Upload 9 files

config.json

@@ -0,0 +1,325 @@
+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:
+  - modele-val
+  TRAIN:
+  - modele-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: 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:
+  - 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: 2
+    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
+    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: /content/drive/MyDrive/layoutparser/modele/modele3_NP?/model_final.pth
+OUTPUT_DIR: /content/drive/MyDrive/layoutparser/modele
+SEED: -1
+SOLVER:
+  AMP:
+    ENABLED: false
+  BASE_LR: 0.00025
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 50
+  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: 300
+  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

config.yaml

@@ -0,0 +1,325 @@
+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:
+  - modele-val
+  TRAIN:
+  - modele-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: 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:
+  - 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: 2
+    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
+    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: /content/drive/MyDrive/layoutparser/modele/modele3_NP?/model_final.pth
+OUTPUT_DIR: /content/drive/MyDrive/layoutparser/modele
+SEED: -1
+SOLVER:
+  AMP:
+    ENABLED: false
+  BASE_LR: 0.00025
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 50
+  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: 300
+  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

events.out.tfevents.1681910385.906c2a3c48ac.2206.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad8ab0e1340cacf4edf029d2e904bb03844ee8ed9408a6e7e1c85ba8f7695a9
+size 88

events.out.tfevents.1681910424.906c2a3c48ac.2416.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622f1f3a134b80b2168c0d4fcb263babc44e4e1b240f593fbca1185a07cb1e95
+size 88

events.out.tfevents.1681910486.906c2a3c48ac.2698.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7c58b7aad0abc3cc2aa8b7b92fbc2f2bc2af1c8b8a29c4a06378c3585025dc
+size 16318

last_checkpoint

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

log.txt

@@ -0,0 +1,2758 @@
+[04/19 13:19:35] detectron2 INFO: Rank of current process: 0. World size: 1
+[04/19 13:19:36] detectron2 INFO: Environment info:
+----------------------  ----------------------------------------------------------------
+sys.platform            linux
+Python                  3.9.16 (main, Dec  7 2022, 01:11:51) [GCC 9.4.0]
+numpy                   1.22.4
+detectron2              0.4 @/usr/local/lib/python3.9/dist-packages/detectron2
+Compiler                GCC 9.4
+CUDA compiler           CUDA 11.8
+detectron2 arch flags   7.5
+DETECTRON2_ENV_MODULE   <not set>
+PyTorch                 2.0.0+cu118 @/usr/local/lib/python3.9/dist-packages/torch
+PyTorch debug build     False
+GPU available           True
+GPU 0                   Tesla T4 (arch=7.5)
+CUDA_HOME               /usr/local/cuda
+Pillow                  9.5.0
+torchvision             0.15.1+cu118 @/usr/local/lib/python3.9/dist-packages/torchvision
+torchvision arch flags  3.5, 5.0, 6.0, 7.0, 7.5, 8.0, 8.6
+fvcore                  0.1.3.post20210317
+cv2                     4.7.0
+----------------------  ----------------------------------------------------------------
+PyTorch built with:
+  - GCC 9.3
+  - C++ Version: 201703
+  - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
+  - Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)
+  - OpenMP 201511 (a.k.a. OpenMP 4.5)
+  - LAPACK is enabled (usually provided by MKL)
+  - NNPACK is enabled
+  - CPU capability usage: AVX2
+  - CUDA Runtime 11.8
+  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90
+  - CuDNN 8.7
+  - Magma 2.6.1
+  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=8.7.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.0.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 
+
+[04/19 13:19:36] detectron2 INFO: Command line arguments: Namespace(config_file='/content/layout-model-training/config_LayoutParser_PrimaDataset.yaml', resume=False, eval_only=False, num_gpus=1, num_machines=1, machine_rank=0, dist_url='tcp://127.0.0.1:49152', opts=['OUTPUT_DIR', '/content/drive/MyDrive/layoutparser/modele', 'SOLVER.IMS_PER_BATCH', '2'], dataset_name='modele', json_annotation_train='/content/drive/MyDrive/layoutparser/dataset6/train/via_project_19Apr2023_15h0m_coco.json', image_path_train='/content/drive/MyDrive/layoutparser/dataset6/train', json_annotation_val='/content/drive/MyDrive/layoutparser/dataset6/val/via_project_19Apr2023_15h9m_coco.json', image_path_val='/content/drive/MyDrive/layoutparser/dataset6/val')
+[04/19 13:19:36] detectron2 INFO: Contents of args.config_file=/content/layout-model-training/config_LayoutParser_PrimaDataset.yaml:
+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:
+  - prima-layout-val
+  TRAIN:
+  - prima-layout-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:
+  - 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_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: 7
+    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:  /content/drive/MyDrive/layoutparser/modele/modele3_NP?/
+OUTPUT_DIR: ../outputs/prima/mask_rcnn_R_50_FPN_3x/
+SEED: -1
+SOLVER:
+  BASE_LR: 0.00025
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 50
+  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: 300
+  MOMENTUM: 0.9
+  NESTEROV: false
+  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
+
+[04/19 13:19:36] detectron2 INFO: Running with full config:
+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: ('modele-val',)
+  TRAIN: ('modele-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: 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: [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: 2
+    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
+    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: /content/drive/MyDrive/layoutparser/modele/modele3_NP?/
+OUTPUT_DIR: /content/drive/MyDrive/layoutparser/modele
+SEED: -1
+SOLVER:
+  AMP:
+    ENABLED: False
+  BASE_LR: 0.00025
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 50
+  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: 300
+  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
+[04/19 13:19:36] detectron2 INFO: Full config saved to /content/drive/MyDrive/layoutparser/modele/config.yaml
+[04/19 13:19:36] d2.utils.env INFO: Using a generated random seed 36661240
+[04/19 13:19:43] d2.engine.defaults INFO: Model:
+GeneralizedRCNN(
+  (backbone): FPN(
+    (fpn_lateral2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+    (fpn_output2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (fpn_lateral3): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
+    (fpn_output3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (fpn_lateral4): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
+    (fpn_output4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (fpn_lateral5): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))
+    (fpn_output5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (top_block): LastLevelMaxPool()
+    (bottom_up): ResNet(
+      (stem): BasicStem(
+        (conv1): Conv2d(
+          3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False
+          (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+        )
+      )
+      (res2): Sequential(
+        (0): BottleneckBlock(
+          (shortcut): Conv2d(
+            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv1): Conv2d(
+            64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+        )
+        (1): BottleneckBlock(
+          (conv1): Conv2d(
+            256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+        )
+        (2): BottleneckBlock(
+          (conv1): Conv2d(
+            256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+        )
+      )
+      (res3): Sequential(
+        (0): BottleneckBlock(
+          (shortcut): Conv2d(
+            256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv1): Conv2d(
+            256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+        )
+        (1): BottleneckBlock(
+          (conv1): Conv2d(
+            512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+        )
+        (2): BottleneckBlock(
+          (conv1): Conv2d(
+            512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+        )
+        (3): BottleneckBlock(
+          (conv1): Conv2d(
+            512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+        )
+      )
+      (res4): Sequential(
+        (0): BottleneckBlock(
+          (shortcut): Conv2d(
+            512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+          (conv1): Conv2d(
+            512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (1): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (2): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (3): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (4): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (5): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+      )
+      (res5): Sequential(
+        (0): BottleneckBlock(
+          (shortcut): Conv2d(
+            1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
+          )
+          (conv1): Conv2d(
+            1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
+          )
+        )
+        (1): BottleneckBlock(
+          (conv1): Conv2d(
+            2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
+          )
+        )
+        (2): BottleneckBlock(
+          (conv1): Conv2d(
+            2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
+          )
+        )
+      )
+    )
+  )
+  (proposal_generator): RPN(
+    (rpn_head): StandardRPNHead(
+      (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      (objectness_logits): Conv2d(256, 3, kernel_size=(1, 1), stride=(1, 1))
+      (anchor_deltas): Conv2d(256, 12, kernel_size=(1, 1), stride=(1, 1))
+    )
+    (anchor_generator): DefaultAnchorGenerator(
+      (cell_anchors): BufferList()
+    )
+  )
+  (roi_heads): StandardROIHeads(
+    (box_pooler): ROIPooler(
+      (level_poolers): ModuleList(
+        (0): ROIAlign(output_size=(7, 7), spatial_scale=0.25, sampling_ratio=0, aligned=True)
+        (1): ROIAlign(output_size=(7, 7), spatial_scale=0.125, sampling_ratio=0, aligned=True)
+        (2): ROIAlign(output_size=(7, 7), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
+        (3): ROIAlign(output_size=(7, 7), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
+      )
+    )
+    (box_head): FastRCNNConvFCHead(
+      (flatten): Flatten(start_dim=1, end_dim=-1)
+      (fc1): Linear(in_features=12544, out_features=1024, bias=True)
+      (fc_relu1): ReLU()
+      (fc2): Linear(in_features=1024, out_features=1024, bias=True)
+      (fc_relu2): ReLU()
+    )
+    (box_predictor): FastRCNNOutputLayers(
+      (cls_score): Linear(in_features=1024, out_features=3, bias=True)
+      (bbox_pred): Linear(in_features=1024, out_features=8, bias=True)
+    )
+    (mask_pooler): ROIPooler(
+      (level_poolers): ModuleList(
+        (0): ROIAlign(output_size=(14, 14), spatial_scale=0.25, sampling_ratio=0, aligned=True)
+        (1): ROIAlign(output_size=(14, 14), spatial_scale=0.125, sampling_ratio=0, aligned=True)
+        (2): ROIAlign(output_size=(14, 14), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
+        (3): ROIAlign(output_size=(14, 14), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
+      )
+    )
+    (mask_head): MaskRCNNConvUpsampleHead(
+      (mask_fcn1): Conv2d(
+        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
+        (activation): ReLU()
+      )
+      (mask_fcn2): Conv2d(
+        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
+        (activation): ReLU()
+      )
+      (mask_fcn3): Conv2d(
+        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
+        (activation): ReLU()
+      )
+      (mask_fcn4): Conv2d(
+        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
+        (activation): ReLU()
+      )
+      (deconv): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2))
+      (deconv_relu): ReLU()
+      (predictor): Conv2d(256, 2, kernel_size=(1, 1), stride=(1, 1))
+    )
+  )
+)
+[04/19 13:19:43] d2.data.dataset_mapper INFO: [DatasetMapper] Augmentations used in training: [ResizeShortestEdge(short_edge_length=(640, 672, 704, 736, 768, 800), max_size=1333, sample_style='choice'), RandomFlip(), RandomRotation(angle=[-90.0, 0.0])]
+[04/19 13:19:43] d2.data.datasets.coco INFO: Loaded 36 images in COCO format from /content/drive/MyDrive/layoutparser/dataset6/train/via_project_19Apr2023_15h0m_coco.json
+[04/19 13:19:43] d2.data.build INFO: Removed 6 images with no usable annotations. 30 images left.
+[04/19 13:19:43] d2.data.build INFO: Distribution of instances among all 2 categories:
+|  category  | #instances   |  category  | #instances   |
+|:----------:|:-------------|:----------:|:-------------|
+|            | 89           |            | 0            |
+|            |              |            |              |
+|   total    | 89           |            |              |
+[04/19 13:19:43] d2.data.build INFO: Using training sampler TrainingSampler
+[04/19 13:19:43] d2.data.common INFO: Serializing 30 elements to byte tensors and concatenating them all ...
+[04/19 13:19:43] d2.data.common INFO: Serialized dataset takes 0.01 MiB
+[04/19 13:19:43] d2.solver.build WARNING: SOLVER.STEPS contains values larger than SOLVER.MAX_ITER. These values will be ignored.
+[04/19 13:19:45] fvcore.common.checkpoint INFO: Loading checkpoint from /content/drive/MyDrive/layoutparser/modele/modele3_NP?/
+[04/19 13:20:18] detectron2 INFO: Rank of current process: 0. World size: 1
+[04/19 13:20:20] detectron2 INFO: Environment info:
+----------------------  ----------------------------------------------------------------
+sys.platform            linux
+Python                  3.9.16 (main, Dec  7 2022, 01:11:51) [GCC 9.4.0]
+numpy                   1.22.4
+detectron2              0.4 @/usr/local/lib/python3.9/dist-packages/detectron2
+Compiler                GCC 9.4
+CUDA compiler           CUDA 11.8
+detectron2 arch flags   7.5
+DETECTRON2_ENV_MODULE   <not set>
+PyTorch                 2.0.0+cu118 @/usr/local/lib/python3.9/dist-packages/torch
+PyTorch debug build     False
+GPU available           True
+GPU 0                   Tesla T4 (arch=7.5)
+CUDA_HOME               /usr/local/cuda
+Pillow                  9.5.0
+torchvision             0.15.1+cu118 @/usr/local/lib/python3.9/dist-packages/torchvision
+torchvision arch flags  3.5, 5.0, 6.0, 7.0, 7.5, 8.0, 8.6
+fvcore                  0.1.3.post20210317
+cv2                     4.7.0
+----------------------  ----------------------------------------------------------------
+PyTorch built with:
+  - GCC 9.3
+  - C++ Version: 201703
+  - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
+  - Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)
+  - OpenMP 201511 (a.k.a. OpenMP 4.5)
+  - LAPACK is enabled (usually provided by MKL)
+  - NNPACK is enabled
+  - CPU capability usage: AVX2
+  - CUDA Runtime 11.8
+  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90
+  - CuDNN 8.7
+  - Magma 2.6.1
+  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=8.7.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.0.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 
+
+[04/19 13:20:20] detectron2 INFO: Command line arguments: Namespace(config_file='/content/layout-model-training/config_LayoutParser_PrimaDataset.yaml', resume=False, eval_only=False, num_gpus=1, num_machines=1, machine_rank=0, dist_url='tcp://127.0.0.1:49152', opts=['OUTPUT_DIR', '/content/drive/MyDrive/layoutparser/modele', 'SOLVER.IMS_PER_BATCH', '2'], dataset_name='modele', json_annotation_train='/content/drive/MyDrive/layoutparser/dataset6/train/via_project_19Apr2023_15h0m_coco.json', image_path_train='/content/drive/MyDrive/layoutparser/dataset6/train', json_annotation_val='/content/drive/MyDrive/layoutparser/dataset6/val/via_project_19Apr2023_15h9m_coco.json', image_path_val='/content/drive/MyDrive/layoutparser/dataset6/val')
+[04/19 13:20:20] detectron2 INFO: Contents of args.config_file=/content/layout-model-training/config_LayoutParser_PrimaDataset.yaml:
+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:
+  - prima-layout-val
+  TRAIN:
+  - prima-layout-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:
+  - 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_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: 7
+    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:  /content/drive/MyDrive/layoutparser/modele/modele3_NP?/modele_final.pth
+OUTPUT_DIR: ../outputs/prima/mask_rcnn_R_50_FPN_3x/
+SEED: -1
+SOLVER:
+  BASE_LR: 0.00025
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 50
+  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: 300
+  MOMENTUM: 0.9
+  NESTEROV: false
+  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
+
+[04/19 13:20:20] detectron2 INFO: Running with full config:
+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: ('modele-val',)
+  TRAIN: ('modele-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: 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: [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: 2
+    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
+    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: /content/drive/MyDrive/layoutparser/modele/modele3_NP?/modele_final.pth
+OUTPUT_DIR: /content/drive/MyDrive/layoutparser/modele
+SEED: -1
+SOLVER:
+  AMP:
+    ENABLED: False
+  BASE_LR: 0.00025
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 50
+  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: 300
+  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
+[04/19 13:20:20] detectron2 INFO: Full config saved to /content/drive/MyDrive/layoutparser/modele/config.yaml
+[04/19 13:20:20] d2.utils.env INFO: Using a generated random seed 20261058
+[04/19 13:20:22] d2.engine.defaults INFO: Model:
+GeneralizedRCNN(
+  (backbone): FPN(
+    (fpn_lateral2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+    (fpn_output2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (fpn_lateral3): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
+    (fpn_output3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (fpn_lateral4): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
+    (fpn_output4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (fpn_lateral5): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))
+    (fpn_output5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (top_block): LastLevelMaxPool()
+    (bottom_up): ResNet(
+      (stem): BasicStem(
+        (conv1): Conv2d(
+          3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False
+          (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+        )
+      )
+      (res2): Sequential(
+        (0): BottleneckBlock(
+          (shortcut): Conv2d(
+            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv1): Conv2d(
+            64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+        )
+        (1): BottleneckBlock(
+          (conv1): Conv2d(
+            256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+        )
+        (2): BottleneckBlock(
+          (conv1): Conv2d(
+            256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+        )
+      )
+      (res3): Sequential(
+        (0): BottleneckBlock(
+          (shortcut): Conv2d(
+            256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv1): Conv2d(
+            256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+        )
+        (1): BottleneckBlock(
+          (conv1): Conv2d(
+            512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+        )
+        (2): BottleneckBlock(
+          (conv1): Conv2d(
+            512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+        )
+        (3): BottleneckBlock(
+          (conv1): Conv2d(
+            512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+        )
+      )
+      (res4): Sequential(
+        (0): BottleneckBlock(
+          (shortcut): Conv2d(
+            512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+          (conv1): Conv2d(
+            512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (1): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (2): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (3): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (4): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (5): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+      )
+      (res5): Sequential(
+        (0): BottleneckBlock(
+          (shortcut): Conv2d(
+            1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
+          )
+          (conv1): Conv2d(
+            1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
+          )
+        )
+        (1): BottleneckBlock(
+          (conv1): Conv2d(
+            2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
+          )
+        )
+        (2): BottleneckBlock(
+          (conv1): Conv2d(
+            2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
+          )
+        )
+      )
+    )
+  )
+  (proposal_generator): RPN(
+    (rpn_head): StandardRPNHead(
+      (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      (objectness_logits): Conv2d(256, 3, kernel_size=(1, 1), stride=(1, 1))
+      (anchor_deltas): Conv2d(256, 12, kernel_size=(1, 1), stride=(1, 1))
+    )
+    (anchor_generator): DefaultAnchorGenerator(
+      (cell_anchors): BufferList()
+    )
+  )
+  (roi_heads): StandardROIHeads(
+    (box_pooler): ROIPooler(
+      (level_poolers): ModuleList(
+        (0): ROIAlign(output_size=(7, 7), spatial_scale=0.25, sampling_ratio=0, aligned=True)
+        (1): ROIAlign(output_size=(7, 7), spatial_scale=0.125, sampling_ratio=0, aligned=True)
+        (2): ROIAlign(output_size=(7, 7), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
+        (3): ROIAlign(output_size=(7, 7), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
+      )
+    )
+    (box_head): FastRCNNConvFCHead(
+      (flatten): Flatten(start_dim=1, end_dim=-1)
+      (fc1): Linear(in_features=12544, out_features=1024, bias=True)
+      (fc_relu1): ReLU()
+      (fc2): Linear(in_features=1024, out_features=1024, bias=True)
+      (fc_relu2): ReLU()
+    )
+    (box_predictor): FastRCNNOutputLayers(
+      (cls_score): Linear(in_features=1024, out_features=3, bias=True)
+      (bbox_pred): Linear(in_features=1024, out_features=8, bias=True)
+    )
+    (mask_pooler): ROIPooler(
+      (level_poolers): ModuleList(
+        (0): ROIAlign(output_size=(14, 14), spatial_scale=0.25, sampling_ratio=0, aligned=True)
+        (1): ROIAlign(output_size=(14, 14), spatial_scale=0.125, sampling_ratio=0, aligned=True)
+        (2): ROIAlign(output_size=(14, 14), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
+        (3): ROIAlign(output_size=(14, 14), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
+      )
+    )
+    (mask_head): MaskRCNNConvUpsampleHead(
+      (mask_fcn1): Conv2d(
+        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
+        (activation): ReLU()
+      )
+      (mask_fcn2): Conv2d(
+        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
+        (activation): ReLU()
+      )
+      (mask_fcn3): Conv2d(
+        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
+        (activation): ReLU()
+      )
+      (mask_fcn4): Conv2d(
+        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
+        (activation): ReLU()
+      )
+      (deconv): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2))
+      (deconv_relu): ReLU()
+      (predictor): Conv2d(256, 2, kernel_size=(1, 1), stride=(1, 1))
+    )
+  )
+)
+[04/19 13:20:22] d2.data.dataset_mapper INFO: [DatasetMapper] Augmentations used in training: [ResizeShortestEdge(short_edge_length=(640, 672, 704, 736, 768, 800), max_size=1333, sample_style='choice'), RandomFlip(), RandomRotation(angle=[-90.0, 0.0])]
+[04/19 13:20:22] d2.data.datasets.coco INFO: Loaded 36 images in COCO format from /content/drive/MyDrive/layoutparser/dataset6/train/via_project_19Apr2023_15h0m_coco.json
+[04/19 13:20:22] d2.data.build INFO: Removed 6 images with no usable annotations. 30 images left.
+[04/19 13:20:22] d2.data.build INFO: Distribution of instances among all 2 categories:
+|  category  | #instances   |  category  | #instances   |
+|:----------:|:-------------|:----------:|:-------------|
+|            | 89           |            | 0            |
+|            |              |            |              |
+|   total    | 89           |            |              |
+[04/19 13:20:22] d2.data.build INFO: Using training sampler TrainingSampler
+[04/19 13:20:22] d2.data.common INFO: Serializing 30 elements to byte tensors and concatenating them all ...
+[04/19 13:20:22] d2.data.common INFO: Serialized dataset takes 0.01 MiB
+[04/19 13:20:22] d2.solver.build WARNING: SOLVER.STEPS contains values larger than SOLVER.MAX_ITER. These values will be ignored.
+[04/19 13:20:24] fvcore.common.checkpoint INFO: Loading checkpoint from /content/drive/MyDrive/layoutparser/modele/modele3_NP?/modele_final.pth
+[04/19 13:21:19] detectron2 INFO: Rank of current process: 0. World size: 1
+[04/19 13:21:20] detectron2 INFO: Environment info:
+----------------------  ----------------------------------------------------------------
+sys.platform            linux
+Python                  3.9.16 (main, Dec  7 2022, 01:11:51) [GCC 9.4.0]
+numpy                   1.22.4
+detectron2              0.4 @/usr/local/lib/python3.9/dist-packages/detectron2
+Compiler                GCC 9.4
+CUDA compiler           CUDA 11.8
+detectron2 arch flags   7.5
+DETECTRON2_ENV_MODULE   <not set>
+PyTorch                 2.0.0+cu118 @/usr/local/lib/python3.9/dist-packages/torch
+PyTorch debug build     False
+GPU available           True
+GPU 0                   Tesla T4 (arch=7.5)
+CUDA_HOME               /usr/local/cuda
+Pillow                  9.5.0
+torchvision             0.15.1+cu118 @/usr/local/lib/python3.9/dist-packages/torchvision
+torchvision arch flags  3.5, 5.0, 6.0, 7.0, 7.5, 8.0, 8.6
+fvcore                  0.1.3.post20210317
+cv2                     4.7.0
+----------------------  ----------------------------------------------------------------
+PyTorch built with:
+  - GCC 9.3
+  - C++ Version: 201703
+  - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
+  - Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)
+  - OpenMP 201511 (a.k.a. OpenMP 4.5)
+  - LAPACK is enabled (usually provided by MKL)
+  - NNPACK is enabled
+  - CPU capability usage: AVX2
+  - CUDA Runtime 11.8
+  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90
+  - CuDNN 8.7
+  - Magma 2.6.1
+  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=8.7.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.0.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 
+
+[04/19 13:21:20] detectron2 INFO: Command line arguments: Namespace(config_file='/content/layout-model-training/config_LayoutParser_PrimaDataset.yaml', resume=False, eval_only=False, num_gpus=1, num_machines=1, machine_rank=0, dist_url='tcp://127.0.0.1:49152', opts=['OUTPUT_DIR', '/content/drive/MyDrive/layoutparser/modele', 'SOLVER.IMS_PER_BATCH', '2'], dataset_name='modele', json_annotation_train='/content/drive/MyDrive/layoutparser/dataset6/train/via_project_19Apr2023_15h0m_coco.json', image_path_train='/content/drive/MyDrive/layoutparser/dataset6/train', json_annotation_val='/content/drive/MyDrive/layoutparser/dataset6/val/via_project_19Apr2023_15h9m_coco.json', image_path_val='/content/drive/MyDrive/layoutparser/dataset6/val')
+[04/19 13:21:20] detectron2 INFO: Contents of args.config_file=/content/layout-model-training/config_LayoutParser_PrimaDataset.yaml:
+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:
+  - prima-layout-val
+  TRAIN:
+  - prima-layout-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:
+  - 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_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: 7
+    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: /content/drive/MyDrive/layoutparser/modele/modele3_NP?/model_final.pth
+OUTPUT_DIR: ../outputs/prima/mask_rcnn_R_50_FPN_3x/
+SEED: -1
+SOLVER:
+  BASE_LR: 0.00025
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 50
+  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: 300
+  MOMENTUM: 0.9
+  NESTEROV: false
+  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
+
+[04/19 13:21:20] detectron2 INFO: Running with full config:
+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: ('modele-val',)
+  TRAIN: ('modele-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: 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: [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: 2
+    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
+    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: /content/drive/MyDrive/layoutparser/modele/modele3_NP?/model_final.pth
+OUTPUT_DIR: /content/drive/MyDrive/layoutparser/modele
+SEED: -1
+SOLVER:
+  AMP:
+    ENABLED: False
+  BASE_LR: 0.00025
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 50
+  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: 300
+  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
+[04/19 13:21:20] detectron2 INFO: Full config saved to /content/drive/MyDrive/layoutparser/modele/config.yaml
+[04/19 13:21:20] d2.utils.env INFO: Using a generated random seed 20391353
+[04/19 13:21:23] d2.engine.defaults INFO: Model:
+GeneralizedRCNN(
+  (backbone): FPN(
+    (fpn_lateral2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
+    (fpn_output2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (fpn_lateral3): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
+    (fpn_output3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (fpn_lateral4): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
+    (fpn_output4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (fpn_lateral5): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))
+    (fpn_output5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (top_block): LastLevelMaxPool()
+    (bottom_up): ResNet(
+      (stem): BasicStem(
+        (conv1): Conv2d(
+          3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False
+          (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+        )
+      )
+      (res2): Sequential(
+        (0): BottleneckBlock(
+          (shortcut): Conv2d(
+            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv1): Conv2d(
+            64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+        )
+        (1): BottleneckBlock(
+          (conv1): Conv2d(
+            256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+        )
+        (2): BottleneckBlock(
+          (conv1): Conv2d(
+            256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+        )
+      )
+      (res3): Sequential(
+        (0): BottleneckBlock(
+          (shortcut): Conv2d(
+            256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv1): Conv2d(
+            256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+        )
+        (1): BottleneckBlock(
+          (conv1): Conv2d(
+            512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+        )
+        (2): BottleneckBlock(
+          (conv1): Conv2d(
+            512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+        )
+        (3): BottleneckBlock(
+          (conv1): Conv2d(
+            512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+        )
+      )
+      (res4): Sequential(
+        (0): BottleneckBlock(
+          (shortcut): Conv2d(
+            512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+          (conv1): Conv2d(
+            512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (1): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (2): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (3): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (4): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+        (5): BottleneckBlock(
+          (conv1): Conv2d(
+            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
+          )
+        )
+      )
+      (res5): Sequential(
+        (0): BottleneckBlock(
+          (shortcut): Conv2d(
+            1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
+          )
+          (conv1): Conv2d(
+            1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
+          )
+        )
+        (1): BottleneckBlock(
+          (conv1): Conv2d(
+            2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
+          )
+        )
+        (2): BottleneckBlock(
+          (conv1): Conv2d(
+            2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv2): Conv2d(
+            512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
+          )
+          (conv3): Conv2d(
+            512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
+            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
+          )
+        )
+      )
+    )
+  )
+  (proposal_generator): RPN(
+    (rpn_head): StandardRPNHead(
+      (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+      (objectness_logits): Conv2d(256, 3, kernel_size=(1, 1), stride=(1, 1))
+      (anchor_deltas): Conv2d(256, 12, kernel_size=(1, 1), stride=(1, 1))
+    )
+    (anchor_generator): DefaultAnchorGenerator(
+      (cell_anchors): BufferList()
+    )
+  )
+  (roi_heads): StandardROIHeads(
+    (box_pooler): ROIPooler(
+      (level_poolers): ModuleList(
+        (0): ROIAlign(output_size=(7, 7), spatial_scale=0.25, sampling_ratio=0, aligned=True)
+        (1): ROIAlign(output_size=(7, 7), spatial_scale=0.125, sampling_ratio=0, aligned=True)
+        (2): ROIAlign(output_size=(7, 7), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
+        (3): ROIAlign(output_size=(7, 7), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
+      )
+    )
+    (box_head): FastRCNNConvFCHead(
+      (flatten): Flatten(start_dim=1, end_dim=-1)
+      (fc1): Linear(in_features=12544, out_features=1024, bias=True)
+      (fc_relu1): ReLU()
+      (fc2): Linear(in_features=1024, out_features=1024, bias=True)
+      (fc_relu2): ReLU()
+    )
+    (box_predictor): FastRCNNOutputLayers(
+      (cls_score): Linear(in_features=1024, out_features=3, bias=True)
+      (bbox_pred): Linear(in_features=1024, out_features=8, bias=True)
+    )
+    (mask_pooler): ROIPooler(
+      (level_poolers): ModuleList(
+        (0): ROIAlign(output_size=(14, 14), spatial_scale=0.25, sampling_ratio=0, aligned=True)
+        (1): ROIAlign(output_size=(14, 14), spatial_scale=0.125, sampling_ratio=0, aligned=True)
+        (2): ROIAlign(output_size=(14, 14), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
+        (3): ROIAlign(output_size=(14, 14), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
+      )
+    )
+    (mask_head): MaskRCNNConvUpsampleHead(
+      (mask_fcn1): Conv2d(
+        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
+        (activation): ReLU()
+      )
+      (mask_fcn2): Conv2d(
+        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
+        (activation): ReLU()
+      )
+      (mask_fcn3): Conv2d(
+        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
+        (activation): ReLU()
+      )
+      (mask_fcn4): Conv2d(
+        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
+        (activation): ReLU()
+      )
+      (deconv): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2))
+      (deconv_relu): ReLU()
+      (predictor): Conv2d(256, 2, kernel_size=(1, 1), stride=(1, 1))
+    )
+  )
+)
+[04/19 13:21:23] d2.data.dataset_mapper INFO: [DatasetMapper] Augmentations used in training: [ResizeShortestEdge(short_edge_length=(640, 672, 704, 736, 768, 800), max_size=1333, sample_style='choice'), RandomFlip(), RandomRotation(angle=[-90.0, 0.0])]
+[04/19 13:21:23] d2.data.datasets.coco INFO: Loaded 36 images in COCO format from /content/drive/MyDrive/layoutparser/dataset6/train/via_project_19Apr2023_15h0m_coco.json
+[04/19 13:21:23] d2.data.build INFO: Removed 6 images with no usable annotations. 30 images left.
+[04/19 13:21:23] d2.data.build INFO: Distribution of instances among all 2 categories:
+|  category  | #instances   |  category  | #instances   |
+|:----------:|:-------------|:----------:|:-------------|
+|            | 89           |            | 0            |
+|            |              |            |              |
+|   total    | 89           |            |              |
+[04/19 13:21:23] d2.data.build INFO: Using training sampler TrainingSampler
+[04/19 13:21:23] d2.data.common INFO: Serializing 30 elements to byte tensors and concatenating them all ...
+[04/19 13:21:23] d2.data.common INFO: Serialized dataset takes 0.01 MiB
+[04/19 13:21:23] d2.solver.build WARNING: SOLVER.STEPS contains values larger than SOLVER.MAX_ITER. These values will be ignored.
+[04/19 13:21:26] fvcore.common.checkpoint INFO: Loading checkpoint from /content/drive/MyDrive/layoutparser/modele/modele3_NP?/model_final.pth
+[04/19 13:21:31] d2.engine.train_loop INFO: Starting training from iteration 0
+[04/19 13:21:59] d2.utils.events INFO:  eta: 0:03:57  iter: 19  total_loss: 0.5817  loss_cls: 0.122  loss_box_reg: 0.1813  loss_mask: 0.2043  loss_rpn_cls: 0.01694  loss_rpn_loc: 0.02236  time: 0.8670  data_time: 0.0615  lr: 4.9953e-06  max_mem: 4741M
+[04/19 13:22:16] d2.utils.events INFO:  eta: 0:03:36  iter: 39  total_loss: 0.5271  loss_cls: 0.108  loss_box_reg: 0.1928  loss_mask: 0.1966  loss_rpn_cls: 0.01371  loss_rpn_loc: 0.0178  time: 0.8510  data_time: 0.0094  lr: 9.9902e-06  max_mem: 4741M
+[04/19 13:22:25] fvcore.common.checkpoint INFO: Saving checkpoint to /content/drive/MyDrive/layoutparser/modele/model_0000049.pth
+[04/19 13:22:35] d2.utils.events INFO:  eta: 0:03:22  iter: 59  total_loss: 0.5328  loss_cls: 0.09943  loss_box_reg: 0.1768  loss_mask: 0.1878  loss_rpn_cls: 0.01652  loss_rpn_loc: 0.02977  time: 0.8703  data_time: 0.0149  lr: 1.4985e-05  max_mem: 4742M
+[04/19 13:22:53] d2.utils.events INFO:  eta: 0:03:09  iter: 79  total_loss: 0.5528  loss_cls: 0.1002  loss_box_reg: 0.1706  loss_mask: 0.2053  loss_rpn_cls: 0.01738  loss_rpn_loc: 0.02357  time: 0.8795  data_time: 0.0108  lr: 1.998e-05  max_mem: 4742M
+[04/19 13:23:11] fvcore.common.checkpoint INFO: Saving checkpoint to /content/drive/MyDrive/layoutparser/modele/model_0000099.pth
+[04/19 13:23:13] d2.utils.events INFO:  eta: 0:02:53  iter: 99  total_loss: 0.5248  loss_cls: 0.08265  loss_box_reg: 0.1726  loss_mask: 0.1772  loss_rpn_cls: 0.01976  loss_rpn_loc: 0.02078  time: 0.8858  data_time: 0.0114  lr: 2.4975e-05  max_mem: 4742M
+[04/19 13:23:32] d2.utils.events INFO:  eta: 0:02:38  iter: 119  total_loss: 0.5286  loss_cls: 0.09827  loss_box_reg: 0.1722  loss_mask: 0.1774  loss_rpn_cls: 0.01788  loss_rpn_loc: 0.0259  time: 0.8971  data_time: 0.0096  lr: 2.997e-05  max_mem: 4742M
+[04/19 13:23:50] d2.utils.events INFO:  eta: 0:02:21  iter: 139  total_loss: 0.5629  loss_cls: 0.09456  loss_box_reg: 0.1846  loss_mask: 0.1865  loss_rpn_cls: 0.02039  loss_rpn_loc: 0.02839  time: 0.9012  data_time: 0.0110  lr: 3.4965e-05  max_mem: 4742M
+[04/19 13:23:59] fvcore.common.checkpoint INFO: Saving checkpoint to /content/drive/MyDrive/layoutparser/modele/model_0000149.pth
+[04/19 13:24:10] d2.utils.events INFO:  eta: 0:02:04  iter: 159  total_loss: 0.491  loss_cls: 0.09832  loss_box_reg: 0.1694  loss_mask: 0.1691  loss_rpn_cls: 0.008938  loss_rpn_loc: 0.01734  time: 0.9020  data_time: 0.0080  lr: 3.996e-05  max_mem: 4742M
+[04/19 13:24:29] d2.utils.events INFO:  eta: 0:01:47  iter: 179  total_loss: 0.4756  loss_cls: 0.08483  loss_box_reg: 0.162  loss_mask: 0.1571  loss_rpn_cls: 0.01482  loss_rpn_loc: 0.03214  time: 0.9094  data_time: 0.0101  lr: 4.4955e-05  max_mem: 4742M
+[04/19 13:24:49] fvcore.common.checkpoint INFO: Saving checkpoint to /content/drive/MyDrive/layoutparser/modele/model_0000199.pth
+[04/19 13:24:50] d2.utils.events INFO:  eta: 0:01:30  iter: 199  total_loss: 0.4405  loss_cls: 0.08707  loss_box_reg: 0.1718  loss_mask: 0.1673  loss_rpn_cls: 0.008687  loss_rpn_loc: 0.02504  time: 0.9157  data_time: 0.0107  lr: 4.995e-05  max_mem: 4742M
+[04/19 13:25:09] d2.utils.events INFO:  eta: 0:01:12  iter: 219  total_loss: 0.4541  loss_cls: 0.08539  loss_box_reg: 0.1581  loss_mask: 0.1605  loss_rpn_cls: 0.01627  loss_rpn_loc: 0.01755  time: 0.9168  data_time: 0.0112  lr: 5.4945e-05  max_mem: 4742M
+[04/19 13:25:28] d2.utils.events INFO:  eta: 0:00:54  iter: 239  total_loss: 0.4896  loss_cls: 0.09352  loss_box_reg: 0.1829  loss_mask: 0.1675  loss_rpn_cls: 0.0139  loss_rpn_loc: 0.02522  time: 0.9196  data_time: 0.0080  lr: 5.994e-05  max_mem: 4742M
+[04/19 13:25:37] fvcore.common.checkpoint INFO: Saving checkpoint to /content/drive/MyDrive/layoutparser/modele/model_0000249.pth
+[04/19 13:25:48] d2.utils.events INFO:  eta: 0:00:36  iter: 259  total_loss: 0.4373  loss_cls: 0.06817  loss_box_reg: 0.1526  loss_mask: 0.1634  loss_rpn_cls: 0.0137  loss_rpn_loc: 0.02394  time: 0.9241  data_time: 0.0098  lr: 6.4935e-05  max_mem: 4742M
+[04/19 13:26:08] d2.utils.events INFO:  eta: 0:00:18  iter: 279  total_loss: 0.4922  loss_cls: 0.1011  loss_box_reg: 0.1941  loss_mask: 0.1613  loss_rpn_cls: 0.01023  loss_rpn_loc: 0.03586  time: 0.9272  data_time: 0.0080  lr: 6.993e-05  max_mem: 4742M
+[04/19 13:26:28] fvcore.common.checkpoint INFO: Saving checkpoint to /content/drive/MyDrive/layoutparser/modele/model_0000299.pth
+[04/19 13:26:29] fvcore.common.checkpoint INFO: Saving checkpoint to /content/drive/MyDrive/layoutparser/modele/model_final.pth
+[04/19 13:26:31] d2.utils.events INFO:  eta: 0:00:00  iter: 299  total_loss: 0.4673  loss_cls: 0.08663  loss_box_reg: 0.178  loss_mask: 0.1653  loss_rpn_cls: 0.006576  loss_rpn_loc: 0.02131  time: 0.9322  data_time: 0.0116  lr: 7.4925e-05  max_mem: 4742M
+[04/19 13:26:31] d2.engine.hooks INFO: Overall training speed: 298 iterations in 0:04:37 (0.9322 s / it)
+[04/19 13:26:31] d2.engine.hooks INFO: Total training time: 0:04:47 (0:00:09 on hooks)

metrics.json

@@ -0,0 +1,15 @@
+{"data_time": 0.0078072735000205284, "eta_seconds": 237.39525767999226, "fast_rcnn/cls_accuracy": 0.95166015625, "fast_rcnn/false_negative": 0.3174242424242424, "fast_rcnn/fg_cls_accuracy": 0.6825757575757576, "iteration": 19, "loss_box_reg": 0.18126913160085678, "loss_cls": 0.12200355529785156, "loss_mask": 0.20430559664964676, "loss_rpn_cls": 0.016937402077019215, "loss_rpn_loc": 0.022357339970767498, "lr": 4.99525e-06, "mask_rcnn/accuracy": 0.9157851735164111, "mask_rcnn/false_negative": 0.08747882744709648, "mask_rcnn/false_positive": 0.0695743153731449, "roi_head/num_bg_samples": 451.75, "roi_head/num_fg_samples": 60.25, "rpn/num_neg_anchors": 241.0, "rpn/num_pos_anchors": 15.0, "time": 0.8478402059999723, "total_loss": 0.5817432205658406}
+{"data_time": 0.00806954000006499, "eta_seconds": 216.88964089000365, "fast_rcnn/cls_accuracy": 0.958984375, "fast_rcnn/false_negative": 0.16390334811387441, "fast_rcnn/fg_cls_accuracy": 0.8360966518861256, "iteration": 39, "loss_box_reg": 0.19283011555671692, "loss_cls": 0.1080242358148098, "loss_mask": 0.19663811475038528, "loss_rpn_cls": 0.013711910229176283, "loss_rpn_loc": 0.017802692018449306, "lr": 9.99025e-06, "mask_rcnn/accuracy": 0.9198041697517024, "mask_rcnn/false_negative": 0.06658453429298014, "mask_rcnn/false_positive": 0.0970188841812121, "roi_head/num_bg_samples": 457.75, "roi_head/num_fg_samples": 54.25, "rpn/num_neg_anchors": 246.5, "rpn/num_pos_anchors": 9.5, "time": 0.833926538500009, "total_loss": 0.5270909374230541}
+{"data_time": 0.00786942999997109, "eta_seconds": 202.049228399992, "fast_rcnn/cls_accuracy": 0.96044921875, "fast_rcnn/false_negative": 0.17474278128111514, "fast_rcnn/fg_cls_accuracy": 0.8252572187188849, "iteration": 59, "loss_box_reg": 0.17683134227991104, "loss_cls": 0.09942953288555145, "loss_mask": 0.18784072250127792, "loss_rpn_cls": 0.016522271558642387, "loss_rpn_loc": 0.029772663488984108, "lr": 1.4985249999999999e-05, "mask_rcnn/accuracy": 0.9230181719833241, "mask_rcnn/false_negative": 0.0657658037432446, "mask_rcnn/false_positive": 0.0900701805017563, "roi_head/num_bg_samples": 448.5, "roi_head/num_fg_samples": 63.5, "rpn/num_neg_anchors": 236.75, "rpn/num_pos_anchors": 19.25, "time": 0.9238360184999692, "total_loss": 0.5328234452754259}
+{"data_time": 0.008662080000021888, "eta_seconds": 189.94938489998844, "fast_rcnn/cls_accuracy": 0.95556640625, "fast_rcnn/false_negative": 0.18949298469387754, "fast_rcnn/fg_cls_accuracy": 0.8105070153061225, "iteration": 79, "loss_box_reg": 0.1706439107656479, "loss_cls": 0.10022062435746193, "loss_mask": 0.2053210288286209, "loss_rpn_cls": 0.01738046295940876, "loss_rpn_loc": 0.023568041622638702, "lr": 1.998025e-05, "mask_rcnn/accuracy": 0.9150773466560775, "mask_rcnn/false_negative": 0.07122972866131304, "mask_rcnn/false_positive": 0.09154645211619379, "roi_head/num_bg_samples": 449.25, "roi_head/num_fg_samples": 62.75, "rpn/num_neg_anchors": 240.25, "rpn/num_pos_anchors": 15.75, "time": 0.8898190154999952, "total_loss": 0.5527677149511874}
+{"data_time": 0.00794200899997577, "eta_seconds": 173.0306518999953, "fast_rcnn/cls_accuracy": 0.96337890625, "fast_rcnn/false_negative": 0.16227766227766227, "fast_rcnn/fg_cls_accuracy": 0.8377223377223377, "iteration": 99, "loss_box_reg": 0.1726074069738388, "loss_cls": 0.08265357092022896, "loss_mask": 0.17723622918128967, "loss_rpn_cls": 0.019758455455303192, "loss_rpn_loc": 0.020779786631464958, "lr": 2.497525e-05, "mask_rcnn/accuracy": 0.926530693319756, "mask_rcnn/false_negative": 0.060582644882807374, "mask_rcnn/false_positive": 0.08944657671381483, "roi_head/num_bg_samples": 455.25, "roi_head/num_fg_samples": 56.75, "rpn/num_neg_anchors": 241.0, "rpn/num_pos_anchors": 15.0, "time": 0.8802101579999544, "total_loss": 0.5247725388035178}
+{"data_time": 0.008146928499968453, "eta_seconds": 158.05110491999926, "fast_rcnn/cls_accuracy": 0.9560546875, "fast_rcnn/false_negative": 0.17490097977902858, "fast_rcnn/fg_cls_accuracy": 0.8250990202209715, "iteration": 119, "loss_box_reg": 0.1722310408949852, "loss_cls": 0.09827171638607979, "loss_mask": 0.17743538320064545, "loss_rpn_cls": 0.01788422279059887, "loss_rpn_loc": 0.02590081002563238, "lr": 2.997025e-05, "mask_rcnn/accuracy": 0.9272291260401985, "mask_rcnn/false_negative": 0.05649131234239554, "mask_rcnn/false_positive": 0.08877379884621533, "roi_head/num_bg_samples": 445.5, "roi_head/num_fg_samples": 66.5, "rpn/num_neg_anchors": 238.25, "rpn/num_pos_anchors": 17.75, "time": 0.9440659295000273, "total_loss": 0.5285513289272785}
+{"data_time": 0.008035532000008061, "eta_seconds": 141.67043927999657, "fast_rcnn/cls_accuracy": 0.96142578125, "fast_rcnn/false_negative": 0.16287878787878787, "fast_rcnn/fg_cls_accuracy": 0.8371212121212122, "iteration": 139, "loss_box_reg": 0.18458272516727448, "loss_cls": 0.09455696865916252, "loss_mask": 0.18651333451271057, "loss_rpn_cls": 0.020386052317917347, "loss_rpn_loc": 0.02839471399784088, "lr": 3.496525e-05, "mask_rcnn/accuracy": 0.9227865388579675, "mask_rcnn/false_negative": 0.07823887426949008, "mask_rcnn/false_positive": 0.07714565725517517, "roi_head/num_bg_samples": 446.5, "roi_head/num_fg_samples": 65.5, "rpn/num_neg_anchors": 238.25, "rpn/num_pos_anchors": 17.75, "time": 0.9290176410000299, "total_loss": 0.5628998675383627}
+{"data_time": 0.007225867999977709, "eta_seconds": 124.62774071999547, "fast_rcnn/cls_accuracy": 0.96044921875, "fast_rcnn/false_negative": 0.1421979510625688, "fast_rcnn/fg_cls_accuracy": 0.8578020489374312, "iteration": 159, "loss_box_reg": 0.1694139465689659, "loss_cls": 0.0983157642185688, "loss_mask": 0.1690504029393196, "loss_rpn_cls": 0.008938258048146963, "loss_rpn_loc": 0.017336225137114525, "lr": 3.996025e-05, "mask_rcnn/accuracy": 0.9304054076088729, "mask_rcnn/false_negative": 0.05453408259940976, "mask_rcnn/false_positive": 0.09687290684287767, "roi_head/num_bg_samples": 445.25, "roi_head/num_fg_samples": 66.75, "rpn/num_neg_anchors": 241.5, "rpn/num_pos_anchors": 14.5, "time": 0.9201212560000158, "total_loss": 0.4909819355234504}
+{"data_time": 0.00790757049998092, "eta_seconds": 107.98438782000176, "fast_rcnn/cls_accuracy": 0.9638671875, "fast_rcnn/false_negative": 0.14458689458689458, "fast_rcnn/fg_cls_accuracy": 0.8554131054131053, "iteration": 179, "loss_box_reg": 0.16203460097312927, "loss_cls": 0.08482548221945763, "loss_mask": 0.15712527930736542, "loss_rpn_cls": 0.014815961476415396, "loss_rpn_loc": 0.03214004077017307, "lr": 4.4955249999999996e-05, "mask_rcnn/accuracy": 0.9360310090632289, "mask_rcnn/false_negative": 0.052590317311748784, "mask_rcnn/false_positive": 0.07957992414234528, "roi_head/num_bg_samples": 450.25, "roi_head/num_fg_samples": 61.75, "rpn/num_neg_anchors": 234.75, "rpn/num_pos_anchors": 21.25, "time": 0.9635756369999626, "total_loss": 0.4756494527682662}
+{"data_time": 0.0086770730000012, "eta_seconds": 90.48390140000038, "fast_rcnn/cls_accuracy": 0.96484375, "fast_rcnn/false_negative": 0.1505813953488372, "fast_rcnn/fg_cls_accuracy": 0.8494186046511627, "iteration": 199, "loss_box_reg": 0.17175166308879852, "loss_cls": 0.08706623315811157, "loss_mask": 0.16731856018304825, "loss_rpn_cls": 0.008686745539307594, "loss_rpn_loc": 0.02504018973559141, "lr": 4.995025e-05, "mask_rcnn/accuracy": 0.9339812504672198, "mask_rcnn/false_negative": 0.05094937251124136, "mask_rcnn/false_positive": 0.08033686683134766, "roi_head/num_bg_samples": 440.25, "roi_head/num_fg_samples": 71.75, "rpn/num_neg_anchors": 237.25, "rpn/num_pos_anchors": 18.75, "time": 0.9430582679999588, "total_loss": 0.44054083712399006}
+{"data_time": 0.008456396499980201, "eta_seconds": 72.20415547999892, "fast_rcnn/cls_accuracy": 0.96435546875, "fast_rcnn/false_negative": 0.1619129207821004, "fast_rcnn/fg_cls_accuracy": 0.8380870792178996, "iteration": 219, "loss_box_reg": 0.15810220688581467, "loss_cls": 0.0853872038424015, "loss_mask": 0.16054382175207138, "loss_rpn_cls": 0.0162694756872952, "loss_rpn_loc": 0.017554521560668945, "lr": 5.4945249999999994e-05, "mask_rcnn/accuracy": 0.9320155062452881, "mask_rcnn/false_negative": 0.04592440045344945, "mask_rcnn/false_positive": 0.0795499642582482, "roi_head/num_bg_samples": 451.5, "roi_head/num_fg_samples": 60.5, "rpn/num_neg_anchors": 242.5, "rpn/num_pos_anchors": 13.5, "time": 0.8711087875000203, "total_loss": 0.45414171810261905}
+{"data_time": 0.007589212500022313, "eta_seconds": 54.58721795999736, "fast_rcnn/cls_accuracy": 0.95849609375, "fast_rcnn/false_negative": 0.16044207317073172, "fast_rcnn/fg_cls_accuracy": 0.8395579268292683, "iteration": 239, "loss_box_reg": 0.1828964427113533, "loss_cls": 0.09351714327931404, "loss_mask": 0.16754969954490662, "loss_rpn_cls": 0.013895321637392044, "loss_rpn_loc": 0.025216294452548027, "lr": 5.994025e-05, "mask_rcnn/accuracy": 0.9330968072439287, "mask_rcnn/false_negative": 0.06683586210006436, "mask_rcnn/false_positive": 0.07417598373963799, "roi_head/num_bg_samples": 444.5, "roi_head/num_fg_samples": 67.5, "rpn/num_neg_anchors": 236.75, "rpn/num_pos_anchors": 19.25, "time": 0.9715423750000127, "total_loss": 0.48956847935914993}
+{"data_time": 0.007639148999999179, "eta_seconds": 36.52443835999975, "fast_rcnn/cls_accuracy": 0.97265625, "fast_rcnn/false_negative": 0.13006756756756757, "fast_rcnn/fg_cls_accuracy": 0.8699324324324325, "iteration": 259, "loss_box_reg": 0.15263817459344864, "loss_cls": 0.06817140802741051, "loss_mask": 0.16339514404535294, "loss_rpn_cls": 0.013702766969799995, "loss_rpn_loc": 0.02394229080528021, "lr": 6.493524999999999e-05, "mask_rcnn/accuracy": 0.9331995923664416, "mask_rcnn/false_negative": 0.06182471100588811, "mask_rcnn/false_positive": 0.07560936337703598, "roi_head/num_bg_samples": 456.0, "roi_head/num_fg_samples": 56.0, "rpn/num_neg_anchors": 237.25, "rpn/num_pos_anchors": 18.75, "time": 0.9697470364999958, "total_loss": 0.4373055868782103}
+{"data_time": 0.006967480000014348, "eta_seconds": 18.328599830000485, "fast_rcnn/cls_accuracy": 0.95849609375, "fast_rcnn/false_negative": 0.15975460122699386, "fast_rcnn/fg_cls_accuracy": 0.8402453987730061, "iteration": 279, "loss_box_reg": 0.19406820833683014, "loss_cls": 0.10113400965929031, "loss_mask": 0.16126281768083572, "loss_rpn_cls": 0.010230929590761662, "loss_rpn_loc": 0.03586099483072758, "lr": 6.993025000000002e-05, "mask_rcnn/accuracy": 0.9344176832287108, "mask_rcnn/false_negative": 0.05820550465518141, "mask_rcnn/false_positive": 0.07525972862418362, "roi_head/num_bg_samples": 439.25, "roi_head/num_fg_samples": 72.75, "rpn/num_neg_anchors": 232.25, "rpn/num_pos_anchors": 23.75, "time": 0.9761503915000276, "total_loss": 0.49223250965587795}
+{"data_time": 0.006742446499970356, "eta_seconds": 0.0, "fast_rcnn/cls_accuracy": 0.96240234375, "fast_rcnn/false_negative": 0.14442586399108137, "fast_rcnn/fg_cls_accuracy": 0.8555741360089186, "iteration": 299, "loss_box_reg": 0.177964448928833, "loss_cls": 0.08662557601928711, "loss_mask": 0.16527117043733597, "loss_rpn_cls": 0.00657613156363368, "loss_rpn_loc": 0.02130951825529337, "lr": 7.492525e-05, "mask_rcnn/accuracy": 0.9326858258393901, "mask_rcnn/false_negative": 0.05731613109281186, "mask_rcnn/false_positive": 0.07353323320056379, "roi_head/num_bg_samples": 439.5, "roi_head/num_fg_samples": 72.5, "rpn/num_neg_anchors": 238.75, "rpn/num_pos_anchors": 17.25, "time": 0.9941317265000293, "total_loss": 0.467316235328326}

model_final.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00d22a9f036ec1348f75c186c06bbe6ad0b450fd4613f24f61bcd531426ccdd1
+size 351071593