adding model

parser_2024-03-12

@@ -1 +0,0 @@
-Subproject commit 4450ff48a28ca65362470e3b672f6d8e942c6d4e

parser_2024-03-12/config.yaml

@@ -0,0 +1,327 @@
+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:
+  - finetune-val
+  TRAIN:
+  - finetune-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
+  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_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: false
+  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:
+  - 1.0
+  - 1.0
+  - 1.0
+  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: FrozenBN
+    NUM_GROUPS: 1
+    OUT_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    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:
+    - p2
+    - p3
+    - p4
+    - p5
+    IOU_LABELS:
+    - 0
+    - 1
+    IOU_THRESHOLDS:
+    - 0.5
+    NAME: StandardROIHeads
+    NMS_THRESH_TEST: 0.5
+    NUM_CLASSES: 11
+    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_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:
+    - 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: /home/ubuntu/layout-parser/models/DocLayNet-large_fast_rcnn_R_50_FPN_3x/model_final.pth
+OUTPUT_DIR: ./outputs/finetune/fast_rcnn_R_50_FPN_3x/
+SEED: -1
+SOLVER:
+  AMP:
+    ENABLED: false
+  BASE_LR: 0.00025
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 20000
+  CLIP_GRADIENTS:
+    CLIP_TYPE: value
+    CLIP_VALUE: 1.0
+    ENABLED: false
+    NORM_TYPE: 2.0
+  GAMMA: 0.1
+  IMS_PER_BATCH: 2
+  LR_SCHEDULER_NAME: WarmupMultiStepLR
+  MAX_ITER: 60000
+  MOMENTUM: 0.9
+  NESTEROV: false
+  REFERENCE_WORLD_SIZE: 0
+  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

parser_2024-03-12/eval.csv

@@ -0,0 +1,18 @@
+,bbox
+AP,48.744662430853865
+AP50,74.36064012361008
+AP75,53.027459747550274
+APs,0.0
+APm,13.334398325824157
+APl,53.40041646256427
+AP-Caption,45.51980198019802
+AP-Footnote,47.66849132392231
+AP-Formula,
+AP-Page-footer,25.746028461057037
+AP-Page-header,67.44123203400125
+AP-Picture,48.699900371420455
+AP-Section-header,45.18482922396696
+AP-Table,73.22847798677735
+AP-Table-of-contents,52.62376237623763
+AP-Text,55.35390253115556
+AP-Title,25.980198019801975

parser_2024-03-12/events.out.tfevents.1710183741.ip-192-170-5-19.2783.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e90d51c0292ccc6d37f8737680ecd22bdb2ba1b3fcdaa0e8f35f6ed0d6ea19a3
+size 2612801

parser_2024-03-12/inference/instances_predictions.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e27b998ce19b78a65f82964714d359f7d6df1f7f298e217c555d3226a9479c77
+size 90720

parser_2024-03-12/last_checkpoint

@@ -0,0 +1 @@
+model_final.pth

parser_2024-03-12/model_0019999.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e66a4eb57effe4ed278b7df33d494d1e9abff92c7161fadbd5b6594a3b6ee60
+size 165917860

parser_2024-03-12/model_0039999.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce2f188e14b18bed144e07742f89313e34679cca31c84b747810e1c0fc396b3e
+size 165917860

parser_2024-03-12/model_0059999.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08fa35a54c5d6aa9e8f49c27843c4e3f2194631449090955625565b13a578717
+size 165917860

parser_2024-03-12/model_final.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08fa35a54c5d6aa9e8f49c27843c4e3f2194631449090955625565b13a578717
+size 165917860