Upload 12 files

work_dir_h/PWOOD/dotav2/10p/best_0.310266_mAP.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb5e610426cb6f0a6f89f21e5b7719973354f2926bc9359a7dc523c85b83949
+size 513600538

work_dir_h/PWOOD/dotav2/20250305_073819.log

@@ -0,0 +1,661 @@
+2025-03-05 07:38:19,997 - mmrotate - INFO - Environment info:
+------------------------------------------------------------
+sys.platform: linux
+Python: 3.8.0 (default, Nov  6 2019, 21:49:08) [GCC 7.3.0]
+CUDA available: True
+GPU 0,1: NVIDIA GeForce RTX 3090
+CUDA_HOME: /usr/local/cuda-11.0
+NVCC: Cuda compilation tools, release 11.0, V11.0.221
+GCC: gcc (GCC) 8.5.0 20210514 (Red Hat 8.5.0-4)
+PyTorch: 1.13.1+cu116
+PyTorch compiling details: PyTorch built with:
+  - GCC 9.3
+  - 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 v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
+  - OpenMP 201511 (a.k.a. OpenMP 4.5)
+  - LAPACK is enabled (usually provided by MKL)
+  - NNPACK is enabled
+  - CPU capability usage: AVX2
+  - CUDA Runtime 11.6
+  - 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 8.3.2  (built against CUDA 11.5)
+  - Magma 2.6.1
+  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.6, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -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 -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, 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, USE_ROCM=OFF, 
+
+TorchVision: 0.14.1+cu116
+OpenCV: 4.11.0
+MMCV: 1.7.2
+MMCV Compiler: GCC 9.3
+MMCV CUDA Compiler: 11.6
+MMRotate: 0.3.4+7833b87
+------------------------------------------------------------
+
+2025-03-05 07:38:20,864 - mmrotate - INFO - Distributed training: True
+2025-03-05 07:38:21,843 - mmrotate - INFO - Config:
+angle_version = 'le90'
+detector = dict(
+    type='SemiRotatedFCOS',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        zero_init_residual=False,
+        norm_cfg=dict(type='BN', requires_grad=True),
+        norm_eval=True,
+        style='pytorch',
+        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
+    neck=dict(
+        type='FPN',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        start_level=1,
+        add_extra_convs='on_output',
+        num_outs=5,
+        relu_before_extra_convs=True),
+    bbox_head=dict(
+        type='SemiRotatedFCOSHeadH2RV2MCL',
+        num_classes=18,
+        in_channels=256,
+        stacked_convs=4,
+        feat_channels=256,
+        strides=[8, 16, 32, 64, 128],
+        center_sampling=True,
+        center_sample_radius=1.5,
+        norm_on_bbox=True,
+        centerness_on_reg=True,
+        square_cls=[1, 9, 11],
+        resize_cls=[1],
+        scale_angle=False,
+        bbox_coder=dict(type='DistanceAnglePointCoder', angle_version='le90'),
+        loss_cls=dict(
+            type='FocalLoss',
+            use_sigmoid=True,
+            gamma=2.0,
+            alpha=0.25,
+            loss_weight=1.0),
+        loss_bbox=dict(type='IoULoss', loss_weight=1.0),
+        loss_centerness=dict(
+            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+        loss_ss_symmetry=dict(type='SmoothL1Loss', loss_weight=0.2, beta=0.1)),
+    train_cfg=None,
+    test_cfg=dict(
+        nms_pre=2000,
+        min_bbox_size=0,
+        score_thr=0.05,
+        nms=dict(iou_thr=0.1),
+        max_per_img=2000))
+model = dict(
+    type='H2RV2MCLTeacher',
+    model=dict(
+        type='SemiRotatedFCOS',
+        backbone=dict(
+            type='ResNet',
+            depth=50,
+            num_stages=4,
+            out_indices=(0, 1, 2, 3),
+            frozen_stages=1,
+            zero_init_residual=False,
+            norm_cfg=dict(type='BN', requires_grad=True),
+            norm_eval=True,
+            style='pytorch',
+            init_cfg=dict(
+                type='Pretrained', checkpoint='torchvision://resnet50')),
+        neck=dict(
+            type='FPN',
+            in_channels=[256, 512, 1024, 2048],
+            out_channels=256,
+            start_level=1,
+            add_extra_convs='on_output',
+            num_outs=5,
+            relu_before_extra_convs=True),
+        bbox_head=dict(
+            type='SemiRotatedFCOSHeadH2RV2MCL',
+            num_classes=18,
+            in_channels=256,
+            stacked_convs=4,
+            feat_channels=256,
+            strides=[8, 16, 32, 64, 128],
+            center_sampling=True,
+            center_sample_radius=1.5,
+            norm_on_bbox=True,
+            centerness_on_reg=True,
+            square_cls=[1, 9, 11],
+            resize_cls=[1],
+            scale_angle=False,
+            bbox_coder=dict(
+                type='DistanceAnglePointCoder', angle_version='le90'),
+            loss_cls=dict(
+                type='FocalLoss',
+                use_sigmoid=True,
+                gamma=2.0,
+                alpha=0.25,
+                loss_weight=1.0),
+            loss_bbox=dict(type='IoULoss', loss_weight=1.0),
+            loss_centerness=dict(
+                type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+            loss_ss_symmetry=dict(
+                type='SmoothL1Loss', loss_weight=0.2, beta=0.1)),
+        train_cfg=None,
+        test_cfg=dict(
+            nms_pre=2000,
+            min_bbox_size=0,
+            score_thr=0.05,
+            nms=dict(iou_thr=0.1),
+            max_per_img=2000)),
+    semi_loss=dict(type='SemiGMMLoss', cls_channels=18, policy='high'),
+    train_cfg=dict(
+        iter_count=0,
+        burn_in_steps=12800,
+        sup_weight=1.0,
+        unsup_weight=1.0,
+        weight_suppress='exp',
+        logit_specific_weights=dict(),
+        cls_channels=18),
+    test_cfg=dict(inference_on='teacher'))
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+common_pipeline = [
+    dict(
+        type='Normalize',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        to_rgb=True),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(
+        type='Collect',
+        keys=['img', 'gt_bboxes', 'gt_labels'],
+        meta_keys=('filename', 'ori_filename', 'ori_shape', 'img_shape',
+                   'pad_shape', 'scale_factor', 'flip', 'flip_direction',
+                   'img_norm_cfg', 'tag'))
+]
+strong_pipeline = [
+    dict(type='DTToPILImage'),
+    dict(
+        type='DTRandomApply',
+        operations=[
+            ColorJitter(
+                brightness=[0.6, 1.4],
+                contrast=[0.6, 1.4],
+                saturation=[0.6, 1.4],
+                hue=[-0.1, 0.1])
+        ],
+        p=0.8),
+    dict(type='DTRandomGrayscale', p=0.2),
+    dict(
+        type='DTRandomApply',
+        operations=[dict(type='DTGaussianBlur', rad_range=[0.1, 2.0])]),
+    dict(type='DTToNumpy'),
+    dict(type='ExtraAttrs', tag='unsup_strong')
+]
+weak_pipeline = [
+    dict(type='RResize', img_scale=(1024, 1024)),
+    dict(
+        type='RRandomFlip',
+        flip_ratio=[0.25, 0.25, 0.25],
+        direction=['horizontal', 'vertical', 'diagonal'],
+        version='le90'),
+    dict(type='ExtraAttrs', tag='unsup_weak')
+]
+unsup_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadEmptyAnnotations', with_bbox=True),
+    dict(
+        type='STMultiBranch',
+        unsup_strong=[
+            dict(type='DTToPILImage'),
+            dict(
+                type='DTRandomApply',
+                operations=[
+                    ColorJitter(
+                        brightness=[0.6, 1.4],
+                        contrast=[0.6, 1.4],
+                        saturation=[0.6, 1.4],
+                        hue=[-0.1, 0.1])
+                ],
+                p=0.8),
+            dict(type='DTRandomGrayscale', p=0.2),
+            dict(
+                type='DTRandomApply',
+                operations=[dict(type='DTGaussianBlur', rad_range=[0.1,
+                                                                   2.0])]),
+            dict(type='DTToNumpy'),
+            dict(type='ExtraAttrs', tag='unsup_strong')
+        ],
+        unsup_weak=[
+            dict(type='RResize', img_scale=(1024, 1024)),
+            dict(
+                type='RRandomFlip',
+                flip_ratio=[0.25, 0.25, 0.25],
+                direction=['horizontal', 'vertical', 'diagonal'],
+                version='le90'),
+            dict(type='ExtraAttrs', tag='unsup_weak')
+        ],
+        common_pipeline=[
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=32),
+            dict(type='DefaultFormatBundle'),
+            dict(
+                type='Collect',
+                keys=['img', 'gt_bboxes', 'gt_labels'],
+                meta_keys=('filename', 'ori_filename', 'ori_shape',
+                           'img_shape', 'pad_shape', 'scale_factor', 'flip',
+                           'flip_direction', 'img_norm_cfg', 'tag'))
+        ],
+        is_seq=True)
+]
+sup_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='RResize', img_scale=(1024, 1024)),
+    dict(
+        type='RRandomFlip',
+        flip_ratio=[0.25, 0.25, 0.25],
+        direction=['horizontal', 'vertical', 'diagonal'],
+        version='le90'),
+    dict(type='ExtraAttrs', tag='sup_weak'),
+    dict(
+        type='Normalize',
+        mean=[123.675, 116.28, 103.53],
+        std=[58.395, 57.12, 57.375],
+        to_rgb=True),
+    dict(type='Pad', size_divisor=32),
+    dict(type='DefaultFormatBundle'),
+    dict(
+        type='Collect',
+        keys=['img', 'gt_bboxes', 'gt_labels'],
+        meta_keys=('filename', 'ori_filename', 'ori_shape', 'img_shape',
+                   'pad_shape', 'scale_factor', 'flip', 'flip_direction',
+                   'img_norm_cfg', 'tag'))
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiScaleFlipAug',
+        img_scale=(1024, 1024),
+        flip=False,
+        transforms=[
+            dict(type='RResize'),
+            dict(
+                type='Normalize',
+                mean=[123.675, 116.28, 103.53],
+                std=[58.395, 57.12, 57.375],
+                to_rgb=True),
+            dict(type='Pad', size_divisor=32),
+            dict(type='DefaultFormatBundle'),
+            dict(type='Collect', keys=['img'])
+        ])
+]
+dataset_type = 'DOTAv2WSOODDataset'
+classes = ('plane', 'baseball-diamond', 'bridge', 'ground-track-field',
+           'small-vehicle', 'large-vehicle', 'ship', 'tennis-court',
+           'basketball-court', 'storage-tank', 'soccer-ball-field',
+           'roundabout', 'harbor', 'swimming-pool', 'helicopter',
+           'container-crane', 'airport', 'helipad')
+data = dict(
+    samples_per_gpu=3,
+    workers_per_gpu=5,
+    train=dict(
+        type='SemiDataset',
+        sup=dict(
+            type='DOTAv2WSOODDataset',
+            pipeline=[
+                dict(type='LoadImageFromFile'),
+                dict(type='LoadAnnotations', with_bbox=True),
+                dict(type='RResize', img_scale=(1024, 1024)),
+                dict(
+                    type='RRandomFlip',
+                    flip_ratio=[0.25, 0.25, 0.25],
+                    direction=['horizontal', 'vertical', 'diagonal'],
+                    version='le90'),
+                dict(type='ExtraAttrs', tag='sup_weak'),
+                dict(
+                    type='Normalize',
+                    mean=[123.675, 116.28, 103.53],
+                    std=[58.395, 57.12, 57.375],
+                    to_rgb=True),
+                dict(type='Pad', size_divisor=32),
+                dict(type='DefaultFormatBundle'),
+                dict(
+                    type='Collect',
+                    keys=['img', 'gt_bboxes', 'gt_labels'],
+                    meta_keys=('filename', 'ori_filename', 'ori_shape',
+                               'img_shape', 'pad_shape', 'scale_factor',
+                               'flip', 'flip_direction', 'img_norm_cfg',
+                               'tag'))
+            ],
+            ann_file='dotav2/train_20p_labeled/annfiles/',
+            img_prefix='dotav2/train_20p_labeled/images/',
+            version='le90',
+            classes=('plane', 'baseball-diamond', 'bridge',
+                     'ground-track-field', 'small-vehicle', 'large-vehicle',
+                     'ship', 'tennis-court', 'basketball-court',
+                     'storage-tank', 'soccer-ball-field', 'roundabout',
+                     'harbor', 'swimming-pool', 'helicopter',
+                     'container-crane', 'airport', 'helipad')),
+        unsup=dict(
+            type='DOTAv2WSOODDataset',
+            pipeline=[
+                dict(type='LoadImageFromFile'),
+                dict(type='LoadEmptyAnnotations', with_bbox=True),
+                dict(
+                    type='STMultiBranch',
+                    unsup_strong=[
+                        dict(type='DTToPILImage'),
+                        dict(
+                            type='DTRandomApply',
+                            operations=[
+                                ColorJitter(
+                                    brightness=[0.6, 1.4],
+                                    contrast=[0.6, 1.4],
+                                    saturation=[0.6, 1.4],
+                                    hue=[-0.1, 0.1])
+                            ],
+                            p=0.8),
+                        dict(type='DTRandomGrayscale', p=0.2),
+                        dict(
+                            type='DTRandomApply',
+                            operations=[
+                                dict(
+                                    type='DTGaussianBlur',
+                                    rad_range=[0.1, 2.0])
+                            ]),
+                        dict(type='DTToNumpy'),
+                        dict(type='ExtraAttrs', tag='unsup_strong')
+                    ],
+                    unsup_weak=[
+                        dict(type='RResize', img_scale=(1024, 1024)),
+                        dict(
+                            type='RRandomFlip',
+                            flip_ratio=[0.25, 0.25, 0.25],
+                            direction=['horizontal', 'vertical', 'diagonal'],
+                            version='le90'),
+                        dict(type='ExtraAttrs', tag='unsup_weak')
+                    ],
+                    common_pipeline=[
+                        dict(
+                            type='Normalize',
+                            mean=[123.675, 116.28, 103.53],
+                            std=[58.395, 57.12, 57.375],
+                            to_rgb=True),
+                        dict(type='Pad', size_divisor=32),
+                        dict(type='DefaultFormatBundle'),
+                        dict(
+                            type='Collect',
+                            keys=['img', 'gt_bboxes', 'gt_labels'],
+                            meta_keys=('filename', 'ori_filename', 'ori_shape',
+                                       'img_shape', 'pad_shape',
+                                       'scale_factor', 'flip',
+                                       'flip_direction', 'img_norm_cfg',
+                                       'tag'))
+                    ],
+                    is_seq=True)
+            ],
+            ann_file='dotav2/train_20p_unlabeled/annfiles/',
+            img_prefix='dotav2/train_20p_unlabeled/images/',
+            version='le90',
+            classes=('plane', 'baseball-diamond', 'bridge',
+                     'ground-track-field', 'small-vehicle', 'large-vehicle',
+                     'ship', 'tennis-court', 'basketball-court',
+                     'storage-tank', 'soccer-ball-field', 'roundabout',
+                     'harbor', 'swimming-pool', 'helicopter',
+                     'container-crane', 'airport', 'helipad'),
+            filter_empty_gt=False)),
+    val=dict(
+        type='DOTAv2WSOODDataset',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1024, 1024),
+                flip=False,
+                transforms=[
+                    dict(type='RResize'),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=32),
+                    dict(type='DefaultFormatBundle'),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ],
+        img_prefix='dotav2/val_ss/images/',
+        ann_file='dotav2/val_ss/annfiles/',
+        version='le90',
+        classes=('plane', 'baseball-diamond', 'bridge', 'ground-track-field',
+                 'small-vehicle', 'large-vehicle', 'ship', 'tennis-court',
+                 'basketball-court', 'storage-tank', 'soccer-ball-field',
+                 'roundabout', 'harbor', 'swimming-pool', 'helicopter',
+                 'container-crane', 'airport', 'helipad')),
+    test=dict(
+        type='DOTAv2WSOODDataset',
+        pipeline=[
+            dict(type='LoadImageFromFile'),
+            dict(
+                type='MultiScaleFlipAug',
+                img_scale=(1024, 1024),
+                flip=False,
+                transforms=[
+                    dict(type='RResize'),
+                    dict(
+                        type='Normalize',
+                        mean=[123.675, 116.28, 103.53],
+                        std=[58.395, 57.12, 57.375],
+                        to_rgb=True),
+                    dict(type='Pad', size_divisor=32),
+                    dict(type='DefaultFormatBundle'),
+                    dict(type='Collect', keys=['img'])
+                ])
+        ],
+        img_prefix='dotav2/val/images/',
+        ann_file='dotav2/val/annfiles/',
+        version='le90',
+        classes=('plane', 'baseball-diamond', 'bridge', 'ground-track-field',
+                 'small-vehicle', 'large-vehicle', 'ship', 'tennis-court',
+                 'basketball-court', 'storage-tank', 'soccer-ball-field',
+                 'roundabout', 'harbor', 'swimming-pool', 'helicopter',
+                 'container-crane', 'airport', 'helipad')),
+    sampler=dict(
+        train=dict(type='MultiSourceSampler', sample_ratio=[2, 1], seed=42)))
+custom_hooks = [
+    dict(type='NumClassCheckHook'),
+    dict(type='MeanTeacher', momentum=0.9996, interval=1, start_steps=3200)
+]
+evaluation = dict(
+    type='SubModulesDistEvalHook',
+    interval=3200,
+    metric='mAP',
+    save_best='mAP')
+optimizer = dict(
+    type='AdamW', lr=0.0001, betas=(0.9, 0.999), weight_decay=0.05)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+lr_config = dict(
+    policy='step',
+    warmup='linear',
+    warmup_iters=500,
+    warmup_ratio=0.3333333333333333,
+    step=120000)
+runner = dict(type='IterBasedRunner', max_iters=120000)
+checkpoint_config = dict(by_epoch=False, interval=3200, max_keep_ckpts=1)
+log_config = dict(
+    _delete_=True, interval=50, hooks=[dict(type='TextLoggerHook')])
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+load_from = None
+resume_from = 'work_dir/h2rv2_mcl/dotav2/gmm/iter_51200.pth'
+workflow = [('train', 1)]
+opencv_num_threads = 0
+mp_start_method = 'fork'
+work_dir = 'work_dir/h2rv2_mcl/dotav2/gmm/'
+auto_resume = False
+gpu_ids = range(0, 2)
+
+2025-03-05 07:38:21,843 - mmrotate - INFO - Set random seed to 42, deterministic: True
+2025-03-05 07:38:29,154 - mmrotate - INFO - load checkpoint from local path: work_dir/h2rv2_mcl/dotav2/gmm/iter_51200.pth
+2025-03-05 07:38:29,576 - mmrotate - INFO - resumed from epoch: 1, iter 51199
+2025-03-05 07:38:29,578 - mmrotate - INFO - Start running, host: dzd@localhost.localdomain, work_dir: /ssd1/dzd/sood-mcl/work_dir/h2rv2_mcl/dotav2/gmm
+2025-03-05 07:38:29,578 - mmrotate - INFO - Hooks will be executed in the following order:
+before_run:
+(VERY_HIGH   ) StepLrUpdaterHook                  
+(NORMAL      ) CheckpointHook                     
+(NORMAL      ) MeanTeacher                        
+(LOW         ) SubModulesDistEvalHook             
+(VERY_LOW    ) TextLoggerHook                     
+ -------------------- 
+before_train_epoch:
+(VERY_HIGH   ) StepLrUpdaterHook                  
+(NORMAL      ) NumClassCheckHook                  
+(LOW         ) IterTimerHook                      
+(LOW         ) SubModulesDistEvalHook             
+(VERY_LOW    ) TextLoggerHook                     
+ -------------------- 
+before_train_iter:
+(VERY_HIGH   ) StepLrUpdaterHook                  
+(LOW         ) IterTimerHook                      
+(LOW         ) SubModulesDistEvalHook             
+ -------------------- 
+after_train_iter:
+(ABOVE_NORMAL) OptimizerHook                      
+(NORMAL      ) CheckpointHook                     
+(NORMAL      ) MeanTeacher                        
+(LOW         ) IterTimerHook                      
+(LOW         ) SubModulesDistEvalHook             
+(VERY_LOW    ) TextLoggerHook                     
+ -------------------- 
+after_train_epoch:
+(NORMAL      ) CheckpointHook                     
+(LOW         ) SubModulesDistEvalHook             
+(VERY_LOW    ) TextLoggerHook                     
+ -------------------- 
+before_val_epoch:
+(NORMAL      ) NumClassCheckHook                  
+(LOW         ) IterTimerHook                      
+(VERY_LOW    ) TextLoggerHook                     
+ -------------------- 
+before_val_iter:
+(LOW         ) IterTimerHook                      
+ -------------------- 
+after_val_iter:
+(LOW         ) IterTimerHook                      
+ -------------------- 
+after_val_epoch:
+(VERY_LOW    ) TextLoggerHook                     
+ -------------------- 
+after_run:
+(VERY_LOW    ) TextLoggerHook                     
+ -------------------- 
+2025-03-05 07:38:29,579 - mmrotate - INFO - workflow: [('train', 1)], max: 120000 iters
+2025-03-05 07:38:29,579 - mmrotate - INFO - Checkpoints will be saved to /ssd1/dzd/sood-mcl/work_dir/h2rv2_mcl/dotav2/gmm by HardDiskBackend.
+2025-03-05 07:38:32,511 - mmrotate - INFO - Saving checkpoint at 51200 iterations
+2025-03-05 07:38:33,444 - mmrotate - INFO - Iter [51200/120000]	lr: 1.000e-04, eta: 143 days, 5:57:40, time: 3.598, data_time: 0.365, memory: 6420, loss_cls_sup: 0.0827, loss_bbox_sup: 0.3179, loss_centerness_sup: 0.6017, loss_ss_sup: 0.0106, loss: 1.0129, grad_norm: 1.7567
+2025-03-05 07:39:09,875 - mmrotate - INFO - 
++--------------------+------+-------+--------+-------+
+| class              | gts  | dets  | recall | ap    |
++--------------------+------+-------+--------+-------+
+| plane              | 381  | 1009  | 0.499  | 0.430 |
+| baseball-diamond   | 82   | 964   | 0.927  | 0.663 |
+| bridge             | 103  | 7078  | 0.437  | 0.301 |
+| ground-track-field | 51   | 1159  | 0.980  | 0.795 |
+| small-vehicle      | 9316 | 40227 | 0.571  | 0.474 |
+| large-vehicle      | 336  | 10820 | 0.601  | 0.130 |
+| ship               | 4561 | 10619 | 0.717  | 0.674 |
+| tennis-court       | 24   | 657   | 0.917  | 0.468 |
+| basketball-court   | 5    | 167   | 0.400  | 0.301 |
+| storage-tank       | 298  | 2444  | 0.218  | 0.140 |
+| soccer-ball-field  | 4    | 626   | 0.500  | 0.018 |
+| roundabout         | 51   | 1671  | 0.451  | 0.170 |
+| harbor             | 504  | 2334  | 0.464  | 0.172 |
+| swimming-pool      | 378  | 2503  | 0.463  | 0.313 |
+| helicopter         | 0    | 124   | 0.000  | 0.000 |
+| container-crane    | 0    | 211   | 0.000  | 0.000 |
+| airport            | 102  | 725   | 0.157  | 0.104 |
+| helipad            | 4    | 165   | 0.500  | 0.545 |
++--------------------+------+-------+--------+-------+
+| mAP                |      |       |        | 0.356 |
++--------------------+------+-------+--------+-------+
+2025-03-05 07:39:46,167 - mmrotate - INFO - 
++--------------------+------+-------+--------+-------+
+| class              | gts  | dets  | recall | ap    |
++--------------------+------+-------+--------+-------+
+| plane              | 381  | 620   | 0.451  | 0.412 |
+| baseball-diamond   | 82   | 1032  | 0.939  | 0.658 |
+| bridge             | 103  | 6898  | 0.417  | 0.241 |
+| ground-track-field | 51   | 1215  | 0.922  | 0.768 |
+| small-vehicle      | 9316 | 35522 | 0.562  | 0.474 |
+| large-vehicle      | 336  | 8488  | 0.568  | 0.128 |
+| ship               | 4561 | 12949 | 0.696  | 0.610 |
+| tennis-court       | 24   | 337   | 0.792  | 0.470 |
+| basketball-court   | 5    | 109   | 0.200  | 0.273 |
+| storage-tank       | 298  | 1604  | 0.191  | 0.120 |
+| soccer-ball-field  | 4    | 681   | 0.500  | 0.013 |
+| roundabout         | 51   | 2158  | 0.471  | 0.160 |
+| harbor             | 504  | 2791  | 0.425  | 0.120 |
+| swimming-pool      | 378  | 1023  | 0.347  | 0.259 |
+| helicopter         | 0    | 147   | 0.000  | 0.000 |
+| container-crane    | 0    | 30    | 0.000  | 0.000 |
+| airport            | 102  | 1083  | 0.147  | 0.108 |
+| helipad            | 4    | 142   | 0.500  | 0.545 |
++--------------------+------+-------+--------+-------+
+| mAP                |      |       |        | 0.335 |
++--------------------+------+-------+--------+-------+
+2025-03-05 07:39:46,195 - mmrotate - INFO - Saving best checkpoint to /ssd1/dzd/sood-mcl/work_dir/h2rv2_mcl/dotav2/gmm/best_0.356127_mAP.pth
+2025-03-05 07:39:47,009 - mmrotate - INFO - Iter(val) [51200]	teacher.mAP: 0.3561, student.mAP: 0.3350
+2025-03-05 07:40:09,808 - mmrotate - INFO - Iter [51250/120000]	lr: 1.000e-04, eta: 4 days, 7:26:45, time: 1.927, data_time: 1.484, memory: 7438, loss_cls_sup: 0.0937, loss_bbox_sup: 0.2519, loss_centerness_sup: 0.6064, loss_ss_sup: 0.0074, loss: 0.9593, grad_norm: 1.9347
+2025-03-05 07:40:32,747 - mmrotate - INFO - Iter [51300/120000]	lr: 1.000e-04, eta: 2 days, 8:31:52, time: 0.459, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0976, loss_bbox_sup: 0.2598, loss_centerness_sup: 0.6114, loss_ss_sup: 0.0146, loss: 0.9834, grad_norm: 2.0014
+2025-03-05 07:40:55,477 - mmrotate - INFO - Iter [51350/120000]	lr: 1.000e-04, eta: 1 day, 16:39:17, time: 0.455, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0866, loss_bbox_sup: 0.2341, loss_centerness_sup: 0.6055, loss_ss_sup: 0.0120, loss: 0.9382, grad_norm: 1.9095
+2025-03-05 07:41:18,285 - mmrotate - INFO - Iter [51400/120000]	lr: 1.000e-04, eta: 1 day, 8:40:55, time: 0.456, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0818, loss_bbox_sup: 0.2434, loss_centerness_sup: 0.6105, loss_ss_sup: 0.0116, loss: 0.9474, grad_norm: 1.9568
+2025-03-05 07:41:41,096 - mmrotate - INFO - Iter [51450/120000]	lr: 1.000e-04, eta: 1 day, 3:52:58, time: 0.456, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0851, loss_bbox_sup: 0.2347, loss_centerness_sup: 0.6071, loss_ss_sup: 0.0077, loss: 0.9346, grad_norm: 1.7522
+2025-03-05 07:42:03,911 - mmrotate - INFO - Iter [51500/120000]	lr: 1.000e-04, eta: 1 day, 0:40:35, time: 0.456, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0800, loss_bbox_sup: 0.2200, loss_centerness_sup: 0.6106, loss_ss_sup: 0.0080, loss: 0.9186, grad_norm: 1.6245
+2025-03-05 07:42:26,625 - mmrotate - INFO - Iter [51550/120000]	lr: 1.000e-04, eta: 22:22:35, time: 0.454, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0878, loss_bbox_sup: 0.2264, loss_centerness_sup: 0.6055, loss_ss_sup: 0.0075, loss: 0.9272, grad_norm: 1.8119
+2025-03-05 07:42:49,376 - mmrotate - INFO - Iter [51600/120000]	lr: 1.000e-04, eta: 20:38:59, time: 0.455, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0842, loss_bbox_sup: 0.2410, loss_centerness_sup: 0.6106, loss_ss_sup: 0.0077, loss: 0.9435, grad_norm: 1.8223
+2025-03-05 07:43:12,317 - mmrotate - INFO - Iter [51650/120000]	lr: 1.000e-04, eta: 19:18:46, time: 0.459, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0841, loss_bbox_sup: 0.2332, loss_centerness_sup: 0.6074, loss_ss_sup: 0.0085, loss: 0.9333, grad_norm: 1.8134
+2025-03-05 07:43:35,313 - mmrotate - INFO - Iter [51700/120000]	lr: 1.000e-04, eta: 18:14:37, time: 0.460, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0864, loss_bbox_sup: 0.2476, loss_centerness_sup: 0.6071, loss_ss_sup: 0.0086, loss: 0.9498, grad_norm: 1.8901
+2025-03-05 07:43:58,445 - mmrotate - INFO - Iter [51750/120000]	lr: 1.000e-04, eta: 17:22:18, time: 0.463, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0930, loss_bbox_sup: 0.2551, loss_centerness_sup: 0.6032, loss_ss_sup: 0.0080, loss: 0.9594, grad_norm: 2.1073
+2025-03-05 07:44:21,432 - mmrotate - INFO - Iter [51800/120000]	lr: 1.000e-04, eta: 16:38:22, time: 0.460, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0906, loss_bbox_sup: 0.2467, loss_centerness_sup: 0.6112, loss_ss_sup: 0.0072, loss: 0.9558, grad_norm: 1.7879
+2025-03-05 07:44:44,353 - mmrotate - INFO - Iter [51850/120000]	lr: 1.000e-04, eta: 16:01:00, time: 0.458, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0889, loss_bbox_sup: 0.2311, loss_centerness_sup: 0.6092, loss_ss_sup: 0.0080, loss: 0.9373, grad_norm: 1.7741
+2025-03-05 07:45:07,569 - mmrotate - INFO - Iter [51900/120000]	lr: 1.000e-04, eta: 15:29:23, time: 0.464, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0823, loss_bbox_sup: 0.2432, loss_centerness_sup: 0.6095, loss_ss_sup: 0.0076, loss: 0.9427, grad_norm: 1.7969
+2025-03-05 07:45:30,488 - mmrotate - INFO - Iter [51950/120000]	lr: 1.000e-04, eta: 15:01:29, time: 0.458, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0781, loss_bbox_sup: 0.2286, loss_centerness_sup: 0.6049, loss_ss_sup: 0.0094, loss: 0.9210, grad_norm: 1.8321
+2025-03-05 07:45:53,336 - mmrotate - INFO - Exp name: gmm.py
+2025-03-05 07:45:53,337 - mmrotate - INFO - Iter [52000/120000]	lr: 1.000e-04, eta: 14:36:55, time: 0.457, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0856, loss_bbox_sup: 0.2354, loss_centerness_sup: 0.6092, loss_ss_sup: 0.0087, loss: 0.9390, grad_norm: 1.7688
+2025-03-05 07:46:16,509 - mmrotate - INFO - Iter [52050/120000]	lr: 1.000e-04, eta: 14:15:38, time: 0.463, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0811, loss_bbox_sup: 0.2561, loss_centerness_sup: 0.6088, loss_ss_sup: 0.0068, loss: 0.9528, grad_norm: 1.5830
+2025-03-05 07:46:39,456 - mmrotate - INFO - Iter [52100/120000]	lr: 1.000e-04, eta: 13:56:22, time: 0.459, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0832, loss_bbox_sup: 0.2394, loss_centerness_sup: 0.6088, loss_ss_sup: 0.0064, loss: 0.9378, grad_norm: 1.6897
+2025-03-05 07:47:02,205 - mmrotate - INFO - Iter [52150/120000]	lr: 1.000e-04, eta: 13:38:52, time: 0.455, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0857, loss_bbox_sup: 0.2413, loss_centerness_sup: 0.6070, loss_ss_sup: 0.0071, loss: 0.9411, grad_norm: 2.0620
+2025-03-05 07:47:25,046 - mmrotate - INFO - Iter [52200/120000]	lr: 1.000e-04, eta: 13:23:10, time: 0.457, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0835, loss_bbox_sup: 0.2371, loss_centerness_sup: 0.6098, loss_ss_sup: 0.0076, loss: 0.9381, grad_norm: 2.0063
+2025-03-05 07:47:47,896 - mmrotate - INFO - Iter [52250/120000]	lr: 1.000e-04, eta: 13:08:57, time: 0.457, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0891, loss_bbox_sup: 0.2273, loss_centerness_sup: 0.6060, loss_ss_sup: 0.0073, loss: 0.9297, grad_norm: 1.9709
+2025-03-05 07:48:10,808 - mmrotate - INFO - Iter [52300/120000]	lr: 1.000e-04, eta: 12:56:03, time: 0.458, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0826, loss_bbox_sup: 0.2319, loss_centerness_sup: 0.6069, loss_ss_sup: 0.0068, loss: 0.9282, grad_norm: 1.8392
+2025-03-05 07:48:33,622 - mmrotate - INFO - Iter [52350/120000]	lr: 1.000e-04, eta: 12:44:08, time: 0.456, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0833, loss_bbox_sup: 0.2210, loss_centerness_sup: 0.6060, loss_ss_sup: 0.0087, loss: 0.9190, grad_norm: 1.9357
+2025-03-05 07:48:56,685 - mmrotate - INFO - Iter [52400/120000]	lr: 1.000e-04, eta: 12:33:25, time: 0.461, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0883, loss_bbox_sup: 0.2656, loss_centerness_sup: 0.6085, loss_ss_sup: 0.0095, loss: 0.9719, grad_norm: 1.8582
+2025-03-05 07:49:19,393 - mmrotate - INFO - Iter [52450/120000]	lr: 1.000e-04, eta: 12:23:12, time: 0.454, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0792, loss_bbox_sup: 0.2156, loss_centerness_sup: 0.6098, loss_ss_sup: 0.0070, loss: 0.9115, grad_norm: 1.9398
+2025-03-05 07:49:42,343 - mmrotate - INFO - Iter [52500/120000]	lr: 1.000e-04, eta: 12:13:57, time: 0.459, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0936, loss_bbox_sup: 0.2564, loss_centerness_sup: 0.6070, loss_ss_sup: 0.0100, loss: 0.9669, grad_norm: 2.0860
+2025-03-05 07:50:05,260 - mmrotate - INFO - Iter [52550/120000]	lr: 1.000e-04, eta: 12:05:20, time: 0.458, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0848, loss_bbox_sup: 0.2472, loss_centerness_sup: 0.6109, loss_ss_sup: 0.0090, loss: 0.9518, grad_norm: 1.8614
+2025-03-05 07:50:28,335 - mmrotate - INFO - Iter [52600/120000]	lr: 1.000e-04, eta: 11:57:26, time: 0.462, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0877, loss_bbox_sup: 0.2518, loss_centerness_sup: 0.6062, loss_ss_sup: 0.0077, loss: 0.9535, grad_norm: 1.7920
+2025-03-05 07:50:51,247 - mmrotate - INFO - Iter [52650/120000]	lr: 1.000e-04, eta: 11:49:55, time: 0.458, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0949, loss_bbox_sup: 0.2474, loss_centerness_sup: 0.6042, loss_ss_sup: 0.0095, loss: 0.9560, grad_norm: 1.9056
+2025-03-05 07:51:14,244 - mmrotate - INFO - Iter [52700/120000]	lr: 1.000e-04, eta: 11:42:57, time: 0.460, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0877, loss_bbox_sup: 0.2378, loss_centerness_sup: 0.6046, loss_ss_sup: 0.0088, loss: 0.9389, grad_norm: 1.8053
+2025-03-05 07:51:36,946 - mmrotate - INFO - Iter [52750/120000]	lr: 1.000e-04, eta: 11:36:11, time: 0.454, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0948, loss_bbox_sup: 0.2298, loss_centerness_sup: 0.6104, loss_ss_sup: 0.0085, loss: 0.9434, grad_norm: 2.0222
+2025-03-05 07:51:59,817 - mmrotate - INFO - Iter [52800/120000]	lr: 1.000e-04, eta: 11:29:57, time: 0.457, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0931, loss_bbox_sup: 0.2631, loss_centerness_sup: 0.6079, loss_ss_sup: 0.0102, loss: 0.9744, grad_norm: 1.9653
+2025-03-05 07:52:22,704 - mmrotate - INFO - Iter [52850/120000]	lr: 1.000e-04, eta: 11:24:04, time: 0.458, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0939, loss_bbox_sup: 0.2447, loss_centerness_sup: 0.6098, loss_ss_sup: 0.0095, loss: 0.9579, grad_norm: 2.0210
+2025-03-05 07:52:45,690 - mmrotate - INFO - Iter [52900/120000]	lr: 1.000e-04, eta: 11:18:34, time: 0.460, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0817, loss_bbox_sup: 0.2410, loss_centerness_sup: 0.6104, loss_ss_sup: 0.0097, loss: 0.9428, grad_norm: 1.9494
+2025-03-05 07:53:08,382 - mmrotate - INFO - Iter [52950/120000]	lr: 1.000e-04, eta: 11:13:11, time: 0.454, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0875, loss_bbox_sup: 0.2477, loss_centerness_sup: 0.6062, loss_ss_sup: 0.0103, loss: 0.9517, grad_norm: 1.9281
+2025-03-05 07:53:31,336 - mmrotate - INFO - Exp name: gmm.py
+2025-03-05 07:53:31,336 - mmrotate - INFO - Iter [53000/120000]	lr: 1.000e-04, eta: 11:08:14, time: 0.459, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0880, loss_bbox_sup: 0.2359, loss_centerness_sup: 0.6067, loss_ss_sup: 0.0085, loss: 0.9391, grad_norm: 2.0925
+2025-03-05 07:53:54,144 - mmrotate - INFO - Iter [53050/120000]	lr: 1.000e-04, eta: 11:03:27, time: 0.456, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0885, loss_bbox_sup: 0.2461, loss_centerness_sup: 0.6061, loss_ss_sup: 0.0074, loss: 0.9482, grad_norm: 1.9594
+2025-03-05 07:54:16,765 - mmrotate - INFO - Iter [53100/120000]	lr: 1.000e-04, eta: 10:58:47, time: 0.452, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0841, loss_bbox_sup: 0.2130, loss_centerness_sup: 0.6061, loss_ss_sup: 0.0076, loss: 0.9108, grad_norm: 1.9083
+2025-03-05 07:54:39,533 - mmrotate - INFO - Iter [53150/120000]	lr: 1.000e-04, eta: 10:54:26, time: 0.455, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0881, loss_bbox_sup: 0.2499, loss_centerness_sup: 0.6065, loss_ss_sup: 0.0069, loss: 0.9514, grad_norm: 1.8047
+2025-03-05 07:55:02,710 - mmrotate - INFO - Iter [53200/120000]	lr: 1.000e-04, eta: 10:50:30, time: 0.464, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0955, loss_bbox_sup: 0.2669, loss_centerness_sup: 0.6057, loss_ss_sup: 0.0082, loss: 0.9763, grad_norm: 1.7269
+2025-03-05 07:55:25,558 - mmrotate - INFO - Iter [53250/120000]	lr: 1.000e-04, eta: 10:46:33, time: 0.457, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0901, loss_bbox_sup: 0.2479, loss_centerness_sup: 0.6072, loss_ss_sup: 0.0102, loss: 0.9554, grad_norm: 2.2759
+2025-03-05 07:55:48,551 - mmrotate - INFO - Iter [53300/120000]	lr: 1.000e-04, eta: 10:42:52, time: 0.460, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0878, loss_bbox_sup: 0.2515, loss_centerness_sup: 0.6084, loss_ss_sup: 0.0119, loss: 0.9595, grad_norm: 1.7291
+2025-03-05 07:56:11,535 - mmrotate - INFO - Iter [53350/120000]	lr: 1.000e-04, eta: 10:39:19, time: 0.460, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0862, loss_bbox_sup: 0.2662, loss_centerness_sup: 0.6101, loss_ss_sup: 0.0078, loss: 0.9703, grad_norm: 1.8771
+2025-03-05 07:56:34,459 - mmrotate - INFO - Iter [53400/120000]	lr: 1.000e-04, eta: 10:35:53, time: 0.458, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0911, loss_bbox_sup: 0.2429, loss_centerness_sup: 0.6054, loss_ss_sup: 0.0072, loss: 0.9466, grad_norm: 2.1015
+2025-03-05 07:56:56,950 - mmrotate - INFO - Iter [53450/120000]	lr: 1.000e-04, eta: 10:32:22, time: 0.450, data_time: 0.012, memory: 10763, loss_cls_sup: 0.0894, loss_bbox_sup: 0.2211, loss_centerness_sup: 0.6064, loss_ss_sup: 0.0083, loss: 0.9252, grad_norm: 1.8091
+2025-03-05 07:57:19,812 - mmrotate - INFO - Iter [53500/120000]	lr: 1.000e-04, eta: 10:29:11, time: 0.457, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0839, loss_bbox_sup: 0.2487, loss_centerness_sup: 0.6125, loss_ss_sup: 0.0067, loss: 0.9519, grad_norm: 1.6105
+2025-03-05 07:57:42,679 - mmrotate - INFO - Iter [53550/120000]	lr: 1.000e-04, eta: 10:26:06, time: 0.457, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0898, loss_bbox_sup: 0.2497, loss_centerness_sup: 0.6096, loss_ss_sup: 0.0112, loss: 0.9604, grad_norm: 2.2032
+2025-03-05 07:58:05,456 - mmrotate - INFO - Iter [53600/120000]	lr: 1.000e-04, eta: 10:23:06, time: 0.456, data_time: 0.013, memory: 10763, loss_cls_sup: 0.0797, loss_bbox_sup: 0.2369, loss_centerness_sup: 0.6069, loss_ss_sup: 0.0096, loss: 0.9331, grad_norm: 1.9537

work_dir_h/PWOOD/dotav2/30p/pro_data/best_0.402659_mAP.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8277d8682dedc17b8f2d29961e52b7570886b3fe988b51d5d70868c3fd9baa8b
+size 513600602

work_dir_h/PWOOD/dotav2/best_0.363926_mAP.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98be837fcaf1e4ad6717d0c58b21ba0ece03a7751e77d767da8c2ee00cd86c8d
+size 513603162