[04/17 14:10:02 detectron2]: Rank of current process: 0. World size: 8 [04/17 14:10:20 detectron2]: Environment info: ---------------------- -------------------------------------------------------------------------------------------------------------------------- sys.platform linux Python 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0] numpy 1.21.5 detectron2 0.6 @/mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/detectron2 Compiler GCC 7.3 CUDA compiler CUDA 11.1 detectron2 arch flags 3.7, 5.0, 5.2, 6.0, 6.1, 7.0, 7.5, 8.0, 8.6 DETECTRON2_ENV_MODULE PyTorch 1.10.0+cu111 @/mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch PyTorch debug build False GPU available Yes GPU 0,1,2,3,4,5,6,7 A100-SXM4-40GB (arch=8.0) Driver version 450.142.00 CUDA_HOME /usr/local/cuda Pillow 8.4.0 torchvision 0.11.1+cu111 @/mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torchvision torchvision arch flags 3.5, 5.0, 6.0, 7.0, 7.5, 8.0, 8.6 fvcore 0.1.5.post20211023 iopath 0.1.9 cv2 Not found ---------------------- -------------------------------------------------------------------------------------------------------------------------- PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.1 - 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 - CuDNN 8.0.5 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -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 -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.10.0, 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=ON, USE_NNPACK=ON, USE_OPENMP=ON, [04/17 14:10:20 detectron2]: Command line arguments: Namespace(config_file='cascade_layoutlmv3.yaml', debug=False, dist_url='tcp://127.0.0.1:50156', eval_only=True, machine_rank=0, num_gpus=8, num_machines=1, opts=['MODEL.WEIGHTS', '/mnt/localdata/users/yupanhuang/models/layoutlmv3/fts/publaynet-base/model_final.pth', 'OUTPUT_DIR', '/mnt/localdata/users/yupanhuang/models/layoutlmv3/fts/publaynet-base/'], resume=False) [04/17 14:10:20 detectron2]: Contents of args.config_file=cascade_layoutlmv3.yaml: MODEL: MASK_ON: True MAX_LENGTH: 510 IMAGE_ONLY: True META_ARCHITECTURE: "VLGeneralizedRCNN" PIXEL_MEAN: [ 127.5, 127.5, 127.5 ] PIXEL_STD: [ 127.5, 127.5, 127.5 ] WEIGHTS: "/mnt/localdata/users/yupanhuang/models/layoutlmv3/pts/layoutlmv3-base/pytorch_model.bin" BACKBONE: NAME: "build_vit_fpn_backbone" VIT: NAME: "layoutlmv3_base" OUT_FEATURES: [ "layer3", "layer5", "layer7", "layer11" ] DROP_PATH: 0.1 IMG_SIZE: [ 224,224 ] POS_TYPE: "abs" ROI_HEADS: NAME: CascadeROIHeads IN_FEATURES: [ "p2", "p3", "p4", "p5" ] NUM_CLASSES: 5 ROI_BOX_HEAD: CLS_AGNOSTIC_BBOX_REG: True NAME: "FastRCNNConvFCHead" NUM_FC: 2 POOLER_RESOLUTION: 7 ROI_MASK_HEAD: NAME: "MaskRCNNConvUpsampleHead" NUM_CONV: 4 POOLER_RESOLUTION: 14 FPN: IN_FEATURES: [ "layer3", "layer5", "layer7", "layer11" ] ANCHOR_GENERATOR: SIZES: [ [ 32 ], [ 64 ], [ 128 ], [ 256 ], [ 512 ] ] # One size for each in feature map ASPECT_RATIOS: [ [ 0.5, 1.0, 2.0 ] ] # Three aspect ratios (same for all in feature maps) RPN: IN_FEATURES: [ "p2", "p3", "p4", "p5", "p6" ] PRE_NMS_TOPK_TRAIN: 2000 # Per FPN level PRE_NMS_TOPK_TEST: 1000 # Per FPN level # Detectron1 uses 2000 proposals per-batch, # (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue) # which is approximately 1000 proposals per-image since the default batch size for FPN is 2. POST_NMS_TOPK_TRAIN: 2000 POST_NMS_TOPK_TEST: 1000 DATASETS: TRAIN: ("publaynet_train",) TEST: ("publaynet_val",) SOLVER: GRADIENT_ACCUMULATION_STEPS: 1 BASE_LR: 0.0002 WARMUP_ITERS: 1000 IMS_PER_BATCH: 32 MAX_ITER: 60000 CHECKPOINT_PERIOD: 2000 LR_SCHEDULER_NAME: "WarmupCosineLR" AMP: ENABLED: True OPTIMIZER: "ADAMW" BACKBONE_MULTIPLIER: 1.0 CLIP_GRADIENTS: ENABLED: True CLIP_TYPE: "full_model" CLIP_VALUE: 1.0 NORM_TYPE: 2.0 WARMUP_FACTOR: 0.01 WEIGHT_DECAY: 0.05 TEST: EVAL_PERIOD: 2000 INPUT: CROP: ENABLED: True TYPE: "absolute_range" SIZE: (384, 600) MIN_SIZE_TRAIN: (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800) FORMAT: "RGB" DATALOADER: FILTER_EMPTY_ANNOTATIONS: False VERSION: 2 AUG: DETR: True SEED: 42 OUTPUT_DIR: "/mnt/localdata/users/yupanhuang/models/layoutlmv3/fts/publaynet/" PUBLAYNET_DATA_DIR_TRAIN: "/mnt/localdata/users/yupanhuang/data/PubLayNet/publaynet/train" PUBLAYNET_DATA_DIR_TEST: "/mnt/localdata/users/yupanhuang/data/PubLayNet/publaynet/val" OCR_DATA_DIR_TRAIN: "/mnt/localdata/users/yupanhuang/data/PubLayNet/ocr/train" OCR_DATA_DIR_TEST: "/mnt/localdata/users/yupanhuang/data/PubLayNet/ocr/val" CACHE_DIR: "/mnt/localdata/users/yupanhuang/cache/huggingface" [04/17 14:10:20 detectron2]: Running with full config: AUG: DETR: true CACHE_DIR: /mnt/localdata/users/yupanhuang/cache/huggingface CUDNN_BENCHMARK: false DATALOADER: ASPECT_RATIO_GROUPING: true FILTER_EMPTY_ANNOTATIONS: false NUM_WORKERS: 4 REPEAT_THRESHOLD: 0.0 SAMPLER_TRAIN: TrainingSampler DATASETS: PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000 PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000 PROPOSAL_FILES_TEST: [] PROPOSAL_FILES_TRAIN: [] TEST: - publaynet_val TRAIN: - publaynet_train GLOBAL: HACK: 1.0 ICDAR_DATA_DIR_TEST: '' ICDAR_DATA_DIR_TRAIN: '' INPUT: CROP: ENABLED: true SIZE: - 384 - 600 TYPE: absolute_range FORMAT: RGB MASK_FORMAT: polygon MAX_SIZE_TEST: 1333 MAX_SIZE_TRAIN: 1333 MIN_SIZE_TEST: 800 MIN_SIZE_TRAIN: - 480 - 512 - 544 - 576 - 608 - 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_vit_fpn_backbone CONFIG_PATH: '' DEVICE: cuda FPN: FUSE_TYPE: sum IN_FEATURES: - layer3 - layer5 - layer7 - layer11 NORM: '' OUT_CHANNELS: 256 IMAGE_ONLY: true KEYPOINT_ON: false LOAD_PROPOSALS: false MASK_ON: true MAX_LENGTH: 510 META_ARCHITECTURE: VLGeneralizedRCNN 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: - 127.5 - 127.5 - 127.5 PIXEL_STD: - 127.5 - 127.5 - 127.5 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: - res4 RES2_OUT_CHANNELS: 256 RES5_DILATION: 1 STEM_OUT_CHANNELS: 64 STRIDE_IN_1X1: true WIDTH_PER_GROUP: 64 RETINANET: BBOX_REG_LOSS_TYPE: smooth_l1 BBOX_REG_WEIGHTS: &id001 - 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: true 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: CascadeROIHeads NMS_THRESH_TEST: 0.5 NUM_CLASSES: 5 POSITIVE_FRACTION: 0.25 PROPOSAL_APPEND_GT: true SCORE_THRESH_TEST: 0.05 ROI_KEYPOINT_HEAD: CONV_DIMS: - 512 - 512 - 512 - 512 - 512 - 512 - 512 - 512 LOSS_WEIGHT: 1.0 MIN_KEYPOINTS_PER_IMAGE: 1 NAME: KRCNNConvDeconvUpsampleHead NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: true NUM_KEYPOINTS: 17 POOLER_RESOLUTION: 14 POOLER_SAMPLING_RATIO: 0 POOLER_TYPE: ROIAlignV2 ROI_MASK_HEAD: CLS_AGNOSTIC_MASK: false CONV_DIM: 256 NAME: MaskRCNNConvUpsampleHead NORM: '' NUM_CONV: 4 POOLER_RESOLUTION: 14 POOLER_SAMPLING_RATIO: 0 POOLER_TYPE: ROIAlignV2 RPN: BATCH_SIZE_PER_IMAGE: 256 BBOX_REG_LOSS_TYPE: smooth_l1 BBOX_REG_LOSS_WEIGHT: 1.0 BBOX_REG_WEIGHTS: *id001 BOUNDARY_THRESH: -1 CONV_DIMS: - -1 HEAD_NAME: StandardRPNHead IN_FEATURES: - p2 - p3 - p4 - p5 - p6 IOU_LABELS: - 0 - -1 - 1 IOU_THRESHOLDS: - 0.3 - 0.7 LOSS_WEIGHT: 1.0 NMS_THRESH: 0.7 POSITIVE_FRACTION: 0.5 POST_NMS_TOPK_TEST: 1000 POST_NMS_TOPK_TRAIN: 2000 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 VIT: DROP_PATH: 0.1 IMG_SIZE: - 224 - 224 MODEL_KWARGS: '{}' NAME: layoutlmv3_base OUT_FEATURES: - layer3 - layer5 - layer7 - layer11 POS_TYPE: abs WEIGHTS: /mnt/localdata/users/yupanhuang/models/layoutlmv3/fts/publaynet-base/model_final.pth OCR_DATA_DIR_TEST: /mnt/localdata/users/yupanhuang/data/PubLayNet/ocr/val OCR_DATA_DIR_TRAIN: /mnt/localdata/users/yupanhuang/data/PubLayNet/ocr/train OUTPUT_DIR: /mnt/localdata/users/yupanhuang/models/layoutlmv3/fts/publaynet-base/ PUBLAYNET_DATA_DIR_TEST: /mnt/localdata/users/yupanhuang/data/PubLayNet/publaynet/val PUBLAYNET_DATA_DIR_TRAIN: /mnt/localdata/users/yupanhuang/data/PubLayNet/publaynet/train SEED: 42 SOLVER: AMP: ENABLED: true BACKBONE_MULTIPLIER: 1.0 BASE_LR: 0.0002 BIAS_LR_FACTOR: 1.0 CHECKPOINT_PERIOD: 2000 CLIP_GRADIENTS: CLIP_TYPE: full_model CLIP_VALUE: 1.0 ENABLED: true NORM_TYPE: 2.0 GAMMA: 0.1 GRADIENT_ACCUMULATION_STEPS: 1 IMS_PER_BATCH: 32 LR_SCHEDULER_NAME: WarmupCosineLR MAX_ITER: 60000 MOMENTUM: 0.9 NESTEROV: false OPTIMIZER: ADAMW REFERENCE_WORLD_SIZE: 0 STEPS: - 30000 WARMUP_FACTOR: 0.01 WARMUP_ITERS: 1000 WARMUP_METHOD: linear WEIGHT_DECAY: 0.05 WEIGHT_DECAY_BIAS: null 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: 2000 EXPECTED_RESULTS: [] KEYPOINT_OKS_SIGMAS: [] PRECISE_BN: ENABLED: false NUM_ITER: 200 VERSION: 2 VIS_PERIOD: 0 [04/17 14:10:20 detectron2]: Full config saved to /mnt/localdata/users/yupanhuang/models/layoutlmv3/fts/publaynet-base/config.yaml [04/17 14:10:21 fvcore.common.checkpoint]: [Checkpointer] Loading from /mnt/localdata/users/yupanhuang/models/layoutlmv3/fts/publaynet-base/model_final.pth ... [04/17 14:10:23 d2.data.datasets.coco]: Loading /mnt/localdata/users/yupanhuang/data/PubLayNet/publaynet/val.json takes 1.71 seconds. [04/17 14:10:24 d2.data.datasets.coco]: Loaded 11245 images in COCO format from /mnt/localdata/users/yupanhuang/data/PubLayNet/publaynet/val.json [04/17 14:10:25 d2.data.build]: Distribution of instances among all 5 categories: | category | #instances | category | #instances | category | #instances | |:----------:|:-------------|:----------:|:-------------|:----------:|:-------------| | text | 88625 | title | 18801 | list | 4239 | | table | 4769 | figure | 4327 | | | | total | 120761 | | | | | [04/17 14:10:25 d2.data.common]: Serializing 11245 elements to byte tensors and concatenating them all ... [04/17 14:10:25 d2.data.common]: Serialized dataset takes 55.80 MiB /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/detectron2/structures/image_list.py:88: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). max_size = (max_size + (stride - 1)) // stride * stride /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/nn/functional.py:3635: UserWarning: Default upsampling behavior when mode=bicubic is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode) /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] [04/17 14:10:27 d2.evaluation.evaluator]: Start inference on 1406 batches /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/detectron2/structures/image_list.py:88: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). max_size = (max_size + (stride - 1)) // stride * stride /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/nn/functional.py:3635: UserWarning: Default upsampling behavior when mode=bicubic is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode) /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/detectron2/structures/image_list.py:88: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). max_size = (max_size + (stride - 1)) // stride * stride /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/detectron2/structures/image_list.py:88: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). max_size = (max_size + (stride - 1)) // stride * stride /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/nn/functional.py:3635: UserWarning: Default upsampling behavior when mode=bicubic is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode) /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/nn/functional.py:3635: UserWarning: Default upsampling behavior when mode=bicubic is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode) /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/detectron2/structures/image_list.py:88: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). max_size = (max_size + (stride - 1)) // stride * stride /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/nn/functional.py:3635: UserWarning: Default upsampling behavior when mode=bicubic is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode) /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/detectron2/structures/image_list.py:88: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). max_size = (max_size + (stride - 1)) // stride * stride /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/detectron2/structures/image_list.py:88: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). max_size = (max_size + (stride - 1)) // stride * stride /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/nn/functional.py:3635: UserWarning: Default upsampling behavior when mode=bicubic is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode) /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/nn/functional.py:3635: UserWarning: Default upsampling behavior when mode=bicubic is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode) /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/detectron2/structures/image_list.py:88: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). max_size = (max_size + (stride - 1)) // stride * stride /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/nn/functional.py:3635: UserWarning: Default upsampling behavior when mode=bicubic is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode) /mnt/localdata/users/yupanhuang/Downloads/miniconda3/envs/layoutlmft/lib/python3.7/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] [04/17 14:10:39 d2.evaluation.evaluator]: Inference done 11/1406. Dataloading: 0.0029 s/iter. Inference: 0.1609 s/iter. Eval: 0.0212 s/iter. Total: 0.1850 s/iter. ETA=0:04:18 [04/17 14:10:44 d2.evaluation.evaluator]: Inference done 38/1406. Dataloading: 0.0036 s/iter. Inference: 0.1729 s/iter. Eval: 0.0140 s/iter. Total: 0.1909 s/iter. ETA=0:04:21 [04/17 14:10:50 d2.evaluation.evaluator]: Inference done 66/1406. Dataloading: 0.0027 s/iter. Inference: 0.1703 s/iter. Eval: 0.0149 s/iter. Total: 0.1882 s/iter. ETA=0:04:12 [04/17 14:10:55 d2.evaluation.evaluator]: Inference done 93/1406. Dataloading: 0.0035 s/iter. Inference: 0.1691 s/iter. Eval: 0.0146 s/iter. Total: 0.1874 s/iter. ETA=0:04:06 [04/17 14:11:00 d2.evaluation.evaluator]: Inference done 121/1406. Dataloading: 0.0034 s/iter. Inference: 0.1687 s/iter. Eval: 0.0141 s/iter. Total: 0.1864 s/iter. ETA=0:03:59 [04/17 14:11:05 d2.evaluation.evaluator]: Inference done 149/1406. Dataloading: 0.0031 s/iter. Inference: 0.1684 s/iter. Eval: 0.0137 s/iter. Total: 0.1853 s/iter. ETA=0:03:52 [04/17 14:11:10 d2.evaluation.evaluator]: Inference done 177/1406. Dataloading: 0.0029 s/iter. Inference: 0.1684 s/iter. Eval: 0.0134 s/iter. Total: 0.1849 s/iter. ETA=0:03:47 [04/17 14:11:15 d2.evaluation.evaluator]: Inference done 206/1406. Dataloading: 0.0030 s/iter. Inference: 0.1680 s/iter. Eval: 0.0127 s/iter. Total: 0.1838 s/iter. ETA=0:03:40 [04/17 14:11:20 d2.evaluation.evaluator]: Inference done 234/1406. Dataloading: 0.0032 s/iter. Inference: 0.1676 s/iter. Eval: 0.0125 s/iter. Total: 0.1835 s/iter. ETA=0:03:35 [04/17 14:11:25 d2.evaluation.evaluator]: Inference done 261/1406. Dataloading: 0.0031 s/iter. Inference: 0.1682 s/iter. Eval: 0.0124 s/iter. Total: 0.1838 s/iter. ETA=0:03:30 [04/17 14:11:30 d2.evaluation.evaluator]: Inference done 288/1406. Dataloading: 0.0031 s/iter. Inference: 0.1692 s/iter. Eval: 0.0122 s/iter. Total: 0.1846 s/iter. ETA=0:03:26 [04/17 14:11:35 d2.evaluation.evaluator]: Inference done 315/1406. Dataloading: 0.0030 s/iter. Inference: 0.1694 s/iter. Eval: 0.0121 s/iter. Total: 0.1846 s/iter. ETA=0:03:21 [04/17 14:11:40 d2.evaluation.evaluator]: Inference done 342/1406. Dataloading: 0.0030 s/iter. Inference: 0.1698 s/iter. Eval: 0.0121 s/iter. Total: 0.1850 s/iter. ETA=0:03:16 [04/17 14:11:46 d2.evaluation.evaluator]: Inference done 370/1406. Dataloading: 0.0030 s/iter. Inference: 0.1696 s/iter. Eval: 0.0118 s/iter. Total: 0.1846 s/iter. ETA=0:03:11 [04/17 14:11:51 d2.evaluation.evaluator]: Inference done 396/1406. Dataloading: 0.0030 s/iter. Inference: 0.1704 s/iter. Eval: 0.0117 s/iter. Total: 0.1852 s/iter. ETA=0:03:07 [04/17 14:11:56 d2.evaluation.evaluator]: Inference done 423/1406. Dataloading: 0.0029 s/iter. Inference: 0.1707 s/iter. Eval: 0.0118 s/iter. Total: 0.1856 s/iter. ETA=0:03:02 [04/17 14:12:01 d2.evaluation.evaluator]: Inference done 450/1406. Dataloading: 0.0030 s/iter. Inference: 0.1708 s/iter. Eval: 0.0120 s/iter. Total: 0.1859 s/iter. ETA=0:02:57 [04/17 14:12:06 d2.evaluation.evaluator]: Inference done 476/1406. Dataloading: 0.0029 s/iter. Inference: 0.1713 s/iter. Eval: 0.0120 s/iter. Total: 0.1863 s/iter. ETA=0:02:53 [04/17 14:12:11 d2.evaluation.evaluator]: Inference done 501/1406. Dataloading: 0.0029 s/iter. Inference: 0.1721 s/iter. Eval: 0.0119 s/iter. Total: 0.1871 s/iter. ETA=0:02:49 [04/17 14:12:16 d2.evaluation.evaluator]: Inference done 528/1406. Dataloading: 0.0030 s/iter. Inference: 0.1720 s/iter. Eval: 0.0120 s/iter. Total: 0.1871 s/iter. ETA=0:02:44 [04/17 14:12:21 d2.evaluation.evaluator]: Inference done 555/1406. Dataloading: 0.0030 s/iter. Inference: 0.1721 s/iter. Eval: 0.0121 s/iter. Total: 0.1873 s/iter. ETA=0:02:39 [04/17 14:12:26 d2.evaluation.evaluator]: Inference done 581/1406. Dataloading: 0.0031 s/iter. Inference: 0.1722 s/iter. Eval: 0.0123 s/iter. Total: 0.1876 s/iter. ETA=0:02:34 [04/17 14:12:31 d2.evaluation.evaluator]: Inference done 607/1406. Dataloading: 0.0031 s/iter. Inference: 0.1725 s/iter. Eval: 0.0123 s/iter. Total: 0.1880 s/iter. ETA=0:02:30 [04/17 14:12:36 d2.evaluation.evaluator]: Inference done 633/1406. Dataloading: 0.0031 s/iter. Inference: 0.1728 s/iter. Eval: 0.0122 s/iter. Total: 0.1882 s/iter. ETA=0:02:25 [04/17 14:12:41 d2.evaluation.evaluator]: Inference done 658/1406. Dataloading: 0.0031 s/iter. Inference: 0.1733 s/iter. Eval: 0.0123 s/iter. Total: 0.1888 s/iter. ETA=0:02:21 [04/17 14:12:47 d2.evaluation.evaluator]: Inference done 684/1406. Dataloading: 0.0031 s/iter. Inference: 0.1736 s/iter. Eval: 0.0123 s/iter. Total: 0.1891 s/iter. ETA=0:02:16 [04/17 14:12:52 d2.evaluation.evaluator]: Inference done 710/1406. Dataloading: 0.0031 s/iter. Inference: 0.1738 s/iter. Eval: 0.0124 s/iter. Total: 0.1894 s/iter. ETA=0:02:11 [04/17 14:12:57 d2.evaluation.evaluator]: Inference done 736/1406. Dataloading: 0.0031 s/iter. Inference: 0.1740 s/iter. Eval: 0.0124 s/iter. Total: 0.1897 s/iter. ETA=0:02:07 [04/17 14:13:02 d2.evaluation.evaluator]: Inference done 762/1406. Dataloading: 0.0031 s/iter. Inference: 0.1742 s/iter. Eval: 0.0124 s/iter. Total: 0.1898 s/iter. ETA=0:02:02 [04/17 14:13:07 d2.evaluation.evaluator]: Inference done 787/1406. Dataloading: 0.0031 s/iter. Inference: 0.1743 s/iter. Eval: 0.0126 s/iter. Total: 0.1902 s/iter. ETA=0:01:57 [04/17 14:13:12 d2.evaluation.evaluator]: Inference done 813/1406. Dataloading: 0.0031 s/iter. Inference: 0.1746 s/iter. Eval: 0.0126 s/iter. Total: 0.1904 s/iter. ETA=0:01:52 [04/17 14:13:17 d2.evaluation.evaluator]: Inference done 839/1406. Dataloading: 0.0031 s/iter. Inference: 0.1748 s/iter. Eval: 0.0125 s/iter. Total: 0.1905 s/iter. ETA=0:01:48 [04/17 14:13:22 d2.evaluation.evaluator]: Inference done 865/1406. Dataloading: 0.0031 s/iter. Inference: 0.1750 s/iter. Eval: 0.0125 s/iter. Total: 0.1907 s/iter. ETA=0:01:43 [04/17 14:13:27 d2.evaluation.evaluator]: Inference done 891/1406. Dataloading: 0.0031 s/iter. Inference: 0.1754 s/iter. Eval: 0.0124 s/iter. Total: 0.1910 s/iter. ETA=0:01:38 [04/17 14:13:32 d2.evaluation.evaluator]: Inference done 918/1406. Dataloading: 0.0031 s/iter. Inference: 0.1755 s/iter. Eval: 0.0123 s/iter. Total: 0.1910 s/iter. ETA=0:01:33 [04/17 14:13:37 d2.evaluation.evaluator]: Inference done 943/1406. Dataloading: 0.0030 s/iter. Inference: 0.1759 s/iter. Eval: 0.0121 s/iter. Total: 0.1912 s/iter. ETA=0:01:28 [04/17 14:13:43 d2.evaluation.evaluator]: Inference done 969/1406. Dataloading: 0.0030 s/iter. Inference: 0.1762 s/iter. Eval: 0.0121 s/iter. Total: 0.1914 s/iter. ETA=0:01:23 [04/17 14:13:48 d2.evaluation.evaluator]: Inference done 995/1406. Dataloading: 0.0030 s/iter. Inference: 0.1763 s/iter. Eval: 0.0121 s/iter. Total: 0.1915 s/iter. ETA=0:01:18 [04/17 14:13:53 d2.evaluation.evaluator]: Inference done 1021/1406. Dataloading: 0.0030 s/iter. Inference: 0.1763 s/iter. Eval: 0.0121 s/iter. Total: 0.1916 s/iter. ETA=0:01:13 [04/17 14:13:58 d2.evaluation.evaluator]: Inference done 1047/1406. Dataloading: 0.0031 s/iter. Inference: 0.1765 s/iter. Eval: 0.0120 s/iter. Total: 0.1917 s/iter. ETA=0:01:08 [04/17 14:14:03 d2.evaluation.evaluator]: Inference done 1073/1406. Dataloading: 0.0031 s/iter. Inference: 0.1766 s/iter. Eval: 0.0120 s/iter. Total: 0.1918 s/iter. ETA=0:01:03 [04/17 14:14:08 d2.evaluation.evaluator]: Inference done 1099/1406. Dataloading: 0.0031 s/iter. Inference: 0.1767 s/iter. Eval: 0.0120 s/iter. Total: 0.1919 s/iter. ETA=0:00:58 [04/17 14:14:13 d2.evaluation.evaluator]: Inference done 1125/1406. Dataloading: 0.0031 s/iter. Inference: 0.1768 s/iter. Eval: 0.0120 s/iter. Total: 0.1919 s/iter. ETA=0:00:53 [04/17 14:14:18 d2.evaluation.evaluator]: Inference done 1151/1406. Dataloading: 0.0031 s/iter. Inference: 0.1768 s/iter. Eval: 0.0120 s/iter. Total: 0.1920 s/iter. ETA=0:00:48 [04/17 14:14:23 d2.evaluation.evaluator]: Inference done 1177/1406. Dataloading: 0.0031 s/iter. Inference: 0.1769 s/iter. Eval: 0.0119 s/iter. Total: 0.1920 s/iter. ETA=0:00:43 [04/17 14:14:28 d2.evaluation.evaluator]: Inference done 1203/1406. Dataloading: 0.0031 s/iter. Inference: 0.1769 s/iter. Eval: 0.0120 s/iter. Total: 0.1921 s/iter. ETA=0:00:39 [04/17 14:14:33 d2.evaluation.evaluator]: Inference done 1228/1406. Dataloading: 0.0031 s/iter. Inference: 0.1770 s/iter. Eval: 0.0121 s/iter. Total: 0.1923 s/iter. ETA=0:00:34 [04/17 14:14:38 d2.evaluation.evaluator]: Inference done 1254/1406. Dataloading: 0.0031 s/iter. Inference: 0.1769 s/iter. Eval: 0.0122 s/iter. Total: 0.1924 s/iter. ETA=0:00:29 [04/17 14:14:43 d2.evaluation.evaluator]: Inference done 1279/1406. Dataloading: 0.0032 s/iter. Inference: 0.1770 s/iter. Eval: 0.0123 s/iter. Total: 0.1926 s/iter. ETA=0:00:24 [04/17 14:14:48 d2.evaluation.evaluator]: Inference done 1305/1406. Dataloading: 0.0031 s/iter. Inference: 0.1769 s/iter. Eval: 0.0124 s/iter. Total: 0.1926 s/iter. ETA=0:00:19 [04/17 14:14:54 d2.evaluation.evaluator]: Inference done 1331/1406. Dataloading: 0.0031 s/iter. Inference: 0.1770 s/iter. Eval: 0.0124 s/iter. Total: 0.1926 s/iter. ETA=0:00:14 [04/17 14:14:59 d2.evaluation.evaluator]: Inference done 1357/1406. Dataloading: 0.0031 s/iter. Inference: 0.1769 s/iter. Eval: 0.0126 s/iter. Total: 0.1927 s/iter. ETA=0:00:09 [04/17 14:15:04 d2.evaluation.evaluator]: Inference done 1385/1406. Dataloading: 0.0031 s/iter. Inference: 0.1767 s/iter. Eval: 0.0125 s/iter. Total: 0.1924 s/iter. ETA=0:00:04 [04/17 14:15:08 d2.evaluation.evaluator]: Total inference time: 0:04:29.845715 (0.192609 s / iter per device, on 8 devices) [04/17 14:15:08 d2.evaluation.evaluator]: Total inference pure compute time: 0:04:07 (0.176466 s / iter per device, on 8 devices) [04/17 14:15:17 d2.evaluation.coco_evaluation]: Preparing results for COCO format ... [04/17 14:15:17 d2.evaluation.coco_evaluation]: Saving results to /mnt/localdata/users/yupanhuang/models/layoutlmv3/fts/publaynet-base/inference/coco_instances_results.json [04/17 14:15:18 d2.evaluation.coco_evaluation]: Evaluating predictions with unofficial COCO API... Loading and preparing results... DONE (t=0.12s) creating index... index created! [04/17 14:15:19 d2.evaluation.fast_eval_api]: Evaluate annotation type *bbox* [04/17 14:15:22 d2.evaluation.fast_eval_api]: COCOeval_opt.evaluate() finished in 3.39 seconds. [04/17 14:15:22 d2.evaluation.fast_eval_api]: Accumulating evaluation results... [04/17 14:15:23 d2.evaluation.fast_eval_api]: COCOeval_opt.accumulate() finished in 0.40 seconds. Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.951 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.981 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.969 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.468 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.856 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.976 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.543 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.953 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.964 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.607 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.897 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.986 [04/17 14:15:23 d2.evaluation.coco_evaluation]: Evaluation results for bbox: | AP | AP50 | AP75 | APs | APm | APl | |:------:|:------:|:------:|:------:|:------:|:------:| | 95.088 | 98.066 | 96.933 | 46.800 | 85.592 | 97.626 | [04/17 14:15:23 d2.evaluation.coco_evaluation]: Per-category bbox AP: | category | AP | category | AP | category | AP | |:-----------|:-------|:-----------|:-------|:-----------|:-------| | text | 94.466 | title | 90.569 | list | 95.522 | | table | 97.883 | figure | 97.001 | | | Loading and preparing results... DONE (t=2.05s) creating index... index created! [04/17 14:15:28 d2.evaluation.fast_eval_api]: Evaluate annotation type *segm* [04/17 14:15:38 d2.evaluation.fast_eval_api]: COCOeval_opt.evaluate() finished in 10.92 seconds. [04/17 14:15:39 d2.evaluation.fast_eval_api]: Accumulating evaluation results... [04/17 14:15:39 d2.evaluation.fast_eval_api]: COCOeval_opt.accumulate() finished in 0.43 seconds. Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.928 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.981 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.967 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.506 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.824 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.959 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.535 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.938 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.949 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.632 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.879 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.973 [04/17 14:15:39 d2.evaluation.coco_evaluation]: Evaluation results for segm: | AP | AP50 | AP75 | APs | APm | APl | |:------:|:------:|:------:|:------:|:------:|:------:| | 92.819 | 98.070 | 96.719 | 50.628 | 82.397 | 95.917 | [04/17 14:15:39 d2.evaluation.coco_evaluation]: Per-category segm AP: | category | AP | category | AP | category | AP | |:-----------|:-------|:-----------|:-------|:-----------|:-------| | text | 93.433 | title | 87.009 | list | 88.864 | | table | 97.799 | figure | 96.989 | | | [04/17 14:15:40 d2.evaluation.testing]: copypaste: Task: bbox [04/17 14:15:40 d2.evaluation.testing]: copypaste: AP,AP50,AP75,APs,APm,APl [04/17 14:15:40 d2.evaluation.testing]: copypaste: 95.0883,98.0662,96.9331,46.8005,85.5919,97.6258 [04/17 14:15:40 d2.evaluation.testing]: copypaste: Task: segm [04/17 14:15:40 d2.evaluation.testing]: copypaste: AP,AP50,AP75,APs,APm,APl [04/17 14:15:40 d2.evaluation.testing]: copypaste: 92.8187,98.0704,96.7191,50.6278,82.3972,95.9172 Process finished with exit code 0