Result verification failed!

Revist commented 3 years ago

Hi, I install pre-build detectron2 from commit 4841e70 then I run tests that are supplied:

./dev/run_inference_tests.sh

At the end I get the message that the "Result verification failed!", nevertheless numbers seem close. Is this a serious error, what I can do about it?

Full logs


========================================================================
Configs to run:
./configs/quick_schedules/cascade_mask_rcnn_R_50_FPN_inference_acc_test.yaml ./configs/quick_schedules/fast_rcnn_R_50_FPN_inference_acc_test.yaml ./configs/quick_schedules/keypoint_rcnn_R_50_FPN_inference_acc_test.yaml ./configs/quick_schedules/mask_rcnn_R_50_C4_inference_acc_test.yaml ./configs/quick_schedules/mask_rcnn_R_50_DC5_inference_acc_test.yaml ./configs/quick_schedules/mask_rcnn_R_50_FPN_inference_acc_test.yaml ./configs/quick_schedules/panoptic_fpn_R_50_inference_acc_test.yaml ./configs/quick_schedules/retinanet_R_50_FPN_inference_acc_test.yaml ./configs/quick_schedules/rpn_R_50_FPN_inference_acc_test.yaml ./configs/quick_schedules/semantic_R_50_FPN_inference_acc_test.yaml
========================================================================
========================================================================
Running ./configs/quick_schedules/cascade_mask_rcnn_R_50_FPN_inference_acc_test.yaml ...
========================================================================
** fvcore version of PathManager will be deprecated soon. **
** Please migrate to the version in iopath repo. **
https://github.com/facebookresearch/iopath

fvcore version of PathManager will be deprecated soon. Please migrate to the version in iopath repo. https://github.com/facebookresearch/iopath

Command Line Args: Namespace(config_file='./configs/quick_schedules/cascade_mask_rcnn_R_50_FPN_inference_acc_test.yaml', dist_url='tcp://127.0.0.1:50155', eval_only=True, machine_rank=0, num_gpus=2, num_machines=1, opts=['OUTPUT_DIR', 'inference_test_output'], resume=False) fvcore version of PathManager will be deprecated soon. Please migrate to the version in iopath repo. https://github.com/facebookresearch/iopath

fvcore version of PathManager will be deprecated soon. Please migrate to the version in iopath repo. https://github.com/facebookresearch/iopath

[02/17 20:32:21 detectron2]: Rank of current process: 0. World size: 2 [02/17 20:32:22 detectron2]: Environment info:

sys.platform linux Python 3.7.9 (default, Aug 31 2020, 12:42:55) [GCC 7.3.0] numpy 1.19.2 detectron2 0.3 @/disk1/cea/fja_detectron2_env/lib/python3.7/site-packages/detectron2 Compiler GCC 7.3 CUDA compiler CUDA 11.0 detectron2 arch flags 3.7, 5.0, 5.2, 6.0, 6.1, 7.0, 7.5, 8.0 DETECTRON2_ENV_MODULE PyTorch 1.7.1 @/disk1/cea/fja_detectron2_env/lib/python3.7/site-packages/torch PyTorch debug build False GPU available True GPU 0,1 Tesla V100-PCIE-16GB (arch=7.0) CUDA_HOME /usr/local/cuda Pillow 8.1.0 torchvision 0.8.2 @/disk1/cea/fja_detectron2_env/lib/python3.7/site-packages/torchvision torchvision arch flags 3.5, 5.0, 6.0, 7.0, 7.5, 8.0 fvcore 0.1.3.post20210213 cv2 3.4.2

PyTorch built with:

GCC 7.3
C++ Version: 201402
Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
OpenMP 201511 (a.k.a. OpenMP 4.5)
NNPACK is enabled
CPU capability usage: AVX2
CUDA Runtime 11.0
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_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_37,code=compute_37
CuDNN 8.0.5
Magma 2.5.2
Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -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, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=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,

[02/17 20:32:22 detectron2]: Command line arguments: Namespace(config_file='./configs/quick_schedules/cascade_mask_rcnn_R_50_FPN_inference_acc_test.yaml', dist_url='tcp://127.0.0.1:50155', eval_only=True, machine_rank=0, num_gpus=2, num_machines=1, opts=['OUTPUT_DIR', 'inference_test_output'], resume=False) [02/17 20:32:22 detectron2]: Contents of args.config_file=./configs/quick_schedules/cascade_mask_rcnn_R_50_FPN_inference_acc_test.yaml: BASE: "../Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml" MODEL: WEIGHTS: "detectron2://Misc/cascade_mask_rcnn_R_50_FPN_3x/144998488/model_final_480dd8.pkl" DATASETS: TEST: ("coco_2017_val_100",) TEST: EXPECTED_RESULTS: [["bbox", "AP", 50.18, 0.02], ["segm", "AP", 43.87, 0.02]]

[02/17 20:32:22 detectron2]: 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: ('coco_2017_val_100',) TRAIN: ('coco_2017_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: 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: 80 POSITIVE_FRACTION: 0.25 PROPOSAL_APPEND_GT: True SCORE_THRESH_TEST: 0.05 ROI_KEYPOINT_HEAD: CONV_DIMS: (512, 512, 512, 512, 512, 512, 512, 512) LOSS_WEIGHT: 1.0 MIN_KEYPOINTS_PER_IMAGE: 1 NAME: KRCNNConvDeconvUpsampleHead NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: True NUM_KEYPOINTS: 17 POOLER_RESOLUTION: 14 POOLER_SAMPLING_RATIO: 0 POOLER_TYPE: ROIAlignV2 ROI_MASK_HEAD: CLS_AGNOSTIC_MASK: False CONV_DIM: 256 NAME: MaskRCNNConvUpsampleHead NORM: NUM_CONV: 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: 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 WEIGHTS: detectron2://Misc/cascade_mask_rcnn_R_50_FPN_3x/144998488/model_final_480dd8.pkl OUTPUT_DIR: inference_test_output SEED: -1 SOLVER: AMP: ENABLED: False BASE_LR: 0.02 BIAS_LR_FACTOR: 1.0 CHECKPOINT_PERIOD: 5000 CLIP_GRADIENTS: CLIP_TYPE: value CLIP_VALUE: 1.0 ENABLED: False NORM_TYPE: 2.0 GAMMA: 0.1 IMS_PER_BATCH: 16 LR_SCHEDULER_NAME: WarmupMultiStepLR MAX_ITER: 270000 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: [['bbox', 'AP', 50.18, 0.02], ['segm', 'AP', 43.87, 0.02]] KEYPOINT_OKS_SIGMAS: [] PRECISE_BN: ENABLED: False NUM_ITER: 200 VERSION: 2 VIS_PERIOD: 0 [02/17 20:32:22 detectron2]: Full config saved to inference_test_output/config.yaml [02/17 20:32:22 d2.utils.env]: Using a generated random seed 22294976

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): CascadeROIHeads( (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): ModuleList( (0): 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() ) (1): 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() ) (2): 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): ModuleList( (0): FastRCNNOutputLayers( (cls_score): Linear(in_features=1024, out_features=81, bias=True) (bbox_pred): Linear(in_features=1024, out_features=4, bias=True) ) (1): FastRCNNOutputLayers( (cls_score): Linear(in_features=1024, out_features=81, bias=True) (bbox_pred): Linear(in_features=1024, out_features=4, bias=True) ) (2): FastRCNNOutputLayers( (cls_score): Linear(in_features=1024, out_features=81, bias=True) (bbox_pred): Linear(in_features=1024, out_features=4, 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, 80, kernel_size=(1, 1), stride=(1, 1)) ) ) ) [02/17 20:32:23 fvcore.common.checkpoint]: Loading checkpoint from detectron2://Misc/cascade_mask_rcnn_R_50_FPN_3x/144998488/model_final_480dd8.pkl [02/17 20:32:23 fvcore.common.checkpoint]: Reading a file from 'Detectron2 Model Zoo' [02/17 20:32:23 d2.data.datasets.coco]: Loaded 100 images in COCO format from /disk1/fja/datasets/coco/annotations/instances_val2017_100.json [02/17 20:32:23 d2.data.build]: Distribution of instances among all 80 categories:	category	#instances	category	#instances	category
person	341	bicycle	10	car	51
motorcycle	23	airplane	0	bus	10
train	2	truck	4	boat	13
traffic light	9	fire hydrant	5	stop sign	1
parking meter	0	bench	14	bird	13
cat	2	dog	4	horse	5
sheep	0	cow	1	elephant	3
bear	6	zebra	16	giraffe	2
backpack	8	umbrella	8	handbag	12
tie	11	suitcase	0	frisbee	9
skis	8	snowboard	1	sports ball	4
kite	19	baseball bat	2	baseball gl..	1
skateboard	1	surfboard	3	tennis racket	9
bottle	16	wine glass	5	cup	15
fork	2	knife	0	spoon	1
bowl	7	banana	1	apple	2
sandwich	2	orange	0	broccoli	9
carrot	4	hot dog	0	pizza	4
donut	7	cake	0	chair	47
couch	8	potted plant	1	bed	2
dining table	17	toilet	2	tv	3
laptop	3	mouse	3	remote	4
keyboard	2	cell phone	8	microwave	1
oven	2	toaster	0	sink	2
refrigerator	1	book	19	clock	3
vase	5	scissors	0	teddy bear	2
hair drier	0	toothbrush	0
total	841

[02/17 20:32:23 d2.data.dataset_mapper]: [DatasetMapper] Augmentations used in inference: [ResizeShortestEdge(short_edge_length=(800, 800), max_size=1333, sample_style='choice')] [02/17 20:32:23 d2.data.common]: Serializing 100 elements to byte tensors and concatenating them all ... [02/17 20:32:23 d2.data.common]: Serialized dataset takes 0.46 MiB WARNING [02/17 20:32:23 d2.evaluation.coco_evaluation]: COCO Evaluator instantiated using config, this is deprecated behavior. Please pass tasks in directly [02/17 20:32:23 d2.evaluation.evaluator]: Start inference on 50 images fvcore version of PathManager will be deprecated soon. Please migrate to the version in iopath repo. https://github.com/facebookresearch/iopath

fvcore version of PathManager will be deprecated soon. Please migrate to the version in iopath repo. https://github.com/facebookresearch/iopath

/disk1/cea/fja_detectron2_env/lib/python3.7/site-packages/detectron2/modeling/roi_heads/fast_rcnn.py:124: UserWarning: This overload of nonzero is deprecated: nonzero() Consider using one of the following signatures instead: nonzero(, bool as_tuple) (Triggered internally at /opt/conda/conda-bld/pytorch_1607370156314/work/torch/csrc/utils/python_arg_parser.cpp:882.) filter_inds = filter_mask.nonzero() /disk1/cea/fja_detectron2_env/lib/python3.7/site-packages/detectron2/modeling/roi_heads/fast_rcnn.py:124: UserWarning: This overload of nonzero is deprecated: nonzero() Consider using one of the following signatures instead: nonzero(, bool as_tuple) (Triggered internally at /opt/conda/conda-bld/pytorch_1607370156314/work/torch/csrc/utils/python_arg_parser.cpp:882.) filter_inds = filter_mask.nonzero() [02/17 20:32:29 d2.evaluation.evaluator]: Inference done 11/50. 0.0526 s / img. ETA=0:00:02 [02/17 20:32:32 d2.evaluation.evaluator]: Total inference time: 0:00:03.364090 (0.074758 s / img per device, on 2 devices) [02/17 20:32:32 d2.evaluation.evaluator]: Total inference pure compute time: 0:00:02 (0.054453 s / img per device, on 2 devices) [02/17 20:32:32 d2.evaluation.coco_evaluation]: Preparing results for COCO format ... [02/17 20:32:32 d2.evaluation.coco_evaluation]: Saving results to inference_test_output/inference/coco_instances_results.json [02/17 20:32:32 d2.evaluation.coco_evaluation]: Evaluating predictions with unofficial COCO API... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type bbox COCOeval_opt.evaluate() finished in 0.10 seconds. Accumulating evaluation results... COCOeval_opt.accumulate() finished in 0.15 seconds. Average Precision (AP) @[ IoU=0.50:0.95	area= all	maxDets=100 ] = 0.499 Average Precision (AP) @[ IoU=0.50	area= all	maxDets=100 ] = 0.659 Average Precision (AP) @[ IoU=0.75	area= all	maxDets=100 ] = 0.526 Average Precision (AP) @[ IoU=0.50:0.95	area= small	maxDets=100 ] = 0.303 Average Precision (AP) @[ IoU=0.50:0.95	area=medium	maxDets=100 ] = 0.505 Average Precision (AP) @[ IoU=0.50:0.95	area= large	maxDets=100 ] = 0.681 Average Recall (AR) @[ IoU=0.50:0.95	area= all	maxDets= 1 ] = 0.397 Average Recall (AR) @[ IoU=0.50:0.95	area= all	maxDets= 10 ] = 0.588 Average Recall (AR) @[ IoU=0.50:0.95	area= all	maxDets=100 ] = 0.609 Average Recall (AR) @[ IoU=0.50:0.95	area= small	maxDets=100 ] = 0.387 Average Recall (AR) @[ IoU=0.50:0.95	area=medium	maxDets=100 ] = 0.605 Average Recall (AR) @[ IoU=0.50:0.95	area= large	maxDets=100 ] = 0.772 [02/17 20:32:32 d2.evaluation.coco_evaluation]: Evaluation results for bbox:	AP	AP50	AP75	APs	APm	APl
49.920	65.888	52.609	30.324	50.519	68.067

[02/17 20:32:32 d2.evaluation.coco_evaluation]: Per-category bbox AP:	category	AP	category	AP	category
person	60.942	bicycle	30.363	car	48.143
motorcycle	47.479	airplane	nan	bus	68.329
train	92.525	truck	22.606	boat	32.373
traffic light	7.905	fire hydrant	60.726	stop sign	22.500
parking meter	nan	bench	53.690	bird	46.648
cat	80.198	dog	23.168	horse	81.628
sheep	nan	cow	30.000	elephant	91.122
bear	65.842	zebra	67.720	giraffe	100.000
backpack	35.645	umbrella	57.483	handbag	36.216
tie	31.249	suitcase	nan	frisbee	51.706
skis	49.841	snowboard	10.000	sports ball	69.307
kite	67.857	baseball bat	30.149	baseball glove	90.000
skateboard	50.000	surfboard	31.023	tennis racket	23.317
bottle	23.160	wine glass	62.822	cup	38.350
fork	22.723	knife	nan	spoon	0.000
bowl	1.357	banana	100.000	apple	85.050
sandwich	75.050	orange	nan	broccoli	42.580
carrot	16.825	hot dog	nan	pizza	36.881
donut	40.495	cake	nan	chair	35.481
couch	44.054	potted plant	45.000	bed	63.696
dining table	30.057	toilet	65.347	tv	83.366
laptop	93.267	mouse	48.119	remote	20.842
keyboard	65.248	cell phone	16.395	microwave	100.000
oven	50.495	toaster	nan	sink	45.446
refrigerator	100.000	book	28.410	clock	33.564
vase	17.755	scissors	nan	teddy bear	95.050
hair drier	nan	toothbrush	nan

Loading and preparing results... DONE (t=0.03s) creating index... index created! Running per image evaluation... Evaluate annotation type segm COCOeval_opt.evaluate() finished in 0.15 seconds. Accumulating evaluation results... COCOeval_opt.accumulate() finished in 0.15 seconds. Average Precision (AP) @[ IoU=0.50:0.95	area= all	maxDets=100 ] = 0.439 Average Precision (AP) @[ IoU=0.50	area= all	maxDets=100 ] = 0.630 Average Precision (AP) @[ IoU=0.75	area= all	maxDets=100 ] = 0.451 Average Precision (AP) @[ IoU=0.50:0.95	area= small	maxDets=100 ] = 0.244 Average Precision (AP) @[ IoU=0.50:0.95	area=medium	maxDets=100 ] = 0.486 Average Precision (AP) @[ IoU=0.50:0.95	area= large	maxDets=100 ] = 0.614 Average Recall (AR) @[ IoU=0.50:0.95	area= all	maxDets= 1 ] = 0.356 Average Recall (AR) @[ IoU=0.50:0.95	area= all	maxDets= 10 ] = 0.508 Average Recall (AR) @[ IoU=0.50:0.95	area= all	maxDets=100 ] = 0.523 Average Recall (AR) @[ IoU=0.50:0.95	area= small	maxDets=100 ] = 0.312 Average Recall (AR) @[ IoU=0.50:0.95	area=medium	maxDets=100 ] = 0.549 Average Recall (AR) @[ IoU=0.50:0.95	area= large	maxDets=100 ] = 0.673 [02/17 20:32:33 d2.evaluation.coco_evaluation]: Evaluation results for segm:	AP	AP50	AP75	APs	APm	APl
43.892	63.042	45.078	24.402	48.555	61.388

[02/17 20:32:33 d2.evaluation.coco_evaluation]: Per-category segm AP:	category	AP	category	AP	category
person	49.552	bicycle	14.158	car	41.887
motorcycle	35.845	airplane	nan	bus	65.695
train	90.000	truck	17.702	boat	37.726
traffic light	8.717	fire hydrant	57.343	stop sign	22.500
parking meter	nan	bench	36.640	bird	40.181
cat	45.347	dog	20.594	horse	77.189
sheep	nan	cow	0.000	elephant	69.901
bear	59.228	zebra	55.520	giraffe	80.000
backpack	20.250	umbrella	61.525	handbag	32.072
tie	21.683	suitcase	nan	frisbee	49.109
skis	15.578	snowboard	0.000	sports ball	71.386
kite	47.841	baseball bat	47.525	baseball glove	90.000
skateboard	20.000	surfboard	10.099	tennis racket	28.243
bottle	22.590	wine glass	69.327	cup	39.779
fork	28.548	knife	nan	spoon	0.000
bowl	1.855	banana	100.000	apple	92.525
sandwich	55.050	orange	nan	broccoli	44.850
carrot	5.919	hot dog	nan	pizza	30.495
donut	43.333	cake	nan	chair	21.731
couch	29.625	potted plant	40.000	bed	58.746
dining table	15.915	toilet	55.347	tv	85.545
laptop	91.683	mouse	54.752	remote	8.911
keyboard	65.248	cell phone	15.084	microwave	100.000
oven	50.495	toaster	nan	sink	45.446
refrigerator	100.000	book	24.853	clock	36.832
vase	14.120	scissors	nan	teddy bear	95.050
hair drier	nan	toothbrush	nan

[02/17 20:32:33 d2.engine.defaults]: Evaluation results for coco_2017_val_100 in csv format: [02/17 20:32:33 d2.evaluation.testing]: copypaste: Task: bbox [02/17 20:32:33 d2.evaluation.testing]: copypaste: AP,AP50,AP75,APs,APm,APl [02/17 20:32:33 d2.evaluation.testing]: copypaste: 49.9204,65.8877,52.6087,30.3239,50.5193,68.0673 [02/17 20:32:33 d2.evaluation.testing]: copypaste: Task: segm [02/17 20:32:33 d2.evaluation.testing]: copypaste: AP,AP50,AP75,APs,APm,APl [02/17 20:32:33 d2.evaluation.testing]: copypaste: 43.8924,63.0419,45.0784,24.4019,48.5554,61.3880 ERROR [02/17 20:32:33 d2.evaluation.testing]: Result verification failed! ERROR [02/17 20:32:33 d2.evaluation.testing]: Expected Results: [['bbox', 'AP', 50.18, 0.02], ['segm', 'AP', 43.87, 0.02]] ERROR [02/17 20:32:33 d2.evaluation.testing]: Actual Results: OrderedDict([('bbox', {'AP': 49.920350939963164, 'AP-airplane': nan, 'AP-apple': 85.04950495049505, 'AP-backpack': 35.64522838838506, 'AP-banana': 100.0, 'AP-baseball bat': 30.148514851485146, 'AP-baseball glove': 90.0, 'AP-bear': 65.84158415841584, 'AP-bed': 63.69636963696369, 'AP-bench': 53.68976897689769, 'AP-bicycle': 30.36303630363036, 'AP-bird': 46.648486826704655, 'AP-boat': 32.37270718022028, 'AP-book': 28.40984335033177, 'AP-bottle': 23.160059802972775, 'AP-bowl': 1.3574778530484624, 'AP-broccoli': 42.58048090523339, 'AP-bus': 68.32940436900833, 'AP-cake': nan, 'AP-car': 48.14264993062022, 'AP-carrot': 16.825064859427115, 'AP-cat': 80.19801980198021, 'AP-cell phone': 16.394874781595806, 'AP-chair': 35.48141572129395, 'AP-clock': 33.56435643564357, 'AP-couch': 44.05382267550063, 'AP-cow': 30.0, 'AP-cup': 38.34999509340605, 'AP-dining table': 30.056930693069305, 'AP-dog': 23.16831683168317, 'AP-donut': 40.4950495049505, 'AP-elephant': 91.12211221122112, 'AP-fire hydrant': 60.72607260726072, 'AP-fork': 22.722772277227723, 'AP-frisbee': 51.706270627062715, 'AP-giraffe': 100.0, 'AP-hair drier': nan, 'AP-handbag': 36.21640228538983, 'AP-horse': 81.62816281628163, 'AP-hot dog': nan, 'AP-keyboard': 65.24752475247524, 'AP-kite': 67.85696297256933, 'AP-knife': nan, 'AP-laptop': 93.26732673267327, 'AP-microwave': 100.0, 'AP-motorcycle': 47.4788905958265, 'AP-mouse': 48.118811881188115, 'AP-orange': nan, 'AP-oven': 50.495049504950494, 'AP-parking meter': nan, 'AP-person': 60.942174903241465, 'AP-pizza': 36.88118811881188, 'AP-potted plant': 45.0, 'AP-refrigerator': 100.0, 'AP-remote': 20.84158415841584, 'AP-sandwich': 75.04950495049505, 'AP-scissors': nan, 'AP-sheep': nan, 'AP-sink': 45.445544554455445, 'AP-skateboard': 50.0, 'AP-skis': 49.840826187881945, 'AP-snowboard': 10.0, 'AP-spoon': 0.0, 'AP-sports ball': 69.30693069306929, 'AP-stop sign': 22.5, 'AP-suitcase': nan, 'AP-surfboard': 31.023102310231028, 'AP-teddy bear': 95.04950495049505, 'AP-tennis racket': 23.316831683168317, 'AP-tie': 31.24920153305653, 'AP-toaster': nan, 'AP-toilet': 65.34653465346535, 'AP-toothbrush': nan, 'AP-traffic light': 7.904950495049505, 'AP-train': 92.52475247524752, 'AP-truck': 22.60587403278143, 'AP-tv': 83.36633663366337, 'AP-umbrella': 57.48349834983498, 'AP-vase': 17.754596888260252, 'AP-wine glass': 62.82178217821782, 'AP-zebra': 67.7198210205636, 'AP50': 65.88766003301699, 'AP75': 52.608677824642214, 'APl': 68.0673159504408, 'APm': 50.51933983719206, 'APs': 30.32386761353462}), ('segm', {'AP': 43.89242383599268, 'AP-airplane': nan, 'AP-apple': 92.52475247524752, 'AP-backpack': 20.250159469728484, 'AP-banana': 100.0, 'AP-baseball bat': 47.524752475247524, 'AP-baseball glove': 90.0, 'AP-bear': 59.22772277227723, 'AP-bed': 58.74587458745874, 'AP-bench': 36.639738973897394, 'AP-bicycle': 14.158415841584157, 'AP-bird': 40.18079280455518, 'AP-boat': 37.72597740543285, 'AP-book': 24.852788190109166, 'AP-bottle': 22.58962587988122, 'AP-bowl': 1.8551328817092232, 'AP-broccoli': 44.84978783592645, 'AP-bus': 65.6954266855257, 'AP-cake': nan, 'AP-car': 41.886982690685244, 'AP-carrot': 5.918886006247684, 'AP-cat': 45.34653465346535, 'AP-cell phone': 15.08363731109953, 'AP-chair': 21.73077102515834, 'AP-clock': 36.83168316831683, 'AP-couch': 29.625176803394627, 'AP-cow': 0.0, 'AP-cup': 39.779037997696484, 'AP-dining table': 15.915120923857087, 'AP-dog': 20.594059405940595, 'AP-donut': 43.333333333333336, 'AP-elephant': 69.9009900990099, 'AP-fire hydrant': 57.343234323432334, 'AP-fork': 28.547854785478542, 'AP-frisbee': 49.10891089108911, 'AP-giraffe': 80.0, 'AP-hair drier': nan, 'AP-handbag': 32.07158319518587, 'AP-horse': 77.18921892189219, 'AP-hot dog': nan, 'AP-keyboard': 65.24752475247524, 'AP-kite': 47.84123636643344, 'AP-knife': nan, 'AP-laptop': 91.68316831683168, 'AP-microwave': 100.0, 'AP-motorcycle': 35.844918503349675, 'AP-mouse': 54.75247524752476, 'AP-orange': nan, 'AP-oven': 50.495049504950494, 'AP-parking meter': nan, 'AP-person': 49.55220687541312, 'AP-pizza': 30.495049504950494, 'AP-potted plant': 40.0, 'AP-refrigerator': 100.0, 'AP-remote': 8.91089108910891, 'AP-sandwich': 55.049504950495056, 'AP-scissors': nan, 'AP-sheep': nan, 'AP-sink': 45.445544554455445, 'AP-skateboard': 20.0, 'AP-skis': 15.577557755775578, 'AP-snowboard': 0.0, 'AP-spoon': 0.0, 'AP-sports ball': 71.38613861386138, 'AP-stop sign': 22.5, 'AP-suitcase': nan, 'AP-surfboard': 10.099009900990099, 'AP-teddy bear': 95.04950495049505, 'AP-tennis racket': 28.24257425742574, 'AP-tie': 21.683168316831683, 'AP-toaster': nan, 'AP-toilet': 55.346534653465355, 'AP-toothbrush': nan, 'AP-traffic light': 8.716831683168316, 'AP-train': 90.0, 'AP-truck': 17.701971877860053, 'AP-tv': 85.54455445544555, 'AP-umbrella': 61.52538715410002, 'AP-vase': 14.11951909476662, 'AP-wine glass': 69.32673267326733, 'AP-zebra': 55.519801980198025, 'AP50': 63.0419077993371, 'AP75': 45.078445807465265, 'APl': 61.387986043486045, 'APm': 48.55535880471486, 'APs': 24.401875736756615})]) Traceback (most recent call last): File "tools/train_net.py", line 169, in args=(args,), File "/disk1/cea/fja_detectron2_env/lib/python3.7/site-packages/detectron2/engine/launch.py", line 59, in launch daemon=False, File "/disk1/cea/fja_detectron2_env/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 199, in spawn return start_processes(fn, args, nprocs, join, daemon, start_method='spawn') File "/disk1/cea/fja_detectron2_env/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 157, in start_processes while not context.join(): File "/disk1/cea/fja_detectron2_env/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 112, in join (error_index, exitcode) Exception: process 0 terminated with exit code 1


## Environment:

sys.platform linux Python 3.7.9 (default, Aug 31 2020, 12:42:55) [GCC 7.3.0] numpy 1.19.2 detectron2 0.3 @/disk1/fja/detectron2/detectron2 detectron2._C failed to import. detectron2 is not built correctly Compiler c++ (GCC) 4.8.5 20150623 (Red Hat 4.8.5-44) CUDA compiler Build cuda_11.1.TC455_06.29190527_0 DETECTRON2_ENV_MODULE PyTorch 1.7.1 @/disk1/cea/fja_detectron2_env/lib/python3.7/site-packages/torch PyTorch debug build False GPU available True GPU 0,1 Tesla V100-PCIE-16GB (arch=7.0) CUDA_HOME /usr/local/cuda Pillow 8.1.0 torchvision 0.8.2 @/disk1/cea/fja_detectron2_env/lib/python3.7/site-packages/torchvision torchvision arch flags 3.5, 5.0, 6.0, 7.0, 7.5, 8.0 fvcore 0.1.3.post20210213 cv2 3.4.2

PyTorch built with:

GCC 7.3
C++ Version: 201402
Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
OpenMP 201511 (a.k.a. OpenMP 4.5)
NNPACK is enabled
CPU capability usage: AVX2
CUDA Runtime 11.0
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_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_37,code=compute_37
CuDNN 8.0.5
Magma 2.5.2
Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -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, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=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,

github-actions[bot] commented 3 years ago

You've chosen to report an unexpected problem or bug. Unless you already know the root cause of it, please include details about it by filling the issue template. The following information is missing: "Instructions To Reproduce the Issue and Full Logs";

ppwwyyxx commented 3 years ago

This is because different versions of libjpeg decodes the jpeg images slightly differently. This is unfortunate but we probably have to live with it, unless there are better ideas.

facebookresearch / detectron2

Result verification failed! #2633