSS_WEIGHT_TYPE: standard
    MLP_DIM: 128
    PSEUDO_BBOX_SAMPLE: thresholding
    SUP_LOSS_WEIGHT: 0.5
    TEACHER_UPDATE_ITER: 1
    Trainer: ateacher
    UNSUP_LOSS_WEIGHT: 1.0
    SOLVER:
    AMP:
    ENABLED: false
    BASE_LR: 0.04
    BIAS_LR_FACTOR: 1.0
    CHECKPOINT_PERIOD: 5000
    CLIP_GRADIENTS:
    CLIP_TYPE: value
    CLIP_VALUE: 1.0
    ENABLED: false
    NORM_TYPE: 2.0
    FACTOR_LIST:
• 1
• 1
• 1
• 1
• 1
  GAMMA: 0.1
  IMG_PER_BATCH_LABEL: 8
  IMG_PER_BATCH_UNLABEL: 8
  IMS_PER_BATCH: 16
  LR_SCHEDULER_NAME: WarmupTwoStageMultiStepLR
  MAX_ITER: 100000
  MOMENTUM: 0.9
  NESTEROV: false
  REFERENCE_WORLD_SIZE: 0
  STEPS:
• 60000
• 80000
• 90000
• 360000
  WARMUP_FACTOR: 0.001
  WARMUP_ITERS: 1000
  WARMUP_METHOD: linear
  WEIGHT_DECAY: 0.0001
  WEIGHT_DECAY_BIAS: 0.0001
  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
    EVALUATOR: COCOeval
    EVAL_PERIOD: 1000
    EXPECTED_RESULTS: []
    KEYPOINT_OKS_SIGMAS: []
    PRECISE_BN:
    ENABLED: false
    NUM_ITER: 200
    VAL_LOSS: true
    VERSION: 2
    VIS_PERIOD: 0