truefoundry
/

layout-parser

Model card Files Files and versions Community

s1lv3rj1nx commited on Apr 29

Commit

2982c17

•

1 Parent(s): c6a80c2

Upload mask_rcnn_X_101_32x8d_FPN_3x.yml with huggingface_hub

Browse files

Files changed (1) hide show

mask_rcnn_X_101_32x8d_FPN_3x.yml +309 -0

mask_rcnn_X_101_32x8d_FPN_3x.yml ADDED Viewed

	@@ -0,0 +1,309 @@

+CUDNN_BENCHMARK: false
+DATALOADER:
+    ASPECT_RATIO_GROUPING: true
+    FILTER_EMPTY_ANNOTATIONS: true
+    NUM_WORKERS: 4
+    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:
+        - publaynet-val
+    TRAIN:
+        - publaynet-train
+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:
+        - 640
+        - 672
+        - 704
+        - 736
+        - 768
+        - 800
+    MIN_SIZE_TRAIN_SAMPLING: choice
+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_resnet_fpn_backbone
+    DEVICE: cuda
+    FPN:
+        FUSE_TYPE: sum
+        IN_FEATURES:
+            - res2
+            - res3
+            - res4
+            - res5
+        NORM: ""
+        OUT_CHANNELS: 256
+    KEYPOINT_ON: false
+    LOAD_PROPOSALS: false
+    MASK_ON: true
+    META_ARCHITECTURE: GeneralizedRCNN
+    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:
+        - 57.375
+        - 57.12
+        - 58.395
+    PROPOSAL_GENERATOR:
+        MIN_SIZE: 0
+        NAME: RPN
+    RESNETS:
+        DEFORM_MODULATED: false
+        DEFORM_NUM_GROUPS: 1
+        DEFORM_ON_PER_STAGE:
+            - false
+            - false
+            - false
+            - false
+        DEPTH: 101
+        NORM: FrozenBN
+        NUM_GROUPS: 32
+        OUT_FEATURES:
+            - res2
+            - res3
+            - res4
+            - res5
+        RES2_OUT_CHANNELS: 256
+        RES5_DILATION: 1
+        STEM_OUT_CHANNELS: 64
+        STRIDE_IN_1X1: false
+        WIDTH_PER_GROUP: 8
+    RETINANET:
+        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
+        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_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:
+            - p2
+            - p3
+            - p4
+            - p5
+        IOU_LABELS:
+            - 0
+            - 1
+        IOU_THRESHOLDS:
+            - 0.5
+        NAME: StandardROIHeads
+        NMS_THRESH_TEST: 0.5
+        NUM_CLASSES: 5
+        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: 4
+        POOLER_RESOLUTION: 14
+        POOLER_SAMPLING_RATIO: 0
+        POOLER_TYPE: ROIAlignV2
+    RPN:
+        BATCH_SIZE_PER_IMAGE: 256
+        BBOX_REG_WEIGHTS:
+            - 1.0
+            - 1.0
+            - 1.0
+            - 1.0
+        BOUNDARY_THRESH: -1
+        HEAD_NAME: StandardRPNHead
+        IN_FEATURES:
+            - p2
+            - p3
+            - p4
+            - p5
+            - p6
+        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: 1000
+        PRE_NMS_TOPK_TEST: 1000
+        PRE_NMS_TOPK_TRAIN: 2000
+        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: https://www.dropbox.com/s/57zjbwv6gh3srry/model_final.pth?dl=1
+OUTPUT_DIR: ../outputs/publaynet/mask_rcnn_X_101_32x8d_FPN_3x/
+SEED: -1
+SOLVER:
+    BASE_LR: 0.0005
+    BIAS_LR_FACTOR: 1.0
+    CHECKPOINT_PERIOD: 60000
+    GAMMA: 0.1
+    IMS_PER_BATCH: 2
+    LR_SCHEDULER_NAME: WarmupMultiStepLR
+    MAX_ITER: 180000
+    MOMENTUM: 0.9
+    STEPS:
+        - 210000
+        - 250000
+    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
+    EVAL_PERIOD: 0
+    EXPECTED_RESULTS: []
+    KEYPOINT_OKS_SIGMAS: []
+    PRECISE_BN:
+        ENABLED: false
+        NUM_ITER: 200
+VERSION: 2
+VIS_PERIOD: 0