2 files

output/native_batch2/w1_chiptrain/train/model_final.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f57a83e7d1ea722f700b3f6980756b65f7a9a1034aa3cd4a18c97c57f9dd3a
+size 2590332730

output/native_batch2/w2a_vistasval/train/config.yaml

@@ -0,0 +1,474 @@
+ANOMALY_DETECTOR: UNO
+CUDNN_BENCHMARK: false
+DATALOADER:
+  ASPECT_RATIO_GROUPING: true
+  FILTER_EMPTY_ANNOTATIONS: true
+  NUM_WORKERS: 4
+  REPEAT_SQRT: true
+  REPEAT_THRESHOLD: 0.0
+  SAMPLER_TRAIN: TrainingSampler
+DATASETS:
+  PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
+  PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
+  PROPOSAL_FILES_TEST: []
+  PROPOSAL_FILES_TRAIN: []
+  TEST: []
+  TRAIN:
+  - cityscapes_fine_sem_seg_train
+  - mapillary_vistas_sem_seg_train
+  - mapillary_vistas_sem_seg_val
+FLOAT32_PRECISION: ''
+GLOBAL:
+  HACK: 1.0
+INPUT:
+  COLOR_AUG_SSD: true
+  CROP:
+    ENABLED: true
+    SINGLE_CATEGORY_MAX_AREA: 1.0
+    SIZE:
+    - 512
+    - 1024
+    TYPE: absolute
+  DATASET_MAPPER_NAME: mask_former_object_paste
+  FORMAT: RGB
+  IMAGE_SIZE: 1024
+  MASK_FORMAT: polygon
+  MAX_SCALE: 2.0
+  MAX_SIZE_TEST: 2048
+  MAX_SIZE_TRAIN: 4096
+  MIN_SCALE: 0.1
+  MIN_SIZE_TEST: 1024
+  MIN_SIZE_TRAIN:
+  - 512
+  - 614
+  - 716
+  - 819
+  - 921
+  - 1024
+  - 1126
+  - 1228
+  - 1331
+  - 1433
+  - 1536
+  - 1638
+  - 1740
+  - 1843
+  - 1945
+  - 2048
+  MIN_SIZE_TRAIN_SAMPLING: choice
+  RANDOM_FLIP: horizontal
+  SIZE_DIVISIBILITY: -1
+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: 0
+    NAME: D2SwinTransformer
+  BLINDSPOT:
+    HOLE: 3
+    KERNEL: 7
+    TEACHER: vit_large_patch16_dinov3.lvd1689m
+    WEIGHT: 0.0
+  DEVICE: cuda
+  DINO_FUSION:
+    HIDDEN: 256
+    LAYERS:
+    - 5
+    - 11
+    - 17
+    - 23
+    LR_MULT: 1.0
+    MODEL: vit_large_patch16_dinov3.lvd1689m
+  DINO_TRUNK:
+    FREEZE: false
+    MODEL: convnext_large.dinov3_lvd1689m
+  FPN:
+    FUSE_TYPE: sum
+    IN_FEATURES: []
+    NORM: ''
+    OUT_CHANNELS: 256
+  KEYPOINT_ON: false
+  LOAD_PROPOSALS: false
+  MASK_FORMER:
+    CLASS_WEIGHT: 2.0
+    DEC_LAYERS: 10
+    DEEP_SUPERVISION: true
+    DICE_WEIGHT: 5.0
+    DIM_FEEDFORWARD: 2048
+    DROPOUT: 0.0
+    ENC_LAYERS: 0
+    ENFORCE_INPUT_PROJ: false
+    HIDDEN_DIM: 256
+    IMPORTANCE_SAMPLE_RATIO: 0.75
+    JSD_WEIGHT: 0.03
+    MASK_WEIGHT: 5.0
+    NHEADS: 8
+    NO_OBJECT_WEIGHT: 0.1
+    NUM_OBJECT_QUERIES: 100
+    NUM_SEED_QUERIES: 0
+    OVERSAMPLE_RATIO: 3.0
+    PRE_NORM: false
+    SEED_POOL: 9
+    SIZE_DIVISIBILITY: 32
+    TEST:
+      INSTANCE_ON: false
+      OBJECT_MASK_THRESHOLD: 0.8
+      OVERLAP_THRESHOLD: 0.8
+      PANOPTIC_ON: false
+      SEMANTIC_ON: true
+      SEM_SEG_POSTPROCESSING_BEFORE_INFERENCE: false
+    TRAIN_NUM_POINTS: 12544
+    TRANSFORMER_DECODER_NAME: MultiScaleMaskedTransformerDecoder
+    TRANSFORMER_IN_FEATURE: multi_scale_pixel_decoder
+    VOID_DROPLOSS: false
+  MASK_ON: false
+  META_ARCHITECTURE: MaskFormer
+  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:
+  - 123.675
+  - 116.28
+  - 103.53
+  PIXEL_STD:
+  - 58.395
+  - 57.12
+  - 57.375
+  PROPOSAL_GENERATOR:
+    MIN_SIZE: 0
+    NAME: RPN
+  RESNETS:
+    DEFORM_MODULATED: false
+    DEFORM_NUM_GROUPS: 1
+    DEFORM_ON_PER_STAGE:
+    - false
+    - false
+    - false
+    - false
+    DEPTH: 50
+    NORM: SyncBN
+    NUM_GROUPS: 1
+    OUT_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    RES2_OUT_CHANNELS: 256
+    RES4_DILATION: 1
+    RES5_DILATION: 1
+    RES5_MULTI_GRID:
+    - 1
+    - 1
+    - 1
+    STEM_OUT_CHANNELS: 64
+    STEM_TYPE: basic
+    STRIDE_IN_1X1: false
+    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
+    FED_LOSS_FREQ_WEIGHT_POWER: 0.5
+    FED_LOSS_NUM_CLASSES: 50
+    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
+    USE_FED_LOSS: false
+    USE_SIGMOID_CE: 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
+  SAFE_DISTILL:
+    WEIGHT: 0.0
+  SAFE_FUSION:
+    HIDDEN: 64
+    LR_MULT: 1.0
+  SEM_SEG_HEAD:
+    ASPP_CHANNELS: 256
+    ASPP_DILATIONS:
+    - 6
+    - 12
+    - 18
+    ASPP_DROPOUT: 0.1
+    COMMON_STRIDE: 4
+    CONVS_DIM: 256
+    DEFORMABLE_TRANSFORMER_ENCODER_IN_FEATURES:
+    - res3
+    - res4
+    - res5
+    DEFORMABLE_TRANSFORMER_ENCODER_N_HEADS: 8
+    DEFORMABLE_TRANSFORMER_ENCODER_N_POINTS: 4
+    IGNORE_VALUE: 255
+    IN_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    LOSS_TYPE: hard_pixel_mining
+    LOSS_WEIGHT: 1.0
+    MASK_DIM: 256
+    NAME: MaskFormerHead
+    NORM: GN
+    NUM_CLASSES: 20
+    PIXEL_DECODER_NAME: MSDeformAttnPixelDecoder
+    PROJECT_CHANNELS:
+    - 48
+    PROJECT_FEATURES:
+    - res2
+    TRANSFORMER_ENC_LAYERS: 6
+    USE_DEPTHWISE_SEPARABLE_CONV: false
+  SWIN:
+    APE: false
+    ATTN_DROP_RATE: 0.0
+    DEPTHS:
+    - 2
+    - 2
+    - 18
+    - 2
+    DROP_PATH_RATE: 0.3
+    DROP_RATE: 0.0
+    EMBED_DIM: 192
+    MLP_RATIO: 4.0
+    NUM_HEADS:
+    - 6
+    - 12
+    - 24
+    - 48
+    OUT_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    PATCH_NORM: true
+    PATCH_SIZE: 4
+    PRETRAIN_IMG_SIZE: 384
+    QKV_BIAS: true
+    QK_SCALE: null
+    USE_CHECKPOINT: false
+    WINDOW_SIZE: 12
+  WEIGHTS: model_weights/m2f_panoptic/vistas_swinL_panoptic_q100.pth
+OUTPUT_DIR: output/native_batch2/w2a_vistasval/train
+PASTE:
+  ANY_SIZE_MAX: 280
+  ANY_SIZE_MIN: 24
+  CAM_HEIGHT_M: 1.3
+  CHIP_MAX_OBJ: 64
+  CHIP_PROB: 0.0
+  CHIP_ZOOM: 3.0
+  GROUP_MAX: 5
+  GROUP_PROB: 0.25
+  HEIGHT_MAX_M: 1.0
+  HEIGHT_MIN_M: 0.1
+  MIN_PIXEL_HEIGHT: 6
+  NUM_MAX: 10
+  NUM_MIN: 4
+  ROAD_FRAC: 0.6
+  SAM3_CLASS: 0
+  SAM3_OBJECTS: ./output/native_batch2/sam3_objects
+  SAM3_REL_PROB: 0.25
+  SAM3_SPLIT_CLASSES:
+  - 5
+  - 6
+  - 7
+  SAM3_TOP_K: 20
+  SEMANTIC_TARGETS: true
+  SYNTH_FRAC: 0.0
+  THING_INSTANCES: true
+SEED: 1
+SOLVER:
+  AMP:
+    ENABLED: true
+  BACKBONE_MULTIPLIER: 0.1
+  BASE_LR: 1.0e-05
+  BASE_LR_END: 0.0
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 3000
+  CLIP_GRADIENTS:
+    CLIP_TYPE: full_model
+    CLIP_VALUE: 0.01
+    ENABLED: true
+    NORM_TYPE: 2.0
+  GAMMA: 0.1
+  IMS_PER_BATCH: 4
+  LR_SCHEDULER_NAME: WarmupPolyLR
+  MAX_ITER: 6000
+  MOMENTUM: 0.9
+  NESTEROV: false
+  NUM_DECAYS: 3
+  OPTIMIZER: ADAMW
+  POLY_LR_CONSTANT_ENDING: 0.0
+  POLY_LR_POWER: 0.9
+  REFERENCE_WORLD_SIZE: 0
+  RESCALE_INTERVAL: false
+  STEPS:
+  - 30000
+  WARMUP_FACTOR: 1.0
+  WARMUP_ITERS: 0
+  WARMUP_METHOD: linear
+  WEIGHT_DECAY: 0.05
+  WEIGHT_DECAY_BIAS: null
+  WEIGHT_DECAY_EMBED: 0.0
+  WEIGHT_DECAY_NORM: 0.0
+TEST:
+  AUG:
+    ENABLED: false
+    FLIP: true
+    MAX_SIZE: 4096
+    MIN_SIZES:
+    - 512
+    - 768
+    - 1024
+    - 1280
+    - 1536
+    - 1792
+  DETECTIONS_PER_IMAGE: 100
+  EVAL_PERIOD: 0
+  EXPECTED_RESULTS: []
+  KEYPOINT_OKS_SIGMAS: []
+  PRECISE_BN:
+    ENABLED: false
+    NUM_ITER: 200
+VERSION: 2
+VIS_PERIOD: 0