Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

How to Train to Achieve the Result in the Paper #31

Open
zranwang opened this issue Feb 25, 2023 · 7 comments
Open

How to Train to Achieve the Result in the Paper #31

zranwang opened this issue Feb 25, 2023 · 7 comments

Comments

@zranwang
Copy link

I trained the model on the dataset COCO-Standard 10%, but I couldn' t reach the result of AP=35.11 given in the paper, and my best result is as follows, What's wrong with me?（I used the provided configuration file without any modifications.）

AP AP50 AP75 APs APm APl
34.519 53.205 37.222 19.698 37.772 43.981
@ZRandomize
Copy link
Collaborator

hi, please test the Teacher (the EMA model)

@zranwang
Copy link
Author

Yes, I test the Teacher (the EMA model).

@ZRandomize
Copy link
Collaborator

can you offer the full log file?

@zranwang
Copy link
Author

oh, I'm sorry that I can't upload the log file due to personal network environment problems, but I can provide key log information.

@ZRandomize
Copy link
Collaborator

please offer the full config log and the history evaluation results

@zranwang
Copy link
Author

2023-02-23 14:04:54.776 | INFO | cvpods.engine.setup:default_setup:137 - Rank of current process: 0. World size: 8
2023-02-23 14:04:56.191 | INFO | cvpods.engine.setup:default_setup:139 - Environment info:

sys.platform linux
Python 3.8.5 (default, Sep 4 2020, 07:30:14) [GCC 7.3.0]
numpy 1.20.3
cvpods 0.1 @/opt/schedule-train/algorithm/DenseTeacher/cvpods/cvpods
cvpods compiler GCC 7.5
cvpods CUDA compiler 10.1
cvpods arch flags sm_70
cvpods_ENV_MODULE
PyTorch 1.8.1+cu102 @/root/miniconda3/lib/python3.8/site-packages/torch
PyTorch debug build False
CUDA available True
GPU 0,1,2,3,4,5,6,7 Tesla V100-SXM2-32GB
CUDA_HOME /usr/local/cuda
NVCC Cuda compilation tools, release 10.1, V10.1.243
Pillow 6.2.1
torchvision 0.9.1+cu102 @/root/miniconda3/lib/python3.8/site-packages/torchvision
torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75
cv2 4.5.4-dev

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 v1.7.0 (Git Hash 7aed236906b1f7a05c0917e5257a1af05e9ff683)
  • OpenMP 201511 (a.k.a. OpenMP 4.5)
  • NNPACK is enabled
  • CPU capability usage: AVX2
  • CUDA Runtime 10.2
  • 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
    2023-02-23 14:07:00.676 | INFO | mp_main:main:103 - Running with full config:
    ╒�����������������������╤�������������������������������������������������������������������������������������╕
    │ config params │ values │
    ╞�����������������������╪�������������������������������������������������������������������������������������╡
    │ MODEL │ {'ANCHOR_GENERATOR': {'ANGLES': [[-90, 0, 90]], │
    │ │ 'ASPECT_RATIOS': [[0.5, 1.0, 2.0]], │
    │ │ 'OFFSET': 0.0, │
    │ │ 'SIZES': [[32, 64, 128, 256, 512]]}, │
    │ │ 'AS_PRETRAIN': False, │
    │ │ 'BACKBONE': {'FREEZE_AT': 2}, │
    │ │ 'DDP_BACKEND': 'torch', │
    │ │ 'DEVICE': 'cuda', │
    │ │ 'FCOS': {'BBOX_REG_WEIGHTS': [1.0, 1.0, 1.0, 1.0], │
    │ │ 'CENTERNESS_ON_REG': True, │
    │ │ 'CENTER_SAMPLING_RADIUS': 1.5, │
    │ │ 'FOCAL_LOSS_ALPHA': 0.25, │
    │ │ 'FOCAL_LOSS_GAMMA': 2.0, │
    │ │ 'FPN_STRIDES': [8, 16, 32, 64, 128], │
    │ │ 'IN_FEATURES': ['p3', 'p4', 'p5', 'p6', 'p7'], │
    │ │ 'IOU_LOSS_TYPE': 'giou', │
    │ │ 'NMS_THRESH_TEST': 0.6, │
    │ │ 'NORM_REG_TARGETS': True, │
    │ │ 'NORM_SYNC': True, │
    │ │ 'NUM_CLASSES': 80, │
    │ │ 'NUM_CONVS': 4, │
    │ │ 'OBJECT_SIZES_OF_INTEREST': [[-1, 64], │
    │ │ [64, 128], │
    │ │ [128, 256], │
    │ │ [256, 512], │
    │ │ [512, inf]], │
    │ │ 'PRIOR_PROB': 0.01, │
    │ │ 'QUALITY_BRANCH': 'iou', │
    │ │ 'SCORE_THRESH_TEST': 0.05, │
    │ │ 'TOPK_CANDIDATES_TEST': 1000}, │
    │ │ 'FPN': {'BLOCK_IN_FEATURES': 'p5', │
    │ │ 'FUSE_TYPE': 'sum', │
    │ │ 'IN_FEATURES': ['res3', 'res4', 'res5'], │
    │ │ 'NORM': '', │
    │ │ 'OUT_CHANNELS': 256}, │
    │ │ 'KEYPOINT_ON': False, │
    │ │ 'LOAD_PROPOSALS': False, │
    │ │ 'MASK_ON': False, │
    │ │ 'NMS_TYPE': 'normal', │
    │ │ 'PIXEL_MEAN': [103.53, 116.28, 123.675], │
    │ │ 'PIXEL_STD': [1.0, 1.0, 1.0], │
    │ │ 'RESNETS': {'ACTIVATION': {'INPLACE': True, 'NAME': 'ReLU'}, │
    │ │ 'DEEP_STEM': False, │
    │ │ 'DEPTH': 50, │
    │ │ 'NORM': 'FrozenBN', │
    │ │ 'NUM_CLASSES': None, │
    │ │ 'NUM_GROUPS': 1, │
    │ │ 'OUT_FEATURES': ['res3', 'res4', 'res5'], │
    │ │ 'RES2_OUT_CHANNELS': 256, │
    │ │ 'RES5_DILATION': 1, │
    │ │ 'STEM_OUT_CHANNELS': 64, │
    │ │ 'STRIDE_IN_1X1': True, │
    │ │ 'WIDTH_PER_GROUP': 64, │
    │ │ 'ZERO_INIT_RESIDUAL': False}, │
    │ │ 'SHIFT_GENERATOR': {'NUM_SHIFTS': 1, 'OFFSET': 0.0}, │
    │ │ 'WEIGHTS': '../checkpoints/R-50.pkl'} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ INPUT │ {'AUG': {'TEST_PIPELINES': [('ResizeShortestEdge', │
    │ │ {'max_size': 1333, │
    │ │ 'sample_style': 'choice', │
    │ │ 'short_edge_length': 800})], │
    │ │ 'TRAIN_PIPELINES': {'SUPERVISED': [<class 'augmentations.WeakAug'>, │
    │ │ {'max_size': 1333, │
    │ │ 'sample_style': 'choice', │
    │ │ 'short_edge_length': [640, │
    │ │ 672, │
    │ │ 704, │
    │ │ 736, │
    │ │ 768, │
    │ │ 800]}], │
    │ │ 'UNSUPERVISED': [<class 'augmentations.StrongAug'>]}}, │
    │ │ 'FORMAT': 'BGR', │
    │ │ 'MASK_FORMAT': 'polygon'} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ DATASETS │ {'CUSTOM_TYPE': ['ConcatDataset', {}], │
    │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TEST': 1000, │
    │ │ 'PRECOMPUTED_PROPOSAL_TOPK_TRAIN': 2000, │
    │ │ 'PROPOSAL_FILES_TEST': [], │
    │ │ 'PROPOSAL_FILES_TRAIN': [], │
    │ │ 'SUPERVISED': [(<class 'dataset.PartialCOCO'>, │
    │ │ {'percentage': 10, │
    │ │ 'seed': 1, │
    │ │ 'sup_file': '../COCO_Division/COCO_supervision.txt', │
    │ │ 'supervised': True})], │
    │ │ 'TEST': ['coco_2017_val'], │
    │ │ 'TRAIN': [], │
    │ │ 'UNSUPERVISED': [(<class 'dataset.PartialCOCO'>, │
    │ │ {'percentage': 10, │
    │ │ 'seed': 1, │
    │ │ 'sup_file': '../COCO_Division/COCO_supervision.txt', │
    │ │ 'supervised': False})]} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ DATALOADER │ {'ASPECT_RATIO_GROUPING': True, │
    │ │ 'ENABLE_INF_SAMPLER': True, │
    │ │ 'FILTER_EMPTY_ANNOTATIONS': True, │
    │ │ 'NUM_WORKERS': 4, │
    │ │ 'REPEAT_THRESHOLD': 0.0, │
    │ │ 'SAMPLER_TRAIN': 'DistributedGroupSampler'} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ TRAINER │ {'DISTILL': {'GAMMA': 2.0, │
    │ │ 'RATIO': 0.01, │
    │ │ 'SUPPRESS': 'linear', │
    │ │ 'SUP_WEIGHT': 1, │
    │ │ 'UNSUP_WEIGHT': 1, │
    │ │ 'WEIGHTS': {'DELTAS': 1.0, 'LOGITS': 4.0, 'QUALITY': 1.0}}, │
    │ │ 'EMA': {'DECAY_FACTOR': 0.9996, │
    │ │ 'FAKE': False, │
    │ │ 'START_STEPS': 3000, │
    │ │ 'UPDATE_STEPS': 1}, │
    │ │ 'FP16': {'ENABLED': False, 'OPTS': {'OPT_LEVEL': 'O1'}, 'TYPE': 'APEX'}, │
    │ │ 'NAME': 'SemiRunner', │
    │ │ 'SSL': {'BURN_IN_STEPS': 5000}, │
    │ │ 'WINDOW_SIZE': 20} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ SOLVER │ {'BATCH_SUBDIVISIONS': 1, │
    │ │ 'CHECKPOINT_PERIOD': 5000, │
    │ │ 'CLIP_GRADIENTS': {'CLIP_TYPE': 'value', │
    │ │ 'CLIP_VALUE': 1.0, │
    │ │ 'ENABLED': True, │
    │ │ 'NORM_TYPE': 2.0}, │
    │ │ 'IMS_PER_BATCH': 16, │
    │ │ 'IMS_PER_DEVICE': 2, │
    │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, │
    │ │ 'GAMMA': 0.1, │
    │ │ 'MAX_EPOCH': None, │
    │ │ 'MAX_ITER': 180000, │
    │ │ 'NAME': 'WarmupMultiStepLR', │
    │ │ 'STEPS': [179995], │
    │ │ 'WARMUP_FACTOR': 0.001, │
    │ │ 'WARMUP_ITERS': 1000, │
    │ │ 'WARMUP_METHOD': 'linear'}, │
    │ │ 'OPTIMIZER': {'BASE_LR': 0.01, │
    │ │ 'BIAS_LR_FACTOR': 1.0, │
    │ │ 'MOMENTUM': 0.9, │
    │ │ 'NAME': 'D2SGD', │
    │ │ 'WEIGHT_DECAY': 0.0001, │
    │ │ 'WEIGHT_DECAY_NORM': 0.0}} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ TEST │ {'AUG': {'ENABLED': False, │
    │ │ 'EXTRA_SIZES': [], │
    │ │ 'FLIP': True, │
    │ │ 'MAX_SIZE': 4000, │
    │ │ 'MIN_SIZES': [400, 500, 600, 700, 800, 900, 1000, 1100, 1200], │
    │ │ 'SCALE_FILTER': False, │
    │ │ 'SCALE_RANGES': []}, │
    │ │ 'DETECTIONS_PER_IMAGE': 100, │
    │ │ 'EVAL_PERIOD': 2000, │
    │ │ 'EXPECTED_RESULTS': [], │
    │ │ 'KEYPOINT_OKS_SIGMAS': [], │
    │ │ 'ON_FILES': False, │
    │ │ 'PRECISE_BN': {'ENABLED': False, 'NUM_ITER': 200}} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ OUTPUT_DIR │ 'outputs' │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ SEED │ 56207473 │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ CUDNN_BENCHMARK │ False │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ VIS_PERIOD │ 0 │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ GLOBAL │ {'CLEARML': {'ENABLE': False, │
    │ │ 'OUTPUT_URI': None, │
    │ │ 'PROJECT_NAME': 'cvpods', │
    │ │ 'TAGS': None, │
    │ │ 'TASK_NAME': None}, │
    │ │ 'DUMP_TEST': False, │
    │ │ 'DUMP_TRAIN': True, │
    │ │ 'HACK': 1.0, │
    │ │ 'LOG_INTERVAL': 10} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ build_backbone │ <function build_backbone at 0x7fabbfebbc10> │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ build_shift_generator │ <function build_shift_generator at 0x7fabbfe61670> │
    ╘�����������������������╧�������������������������������������������������������������������������������������╛
    2023-02-23 14:07:00.681 | INFO | mp_main:main:105 - different config with base class:
    ╒�����������������������╤�������������������������������������������������������������������������������������╕
    │ config params │ values │
    ╞�����������������������╪�������������������������������������������������������������������������������������╡
    │ MODEL │ {'FCOS': {'CENTERNESS_ON_REG': True, │
    │ │ 'CENTER_SAMPLING_RADIUS': 1.5, │
    │ │ 'IOU_LOSS_TYPE': 'giou', │
    │ │ 'NORM_REG_TARGETS': True, │
    │ │ 'QUALITY_BRANCH': 'iou'}, │
    │ │ 'RESNETS': {'DEPTH': 50}, │
    │ │ 'WEIGHTS': '../checkpoints/R-50.pkl'} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ INPUT │ {'AUG': {'TRAIN_PIPELINES': {'SUPERVISED': [<class 'augmentations.WeakAug'>, │
    │ │ {'max_size': 1333, │
    │ │ 'sample_style': 'choice', │
    │ │ 'short_edge_length': [640, │
    │ │ 672, │
    │ │ 704, │
    │ │ 736, │
    │ │ 768, │
    │ │ 800]}], │
    │ │ 'UNSUPERVISED': [<class 'augmentations.StrongAug'>]}}} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ DATASETS │ {'SUPERVISED': [(<class 'dataset.PartialCOCO'>, │
    │ │ {'percentage': 10, │
    │ │ 'seed': 1, │
    │ │ 'sup_file': '../COCO_Division/COCO_supervision.txt', │
    │ │ 'supervised': True})], │
    │ │ 'TEST': ['coco_2017_val'], │
    │ │ 'UNSUPERVISED': [(<class 'dataset.PartialCOCO'>, │
    │ │ {'percentage': 10, │
    │ │ 'seed': 1, │
    │ │ 'sup_file': '../COCO_Division/COCO_supervision.txt', │
    │ │ 'supervised': False})]} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ DATALOADER │ {'NUM_WORKERS': 4} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ TRAINER │ {'DISTILL': {'GAMMA': 2.0, │
    │ │ 'RATIO': 0.01, │
    │ │ 'SUPPRESS': 'linear', │
    │ │ 'SUP_WEIGHT': 1, │
    │ │ 'UNSUP_WEIGHT': 1, │
    │ │ 'WEIGHTS': {'DELTAS': 1.0, 'LOGITS': 4.0, 'QUALITY': 1.0}}, │
    │ │ 'EMA': {'DECAY_FACTOR': 0.9996, │
    │ │ 'FAKE': False, │
    │ │ 'START_STEPS': 3000, │
    │ │ 'UPDATE_STEPS': 1}, │
    │ │ 'NAME': 'SemiRunner', │
    │ │ 'SSL': {'BURN_IN_STEPS': 5000}} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ SOLVER │ {'CLIP_GRADIENTS': {'ENABLED': True}, │
    │ │ 'LR_SCHEDULER': {'EPOCH_ITERS': -1, 'MAX_ITER': 180000, 'STEPS': [179995]}, │
    │ │ 'OPTIMIZER': {'BASE_LR': 0.01}} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ TEST │ {'EVAL_PERIOD': 2000} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ OUTPUT_DIR │ 'outputs' │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ SEED │ 56207473 │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ GLOBAL │ {'LOG_INTERVAL': 10} │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ build_backbone │ <function build_backbone at 0x7fabbfebbc10> │
    ├───────────────────────┼─────────────────────────────────────────────────────────────────────────────────────┤
    │ build_shift_generator │ <function build_shift_generator at 0x7fabbfe61670> │
    ╘�����������������������╧�������������������������������������������������������������������������������������╛

2023-02-23 14:19:33.378 | INFO | runner:test_and_save_ema_results:142 - Evaluating: EMA
2023-02-23 14:20:37.690 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
0.000 0.000 0.000 0.000 0.000 0.000

2023-02-23 14:34:23.947 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
17.519 31.243 17.486 8.981 20.410 23.056

2023-02-23 14:53:15.495 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
20.719 35.841 21.095 10.592 23.742 26.901

2023-02-23 15:17:09.620 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
22.681 38.523 23.571 11.876 25.539 29.117

2023-02-23 15:41:01.502 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
23.959 40.206 24.961 12.610 27.005 30.500

2023-02-23 16:04:28.905 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
24.967 41.445 26.272 13.852 27.989 31.627

2023-02-23 16:27:54.270 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
25.880 42.690 27.194 13.831 29.113 32.653

2023-02-23 16:51:29.613 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
26.663 43.757 28.180 14.608 29.767 33.601

2023-02-23 17:15:03.982 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
27.422 44.594 29.118 14.842 30.525 34.651

2023-02-23 17:38:58.236 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
28.142 45.514 29.917 15.210 31.289 35.643

2023-02-23 18:02:59.018 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
28.692 46.328 30.475 15.547 31.845 36.326

2023-02-23 18:27:27.747 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
29.225 46.963 31.042 15.726 32.296 37.019

2023-02-23 18:51:41.811 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
29.664 47.515 31.669 16.029 32.638 37.726

2023-02-23 19:15:57.196 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
30.092 48.097 32.150 16.291 32.987 38.301

2023-02-23 19:39:54.444 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
30.441 48.555 32.316 16.635 33.361 38.694

2023-02-23 20:04:04.683 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
30.756 49.027 32.760 17.047 33.672 39.122

2023-02-23 20:27:52.081 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
31.104 49.398 33.281 17.557 34.050 39.554

2023-02-23 20:51:49.600 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
31.396 49.785 33.518 17.729 34.464 39.925

2023-02-23 21:15:56.587 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
31.678 49.921 33.937 17.919 34.726 40.141

2023-02-23 21:39:52.919 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
31.897 50.245 34.039 18.103 34.806 40.311

2023-02-23 22:04:28.469 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
32.076 50.414 34.277 18.208 35.037 41.123

2023-02-23 22:28:55.524 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
32.269 50.685 34.489 18.222 35.330 41.314

2023-02-23 22:53:39.985 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
32.391 50.935 34.510 17.865 35.604 41.475

2023-02-23 23:18:08.452 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
32.563 51.018 34.698 17.965 35.806 41.568

2023-02-23 23:42:54.143 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
32.659 51.209 34.868 18.033 35.870 41.774

2023-02-24 00:07:03.809 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
32.807 51.369 35.025 18.068 36.146 41.949

2023-02-24 00:31:32.331 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
32.967 51.481 35.284 18.508 36.345 42.181

2023-02-24 00:56:06.253 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.058 51.570 35.385 18.587 36.356 42.325

2023-02-24 01:20:59.358 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.115 51.664 35.527 18.628 36.338 42.524

2023-02-24 01:46:03.849 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.182 51.703 35.440 18.541 36.519 42.593

2023-02-24 02:11:14.076 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.230 51.697 35.541 18.385 36.535 42.874

2023-02-24 02:36:30.175 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.384 51.872 35.888 18.755 36.450 43.061

2023-02-24 03:01:32.966 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.427 51.842 36.080 18.691 36.501 43.103

2023-02-24 03:26:20.745 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.555 52.031 36.231 18.604 36.718 42.944

2023-02-24 03:51:07.817 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.626 52.172 36.110 18.538 36.901 42.437

2023-02-24 04:16:18.605 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.677 52.143 36.208 18.589 36.805 42.723

2023-02-24 04:41:23.969 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.684 52.191 36.119 18.745 37.007 42.800

2023-02-24 05:06:58.397 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.837 52.379 36.174 18.503 37.169 43.079

2023-02-24 05:32:25.041 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.883 52.296 36.214 18.702 37.156 43.052

2023-02-24 05:58:01.350 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.852 52.366 36.213 18.545 37.128 42.995

2023-02-24 06:23:22.724 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.835 52.352 36.284 18.428 37.115 42.898

2023-02-24 06:48:38.466 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.874 52.451 36.313 18.609 37.221 43.084

2023-02-24 07:13:59.622 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
33.944 52.475 36.498 18.900 37.218 42.887

2023-02-24 07:39:22.376 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.031 52.583 36.702 18.876 37.380 42.979

2023-02-24 08:04:55.782 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.127 52.679 36.715 18.709 37.538 43.158

2023-02-24 08:30:21.470 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.133 52.758 36.760 18.801 37.642 43.290

2023-02-24 08:56:13.877 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.097 52.724 36.629 18.696 37.543 43.393

2023-02-24 09:21:58.501 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.169 52.766 36.659 18.651 37.633 43.511

2023-02-24 09:47:52.513 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.199 52.782 36.763 18.561 37.582 43.459

2023-02-24 10:13:13.087 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.238 52.715 36.905 18.676 37.549 43.583

2023-02-24 10:38:41.427 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.311 52.721 36.971 18.821 37.578 43.628

2023-02-24 11:04:22.560 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.340 52.751 36.990 18.749 37.593 43.587

2023-02-24 11:30:02.377 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.361 52.772 37.189 18.889 37.783 43.441

2023-02-24 11:55:43.074 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.313 52.709 37.199 18.808 37.685 43.663

2023-02-24 12:21:53.472 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.359 52.772 37.162 18.547 37.665 43.692

2023-02-24 12:47:47.723 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.420 52.843 37.185 18.589 37.759 43.791

2023-02-24 13:14:05.629 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.371 52.977 37.007 18.629 37.608 43.955

2023-02-24 13:39:56.353 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.401 53.004 37.024 18.780 37.665 44.060

2023-02-24 14:05:48.075 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.413 53.091 36.836 18.801 37.482 43.936

2023-02-24 14:31:55.191 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.435 53.056 36.790 18.738 37.705 43.746

2023-02-24 14:57:56.404 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.509 53.098 36.902 19.063 37.668 43.719

2023-02-24 15:24:13.663 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.432 53.071 36.720 19.079 37.649 43.657

2023-02-24 15:50:41.306 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.346 52.928 36.778 19.076 37.623 43.722

2023-02-24 16:16:56.762 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.459 52.994 36.945 19.261 37.887 43.645

2023-02-24 16:43:07.267 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.447 53.021 37.085 19.535 37.857 43.336

2023-02-24 17:09:30.098 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.449 52.980 36.989 19.467 37.750 43.562

2023-02-24 17:35:31.747 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.440 53.055 37.087 19.629 37.774 43.662

2023-02-24 18:02:00.564 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.519 53.205 37.222 19.698 37.772 43.981

2023-02-24 18:28:40.685 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.545 53.247 37.217 19.433 37.776 43.942

2023-02-24 18:55:17.708 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.448 53.053 36.976 19.301 37.662 44.103

2023-02-24 19:22:26.150 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.502 53.094 36.950 19.186 37.550 43.889

2023-02-24 19:48:52.466 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.563 53.160 37.071 19.202 37.659 43.877

2023-02-24 20:15:32.536 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.474 53.151 36.814 19.481 37.600 44.219

2023-02-24 20:41:49.933 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.464 53.021 36.848 19.157 37.554 44.351

2023-02-24 21:08:26.357 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.484 53.022 36.852 19.111 37.687 44.071

2023-02-24 21:35:10.100 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.459 53.060 36.835 19.105 37.768 43.927

2023-02-24 22:01:58.302 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.549 53.128 36.971 19.246 37.902 44.075

2023-02-24 22:29:16.758 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.535 53.033 36.944 19.750 37.899 43.908

2023-02-24 22:56:17.983 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.626 53.253 36.829 19.652 37.905 44.143

2023-02-24 23:23:30.047 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.589 53.208 36.844 19.299 37.993 44.278

2023-02-24 23:50:25.424 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.639 53.163 37.059 19.445 37.785 44.304

2023-02-25 00:17:14.893 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.647 53.267 36.925 19.285 37.847 44.336

2023-02-25 00:44:30.016 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.657 53.215 36.989 19.186 37.945 44.671

2023-02-25 01:11:41.911 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.634 53.192 36.892 19.090 37.858 44.612

2023-02-25 01:39:18.500 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.707 53.252 36.978 19.116 37.876 44.509

2023-02-25 02:07:05.581 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.736 53.175 37.031 19.048 37.988 44.237

2023-02-25 02:34:58.286 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.717 53.146 37.095 19.043 37.993 44.245

2023-02-25 03:02:41.780 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.773 53.188 37.138 19.352 37.971 44.231

2023-02-25 03:30:14.178 | INFO | cvpods.evaluation.coco_evaluation:_derive_coco_results:318 - Evaluation results for bbox:

AP AP50 AP75 APs APm APl
34.759 53.284 37.155 19.369 38.029 44.326

@ZRandomize
Copy link
Collaborator

Seems like nothing goes wrong. This might be caused by different GPU (2080ti & V100) or random states.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@zranwang @ZRandomize