2022-11-26 15:27:29,674 - mmdet - INFO - Environment info: ------------------------------------------------------------ sys.platform: linux Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] CUDA available: True GPU 0: GeForce RTX 3090 CUDA_HOME: /usr/local/cuda NVCC: Build cuda_11.1.TC455_06.29190527_0 GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 PyTorch: 1.11.0 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.3 - 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_86,code=sm_86;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.2 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.11.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.12.0 OpenCV: 4.5.5 MMCV: 1.4.8 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 11.3 MMDetection: 2.23.0+8bcaa7c ------------------------------------------------------------ 2022-11-26 15:27:29,962 - mmdet - INFO - Distributed training: False 2022-11-26 15:27:30,238 - mmdet - INFO - Config: optimizer = dict( type='SGD', lr=0.005, momentum=0.9, weight_decay=0.0001, paramwise_cfg=dict(bias_lr_mult=2.0, bias_decay_mult=0.0)) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2)) lr_config = dict( policy='step', warmup='constant', warmup_iters=5000, warmup_ratio=0.3333333333333333, step=[8, 11]) runner = dict(type='EpochBasedRunner', max_epochs=12) log_config = dict( interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)]) dist_params = dict(backend='nccl') log_level = 'INFO' load_from = None resume_from = None workflow = [('train', 1)] cudnn_benchmark = True dataset_type = 'SIRSTDet2NoCoDataset' data_root = 'data/sirst/' img_norm_cfg = dict( mean=[111.89, 111.89, 111.89], std=[27.62, 27.62, 27.62], to_rgb=True) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict(type='Resize', img_scale=(1000, 600), keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), dict( type='Normalize', mean=[111.89, 111.89, 111.89], std=[27.62, 27.62, 27.62], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[111.89, 111.89, 111.89], std=[27.62, 27.62, 27.62], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ] data = dict( samples_per_gpu=4, workers_per_gpu=4, train=dict( type='RepeatDataset', times=3, dataset=dict( type='SIRSTDet2NoCoDataset', ann_file=['data/sirst/splits/trainval_full.txt'], img_prefix=['data/sirst/'], pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict(type='Resize', img_scale=(1000, 600), keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), dict( type='Normalize', mean=[111.89, 111.89, 111.89], std=[27.62, 27.62, 27.62], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ])), val=dict( type='SIRSTDet2NoCoDataset', ann_file='data/sirst/splits/test_full.txt', img_prefix='data/sirst/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[111.89, 111.89, 111.89], std=[27.62, 27.62, 27.62], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ]), test=dict( type='SIRSTDet2NoCoDataset', ann_file='data/sirst/splits/test_full.txt', img_prefix='data/sirst/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1000, 600), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[111.89, 111.89, 111.89], std=[27.62, 27.62, 27.62], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ])) model = dict( type='FCOS', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, norm_cfg=dict(type='BN', requires_grad=False), norm_eval=True, style='caffe', init_cfg=dict( type='Pretrained', checkpoint='open-mmlab://detectron/resnet50_caffe')), 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='RFLA_FCOSHead', norm_cfg=None, num_classes=18, in_channels=256, stacked_convs=4, feat_channels=256, strides=[8, 16, 32, 64, 128], norm_on_bbox=True, centerness_on_reg=True, dcn_on_last_conv=False, conv_bias=True, fpn_layer='p3', fraction=0.5, loss_cls=dict( type='FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, loss_weight=1.0), loss_bbox=dict(type='DIoULoss', loss_weight=1.0), loss_centerness=dict( type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)), train_cfg=dict( assigner=dict( type='HieAssigner', ignore_iof_thr=-1, gpu_assign_thr=256, iou_calculator=dict(type='BboxDistanceMetric'), assign_metric='kl', topk=[6, 1], ratio=0.9), allowed_border=-1, pos_weight=-1, debug=False), test_cfg=dict( nms_pre=3000, min_bbox_size=0, score_thr=0.05, nms=dict(type='nms', iou_threshold=0.5), max_per_img=3000)) checkpoint_config = dict(interval=1) work_dir = './work_dirs/sirstv2_fcos_rfla_r50_kld_1x' auto_resume = False gpu_ids = [0] 2022-11-26 15:27:30,238 - mmdet - INFO - Set random seed to 1371792221, deterministic: False 2022-11-26 15:27:30,896 - mmdet - INFO - initialize ResNet with init_cfg {'type': 'Pretrained', 'checkpoint': 'open-mmlab://detectron/resnet50_caffe'} 2022-11-26 15:27:31,699 - mmdet - INFO - initialize FPN with init_cfg {'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'} 2022-11-26 15:27:31,998 - mmdet - INFO - initialize RFLA_FCOSHead with init_cfg {'type': 'Normal', 'layer': 'Conv2d', 'std': 0.01, 'override': {'type': 'Normal', 'name': 'conv_cls', 'std': 0.01, 'bias_prob': 0.01}} Name of parameter - Initialization information backbone.conv1.weight - torch.Size([64, 3, 7, 7]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.bn1.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.bn1.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.0.conv1.weight - torch.Size([64, 64, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.0.bn1.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.0.bn1.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.0.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.0.bn2.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.0.bn2.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.0.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.0.bn3.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.0.bn3.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.0.downsample.1.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.0.downsample.1.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.1.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.1.bn1.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.1.bn1.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.1.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.1.bn2.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.1.bn2.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.1.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.1.bn3.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.1.bn3.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.2.conv1.weight - torch.Size([64, 256, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.2.bn1.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.2.bn1.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.2.conv2.weight - torch.Size([64, 64, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.2.bn2.weight - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.2.bn2.bias - torch.Size([64]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.2.conv3.weight - torch.Size([256, 64, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.2.bn3.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer1.2.bn3.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.0.conv1.weight - torch.Size([128, 256, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.0.bn1.weight - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.0.bn1.bias - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.0.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.0.bn2.weight - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.0.bn2.bias - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.0.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.0.bn3.weight - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.0.bn3.bias - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.0.downsample.0.weight - torch.Size([512, 256, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.0.downsample.1.weight - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.0.downsample.1.bias - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.1.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.1.bn1.weight - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.1.bn1.bias - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.1.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.1.bn2.weight - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.1.bn2.bias - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.1.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.1.bn3.weight - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.1.bn3.bias - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.2.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.2.bn1.weight - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.2.bn1.bias - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.2.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.2.bn2.weight - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.2.bn2.bias - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.2.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.2.bn3.weight - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.2.bn3.bias - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.3.conv1.weight - torch.Size([128, 512, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.3.bn1.weight - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.3.bn1.bias - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.3.conv2.weight - torch.Size([128, 128, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.3.bn2.weight - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.3.bn2.bias - torch.Size([128]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.3.conv3.weight - torch.Size([512, 128, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.3.bn3.weight - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer2.3.bn3.bias - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.0.conv1.weight - torch.Size([256, 512, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.0.bn1.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.0.bn1.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.0.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.0.bn2.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.0.bn2.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.0.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.0.bn3.weight - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.0.bn3.bias - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.0.downsample.0.weight - torch.Size([1024, 512, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.0.downsample.1.weight - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.0.downsample.1.bias - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.1.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.1.bn1.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.1.bn1.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.1.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.1.bn2.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.1.bn2.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.1.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.1.bn3.weight - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.1.bn3.bias - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.2.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.2.bn1.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.2.bn1.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.2.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.2.bn2.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.2.bn2.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.2.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.2.bn3.weight - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.2.bn3.bias - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.3.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.3.bn1.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.3.bn1.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.3.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.3.bn2.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.3.bn2.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.3.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.3.bn3.weight - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.3.bn3.bias - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.4.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.4.bn1.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.4.bn1.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.4.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.4.bn2.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.4.bn2.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.4.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.4.bn3.weight - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.4.bn3.bias - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.5.conv1.weight - torch.Size([256, 1024, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.5.bn1.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.5.bn1.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.5.conv2.weight - torch.Size([256, 256, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.5.bn2.weight - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.5.bn2.bias - torch.Size([256]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.5.conv3.weight - torch.Size([1024, 256, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.5.bn3.weight - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer3.5.bn3.bias - torch.Size([1024]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.0.conv1.weight - torch.Size([512, 1024, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.0.bn1.weight - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.0.bn1.bias - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.0.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.0.bn2.weight - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.0.bn2.bias - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.0.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.0.bn3.weight - torch.Size([2048]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.0.bn3.bias - torch.Size([2048]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.0.downsample.0.weight - torch.Size([2048, 1024, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.0.downsample.1.weight - torch.Size([2048]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.0.downsample.1.bias - torch.Size([2048]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.1.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.1.bn1.weight - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.1.bn1.bias - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.1.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.1.bn2.weight - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.1.bn2.bias - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.1.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.1.bn3.weight - torch.Size([2048]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.1.bn3.bias - torch.Size([2048]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.2.conv1.weight - torch.Size([512, 2048, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.2.bn1.weight - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.2.bn1.bias - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.2.conv2.weight - torch.Size([512, 512, 3, 3]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.2.bn2.weight - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.2.bn2.bias - torch.Size([512]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.2.conv3.weight - torch.Size([2048, 512, 1, 1]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.2.bn3.weight - torch.Size([2048]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe backbone.layer4.2.bn3.bias - torch.Size([2048]): PretrainedInit: load from open-mmlab://detectron/resnet50_caffe neck.lateral_convs.0.conv.weight - torch.Size([256, 512, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS neck.lateral_convs.1.conv.weight - torch.Size([256, 1024, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS neck.lateral_convs.2.conv.weight - torch.Size([256, 2048, 1, 1]): XavierInit: gain=1, distribution=uniform, bias=0 neck.lateral_convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS neck.fpn_convs.0.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS neck.fpn_convs.1.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS neck.fpn_convs.2.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS neck.fpn_convs.3.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS neck.fpn_convs.4.conv.weight - torch.Size([256, 256, 3, 3]): XavierInit: gain=1, distribution=uniform, bias=0 neck.fpn_convs.4.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS bbox_head.cls_convs.0.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.cls_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS bbox_head.cls_convs.1.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.cls_convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS bbox_head.cls_convs.2.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.cls_convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS bbox_head.cls_convs.3.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.cls_convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS bbox_head.reg_convs.0.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.reg_convs.0.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS bbox_head.reg_convs.1.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.reg_convs.1.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS bbox_head.reg_convs.2.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.reg_convs.2.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS bbox_head.reg_convs.3.conv.weight - torch.Size([256, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.reg_convs.3.conv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of FCOS bbox_head.conv_cls.weight - torch.Size([18, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=-4.59511985013459 bbox_head.conv_cls.bias - torch.Size([18]): NormalInit: mean=0, std=0.01, bias=-4.59511985013459 bbox_head.conv_reg.weight - torch.Size([4, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.conv_reg.bias - torch.Size([4]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.conv_centerness.weight - torch.Size([1, 256, 3, 3]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.conv_centerness.bias - torch.Size([1]): NormalInit: mean=0, std=0.01, bias=0 bbox_head.scales.0.scale - torch.Size([]): The value is the same before and after calling `init_weights` of FCOS bbox_head.scales.1.scale - torch.Size([]): The value is the same before and after calling `init_weights` of FCOS bbox_head.scales.2.scale - torch.Size([]): The value is the same before and after calling `init_weights` of FCOS bbox_head.scales.3.scale - torch.Size([]): The value is the same before and after calling `init_weights` of FCOS bbox_head.scales.4.scale - torch.Size([]): The value is the same before and after calling `init_weights` of FCOS 2022-11-26 15:28:28,025 - mmdet - INFO - Start running, host: root@interactive95348, work_dir: /opt/data/private/deepinfrared/work_dirs/sirstv2_fcos_rfla_r50_kld_1x 2022-11-26 15:28:28,026 - mmdet - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) StepLrUpdaterHook (NORMAL ) CheckpointHook (LOW ) EvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_epoch: (VERY_HIGH ) StepLrUpdaterHook (LOW ) IterTimerHook (LOW ) EvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_iter: (VERY_HIGH ) StepLrUpdaterHook (LOW ) IterTimerHook (LOW ) EvalHook -------------------- after_train_iter: (ABOVE_NORMAL) OptimizerHook (NORMAL ) CheckpointHook (LOW ) IterTimerHook (LOW ) EvalHook (VERY_LOW ) TextLoggerHook -------------------- after_train_epoch: (NORMAL ) CheckpointHook (LOW ) EvalHook (VERY_LOW ) TextLoggerHook -------------------- before_val_epoch: (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 -------------------- 2022-11-26 15:28:28,027 - mmdet - INFO - workflow: [('train', 1)], max: 12 epochs 2022-11-26 15:28:28,027 - mmdet - INFO - Checkpoints will be saved to /opt/data/private/deepinfrared/work_dirs/sirstv2_fcos_rfla_r50_kld_1x by HardDiskBackend. 2022-11-26 15:29:21,120 - mmdet - INFO - Iter [50/6924] lr: 1.667e-03, eta: 2:01:36, time: 1.061, data_time: 0.077, memory: 11396, loss_cls: 1.0555, loss_bbox: 0.9627, loss_centerness: 0.5108, loss: 2.5291, grad_norm: 14.6703 2022-11-26 15:29:50,172 - mmdet - INFO - Iter [100/6924] lr: 1.667e-03, eta: 1:33:24, time: 0.581, data_time: 0.010, memory: 11396, loss_cls: 1.0573, loss_bbox: 0.9631, loss_centerness: 0.4892, loss: 2.5096, grad_norm: 2.8755 2022-11-26 15:30:00,349 - mmdet - INFO - Iter [150/6924] lr: 1.667e-03, eta: 1:09:28, time: 0.204, data_time: 0.009, memory: 11396, loss_cls: 1.0009, loss_bbox: 0.9515, loss_centerness: 0.5058, loss: 2.4582, grad_norm: 2.7620 2022-11-26 15:30:10,003 - mmdet - INFO - Iter [200/6924] lr: 1.667e-03, eta: 0:57:07, time: 0.193, data_time: 0.008, memory: 11396, loss_cls: 0.9491, loss_bbox: 0.9556, loss_centerness: 0.5554, loss: 2.4601, grad_norm: 3.1687 2022-11-26 15:30:19,215 - mmdet - INFO - Iter [250/6924] lr: 1.667e-03, eta: 0:49:27, time: 0.184, data_time: 0.010, memory: 11396, loss_cls: 0.9309, loss_bbox: 0.9486, loss_centerness: 0.4825, loss: 2.3621, grad_norm: 3.0650 2022-11-26 15:30:29,119 - mmdet - INFO - Iter [300/6924] lr: 1.667e-03, eta: 0:44:33, time: 0.198, data_time: 0.010, memory: 11396, loss_cls: 0.9157, loss_bbox: 0.9306, loss_centerness: 0.5172, loss: 2.3635, grad_norm: 3.7407 2022-11-26 15:30:39,476 - mmdet - INFO - Iter [350/6924] lr: 1.667e-03, eta: 0:41:08, time: 0.207, data_time: 0.010, memory: 11396, loss_cls: 0.9166, loss_bbox: 0.9916, loss_centerness: 0.5162, loss: 2.4245, grad_norm: 1.9375 2022-11-26 15:30:49,538 - mmdet - INFO - Iter [400/6924] lr: 1.667e-03, eta: 0:38:27, time: 0.201, data_time: 0.009, memory: 11396, loss_cls: 0.7874, loss_bbox: 0.9679, loss_centerness: 0.5244, loss: 2.2798, grad_norm: 11.4163 2022-11-26 15:30:59,094 - mmdet - INFO - Iter [450/6924] lr: 1.667e-03, eta: 0:36:13, time: 0.191, data_time: 0.010, memory: 11396, loss_cls: 0.6355, loss_bbox: 0.9515, loss_centerness: 0.5205, loss: 2.1075, grad_norm: 9.3855 2022-11-26 15:31:09,341 - mmdet - INFO - Iter [500/6924] lr: 1.667e-03, eta: 0:34:32, time: 0.205, data_time: 0.009, memory: 11396, loss_cls: 0.6106, loss_bbox: 0.8866, loss_centerness: 0.4478, loss: 1.9450, grad_norm: 18.7823 2022-11-26 15:31:19,555 - mmdet - INFO - Iter [550/6924] lr: 1.667e-03, eta: 0:33:07, time: 0.204, data_time: 0.011, memory: 11396, loss_cls: 0.4758, loss_bbox: 0.9657, loss_centerness: 0.5215, loss: 1.9631, grad_norm: 8.3803 2022-11-26 15:31:24,577 - mmdet - INFO - Saving checkpoint at 1 epochs 2022-11-26 15:32:26,929 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 6196 | 0.893 | 0.390 | +-------+-----+------+--------+-------+ | mAP | | | | 0.390 | +-------+-----+------+--------+-------+ 2022-11-26 15:32:32,077 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 6196 | 0.833 | 0.355 | +-------+-----+------+--------+-------+ | mAP | | | | 0.355 | +-------+-----+------+--------+-------+ 2022-11-26 15:32:37,323 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 6196 | 0.800 | 0.343 | +-------+-----+------+--------+-------+ | mAP | | | | 0.343 | +-------+-----+------+--------+-------+ 2022-11-26 15:32:43,131 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 6196 | 0.767 | 0.323 | +-------+-----+------+--------+-------+ | mAP | | | | 0.323 | +-------+-----+------+--------+-------+ 2022-11-26 15:32:47,994 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 6196 | 0.713 | 0.257 | +-------+-----+------+--------+-------+ | mAP | | | | 0.257 | +-------+-----+------+--------+-------+ 2022-11-26 15:32:52,065 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 6196 | 0.687 | 0.216 | +-------+-----+------+--------+-------+ | mAP | | | | 0.216 | +-------+-----+------+--------+-------+ 2022-11-26 15:32:56,961 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 6196 | 0.653 | 0.176 | +-------+-----+------+--------+-------+ | mAP | | | | 0.176 | +-------+-----+------+--------+-------+ 2022-11-26 15:33:01,031 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 6196 | 0.547 | 0.130 | +-------+-----+------+--------+-------+ | mAP | | | | 0.130 | +-------+-----+------+--------+-------+ 2022-11-26 15:33:04,531 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 6196 | 0.400 | 0.062 | +-------+-----+------+--------+-------+ | mAP | | | | 0.062 | +-------+-----+------+--------+-------+ 2022-11-26 15:33:04,538 - mmdet - INFO - Iter(val) [256] NoCoAP10: 0.3900, NoCoAP20: 0.3550, NoCoAP30: 0.3430, NoCoAP40: 0.3230, NoCoAP50: 0.2570, NoCoAP60: 0.2160, NoCoAP70: 0.1760, NoCoAP80: 0.1300, NoCoAP90: 0.0620, mNoCoAP: 0.2502 2022-11-26 15:33:12,450 - mmdet - INFO - Iter [600/6924] lr: 1.667e-03, eta: 0:33:07, time: 0.342, data_time: 0.167, memory: 11396, loss_cls: 0.4003, loss_bbox: 1.0057, loss_centerness: 0.5021, loss: 1.9081, grad_norm: 10.0635 2022-11-26 15:33:21,963 - mmdet - INFO - Iter [650/6924] lr: 1.667e-03, eta: 0:31:52, time: 0.190, data_time: 0.009, memory: 11396, loss_cls: 0.4571, loss_bbox: 0.8851, loss_centerness: 0.4625, loss: 1.8046, grad_norm: 20.2669 2022-11-26 15:33:31,926 - mmdet - INFO - Iter [700/6924] lr: 1.667e-03, eta: 0:30:50, time: 0.199, data_time: 0.008, memory: 11396, loss_cls: 0.5459, loss_bbox: 0.8261, loss_centerness: 0.4572, loss: 1.8292, grad_norm: 16.1978 2022-11-26 15:33:41,870 - mmdet - INFO - Iter [750/6924] lr: 1.667e-03, eta: 0:29:54, time: 0.199, data_time: 0.008, memory: 11396, loss_cls: 0.4770, loss_bbox: 0.8071, loss_centerness: 0.5030, loss: 1.7870, grad_norm: 9.3205 2022-11-26 15:33:51,512 - mmdet - INFO - Iter [800/6924] lr: 1.667e-03, eta: 0:29:02, time: 0.193, data_time: 0.008, memory: 11396, loss_cls: 0.3812, loss_bbox: 0.7858, loss_centerness: 0.4982, loss: 1.6652, grad_norm: 7.6773 2022-11-26 15:34:00,414 - mmdet - INFO - Iter [850/6924] lr: 1.667e-03, eta: 0:28:10, time: 0.178, data_time: 0.008, memory: 11396, loss_cls: 0.3705, loss_bbox: 0.7193, loss_centerness: 0.4861, loss: 1.5759, grad_norm: 10.3017 2022-11-26 15:34:10,297 - mmdet - INFO - Iter [900/6924] lr: 1.667e-03, eta: 0:27:29, time: 0.198, data_time: 0.008, memory: 11396, loss_cls: 0.2737, loss_bbox: 0.5726, loss_centerness: 0.4393, loss: 1.2855, grad_norm: 10.2104 2022-11-26 15:34:19,520 - mmdet - INFO - Iter [950/6924] lr: 1.667e-03, eta: 0:26:47, time: 0.184, data_time: 0.007, memory: 11396, loss_cls: 0.2818, loss_bbox: 0.5506, loss_centerness: 0.4283, loss: 1.2607, grad_norm: 9.7350 2022-11-26 15:34:29,199 - mmdet - INFO - Exp name: sirstv2_fcos_rfla_r50_kld_1x.py 2022-11-26 15:34:29,200 - mmdet - INFO - Iter [1000/6924] lr: 1.667e-03, eta: 0:26:11, time: 0.194, data_time: 0.008, memory: 11396, loss_cls: 0.2480, loss_bbox: 0.5131, loss_centerness: 0.4562, loss: 1.2173, grad_norm: 8.3621 2022-11-26 15:34:39,077 - mmdet - INFO - Iter [1050/6924] lr: 1.667e-03, eta: 0:25:39, time: 0.198, data_time: 0.009, memory: 11396, loss_cls: 0.1792, loss_bbox: 0.5568, loss_centerness: 0.4402, loss: 1.1762, grad_norm: 6.7386 2022-11-26 15:34:48,576 - mmdet - INFO - Iter [1100/6924] lr: 1.667e-03, eta: 0:25:07, time: 0.190, data_time: 0.009, memory: 11396, loss_cls: 0.2070, loss_bbox: 0.4653, loss_centerness: 0.4373, loss: 1.1096, grad_norm: 8.8501 2022-11-26 15:34:58,182 - mmdet - INFO - Iter [1150/6924] lr: 1.667e-03, eta: 0:24:37, time: 0.192, data_time: 0.008, memory: 11396, loss_cls: 0.2124, loss_bbox: 0.5657, loss_centerness: 0.4559, loss: 1.2340, grad_norm: 7.7853 2022-11-26 15:34:59,248 - mmdet - INFO - Saving checkpoint at 2 epochs 2022-11-26 15:35:13,712 - mmdet - INFO - +-------+-----+-------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+-------+--------+-------+ | 0 | 150 | 15482 | 0.987 | 0.846 | +-------+-----+-------+--------+-------+ | mAP | | | | 0.846 | +-------+-----+-------+--------+-------+ 2022-11-26 15:35:19,101 - mmdet - INFO - +-------+-----+-------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+-------+--------+-------+ | 0 | 150 | 15482 | 0.980 | 0.831 | +-------+-----+-------+--------+-------+ | mAP | | | | 0.831 | +-------+-----+-------+--------+-------+ 2022-11-26 15:35:25,648 - mmdet - INFO - +-------+-----+-------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+-------+--------+-------+ | 0 | 150 | 15482 | 0.973 | 0.817 | +-------+-----+-------+--------+-------+ | mAP | | | | 0.817 | +-------+-----+-------+--------+-------+ 2022-11-26 15:35:29,119 - mmdet - INFO - +-------+-----+-------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+-------+--------+-------+ | 0 | 150 | 15482 | 0.967 | 0.762 | +-------+-----+-------+--------+-------+ | mAP | | | | 0.762 | +-------+-----+-------+--------+-------+ 2022-11-26 15:35:33,451 - mmdet - INFO - +-------+-----+-------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+-------+--------+-------+ | 0 | 150 | 15482 | 0.927 | 0.711 | +-------+-----+-------+--------+-------+ | mAP | | | | 0.711 | +-------+-----+-------+--------+-------+ 2022-11-26 15:35:36,660 - mmdet - INFO - +-------+-----+-------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+-------+--------+-------+ | 0 | 150 | 15482 | 0.893 | 0.645 | +-------+-----+-------+--------+-------+ | mAP | | | | 0.645 | +-------+-----+-------+--------+-------+ 2022-11-26 15:35:42,553 - mmdet - INFO - +-------+-----+-------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+-------+--------+-------+ | 0 | 150 | 15482 | 0.833 | 0.498 | +-------+-----+-------+--------+-------+ | mAP | | | | 0.498 | +-------+-----+-------+--------+-------+ 2022-11-26 15:35:45,726 - mmdet - INFO - +-------+-----+-------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+-------+--------+-------+ | 0 | 150 | 15482 | 0.733 | 0.322 | +-------+-----+-------+--------+-------+ | mAP | | | | 0.322 | +-------+-----+-------+--------+-------+ 2022-11-26 15:35:49,346 - mmdet - INFO - +-------+-----+-------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+-------+--------+-------+ | 0 | 150 | 15482 | 0.567 | 0.147 | +-------+-----+-------+--------+-------+ | mAP | | | | 0.147 | +-------+-----+-------+--------+-------+ 2022-11-26 15:35:49,353 - mmdet - INFO - Iter(val) [256] NoCoAP10: 0.8460, NoCoAP20: 0.8310, NoCoAP30: 0.8170, NoCoAP40: 0.7620, NoCoAP50: 0.7110, NoCoAP60: 0.6450, NoCoAP70: 0.4980, NoCoAP80: 0.3220, NoCoAP90: 0.1470, mNoCoAP: 0.6199 2022-11-26 15:36:01,850 - mmdet - INFO - Iter [1200/6924] lr: 1.667e-03, eta: 0:24:28, time: 0.271, data_time: 0.087, memory: 11396, loss_cls: 0.1975, loss_bbox: 0.4754, loss_centerness: 0.4590, loss: 1.1319, grad_norm: 8.2242 2022-11-26 15:36:11,247 - mmdet - INFO - Iter [1250/6924] lr: 1.667e-03, eta: 0:24:00, time: 0.188, data_time: 0.008, memory: 11396, loss_cls: 0.2193, loss_bbox: 0.4541, loss_centerness: 0.3726, loss: 1.0459, grad_norm: 9.0180 2022-11-26 15:36:21,106 - mmdet - INFO - Iter [1300/6924] lr: 1.667e-03, eta: 0:23:35, time: 0.197, data_time: 0.008, memory: 11396, loss_cls: 0.1513, loss_bbox: 0.5058, loss_centerness: 0.3992, loss: 1.0563, grad_norm: 6.3060 2022-11-26 15:36:30,921 - mmdet - INFO - Iter [1350/6924] lr: 1.667e-03, eta: 0:23:11, time: 0.196, data_time: 0.008, memory: 11396, loss_cls: 0.2338, loss_bbox: 0.4924, loss_centerness: 0.4109, loss: 1.1372, grad_norm: 8.7385 2022-11-26 15:36:40,621 - mmdet - INFO - Iter [1400/6924] lr: 1.667e-03, eta: 0:22:47, time: 0.194, data_time: 0.010, memory: 11396, loss_cls: 0.2520, loss_bbox: 0.5085, loss_centerness: 0.4375, loss: 1.1979, grad_norm: 9.7371 2022-11-26 15:36:50,189 - mmdet - INFO - Iter [1450/6924] lr: 1.667e-03, eta: 0:22:24, time: 0.191, data_time: 0.009, memory: 11396, loss_cls: 0.1695, loss_bbox: 0.4750, loss_centerness: 0.3863, loss: 1.0308, grad_norm: 6.6697 2022-11-26 15:36:59,870 - mmdet - INFO - Iter [1500/6924] lr: 1.667e-03, eta: 0:22:03, time: 0.194, data_time: 0.008, memory: 11396, loss_cls: 0.2073, loss_bbox: 0.4687, loss_centerness: 0.4032, loss: 1.0792, grad_norm: 7.6918 2022-11-26 15:37:09,478 - mmdet - INFO - Iter [1550/6924] lr: 1.667e-03, eta: 0:21:41, time: 0.192, data_time: 0.008, memory: 11396, loss_cls: 0.1537, loss_bbox: 0.4269, loss_centerness: 0.4211, loss: 1.0017, grad_norm: 6.7298 2022-11-26 15:37:19,366 - mmdet - INFO - Iter [1600/6924] lr: 1.667e-03, eta: 0:21:22, time: 0.198, data_time: 0.008, memory: 11396, loss_cls: 0.1241, loss_bbox: 0.4557, loss_centerness: 0.3873, loss: 0.9670, grad_norm: 6.1426 2022-11-26 15:37:28,987 - mmdet - INFO - Iter [1650/6924] lr: 1.667e-03, eta: 0:21:02, time: 0.192, data_time: 0.008, memory: 11396, loss_cls: 0.2097, loss_bbox: 0.4645, loss_centerness: 0.4421, loss: 1.1163, grad_norm: 8.3968 2022-11-26 15:37:39,713 - mmdet - INFO - Iter [1700/6924] lr: 1.667e-03, eta: 0:20:46, time: 0.215, data_time: 0.008, memory: 11396, loss_cls: 0.1811, loss_bbox: 0.4602, loss_centerness: 0.4227, loss: 1.0640, grad_norm: 7.8037 2022-11-26 15:37:45,820 - mmdet - INFO - Saving checkpoint at 3 epochs 2022-11-26 15:37:58,352 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2726 | 0.973 | 0.857 | +-------+-----+------+--------+-------+ | mAP | | | | 0.857 | +-------+-----+------+--------+-------+ 2022-11-26 15:38:01,484 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2726 | 0.973 | 0.843 | +-------+-----+------+--------+-------+ | mAP | | | | 0.843 | +-------+-----+------+--------+-------+ 2022-11-26 15:38:05,605 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2726 | 0.940 | 0.806 | +-------+-----+------+--------+-------+ | mAP | | | | 0.806 | +-------+-----+------+--------+-------+ 2022-11-26 15:38:09,052 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2726 | 0.933 | 0.765 | +-------+-----+------+--------+-------+ | mAP | | | | 0.765 | +-------+-----+------+--------+-------+ 2022-11-26 15:38:14,751 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2726 | 0.913 | 0.711 | +-------+-----+------+--------+-------+ | mAP | | | | 0.711 | +-------+-----+------+--------+-------+ 2022-11-26 15:38:18,459 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2726 | 0.887 | 0.640 | +-------+-----+------+--------+-------+ | mAP | | | | 0.640 | +-------+-----+------+--------+-------+ 2022-11-26 15:38:23,730 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2726 | 0.853 | 0.572 | +-------+-----+------+--------+-------+ | mAP | | | | 0.572 | +-------+-----+------+--------+-------+ 2022-11-26 15:38:28,969 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2726 | 0.780 | 0.442 | +-------+-----+------+--------+-------+ | mAP | | | | 0.442 | +-------+-----+------+--------+-------+ 2022-11-26 15:38:32,141 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2726 | 0.640 | 0.237 | +-------+-----+------+--------+-------+ | mAP | | | | 0.237 | +-------+-----+------+--------+-------+ 2022-11-26 15:38:32,149 - mmdet - INFO - Iter(val) [256] NoCoAP10: 0.8570, NoCoAP20: 0.8430, NoCoAP30: 0.8060, NoCoAP40: 0.7650, NoCoAP50: 0.7110, NoCoAP60: 0.6400, NoCoAP70: 0.5720, NoCoAP80: 0.4420, NoCoAP90: 0.2370, mNoCoAP: 0.6526 2022-11-26 15:38:39,316 - mmdet - INFO - Iter [1750/6924] lr: 1.667e-03, eta: 0:20:55, time: 0.375, data_time: 0.197, memory: 11396, loss_cls: 0.3121, loss_bbox: 0.4374, loss_centerness: 0.4348, loss: 1.1843, grad_norm: 10.6269 2022-11-26 15:38:49,487 - mmdet - INFO - Iter [1800/6924] lr: 1.667e-03, eta: 0:20:37, time: 0.203, data_time: 0.010, memory: 11396, loss_cls: 0.1614, loss_bbox: 0.4511, loss_centerness: 0.3977, loss: 1.0101, grad_norm: 7.4390 2022-11-26 15:38:59,502 - mmdet - INFO - Iter [1850/6924] lr: 1.667e-03, eta: 0:20:19, time: 0.200, data_time: 0.010, memory: 11396, loss_cls: 0.1635, loss_bbox: 0.4281, loss_centerness: 0.4172, loss: 1.0088, grad_norm: 6.8363 2022-11-26 15:39:09,592 - mmdet - INFO - Iter [1900/6924] lr: 1.667e-03, eta: 0:20:02, time: 0.202, data_time: 0.009, memory: 11396, loss_cls: 0.1109, loss_bbox: 0.4130, loss_centerness: 0.4127, loss: 0.9366, grad_norm: 5.9905 2022-11-26 15:39:20,105 - mmdet - INFO - Iter [1950/6924] lr: 1.667e-03, eta: 0:19:46, time: 0.210, data_time: 0.009, memory: 11396, loss_cls: 0.1259, loss_bbox: 0.3841, loss_centerness: 0.4029, loss: 0.9129, grad_norm: 6.6031 2022-11-26 15:39:30,550 - mmdet - INFO - Exp name: sirstv2_fcos_rfla_r50_kld_1x.py 2022-11-26 15:39:30,550 - mmdet - INFO - Iter [2000/6924] lr: 1.667e-03, eta: 0:19:31, time: 0.209, data_time: 0.009, memory: 11396, loss_cls: 0.2101, loss_bbox: 0.4000, loss_centerness: 0.3810, loss: 0.9912, grad_norm: 8.0912 2022-11-26 15:39:40,137 - mmdet - INFO - Iter [2050/6924] lr: 1.667e-03, eta: 0:19:13, time: 0.192, data_time: 0.009, memory: 11396, loss_cls: 0.1322, loss_bbox: 0.3753, loss_centerness: 0.3700, loss: 0.8775, grad_norm: 6.8602 2022-11-26 15:39:49,874 - mmdet - INFO - Iter [2100/6924] lr: 1.667e-03, eta: 0:18:57, time: 0.195, data_time: 0.009, memory: 11396, loss_cls: 0.1841, loss_bbox: 0.4607, loss_centerness: 0.4064, loss: 1.0512, grad_norm: 8.5273 2022-11-26 15:40:00,002 - mmdet - INFO - Iter [2150/6924] lr: 1.667e-03, eta: 0:18:41, time: 0.203, data_time: 0.009, memory: 11396, loss_cls: 0.1171, loss_bbox: 0.4394, loss_centerness: 0.3978, loss: 0.9543, grad_norm: 6.0311 2022-11-26 15:40:09,470 - mmdet - INFO - Iter [2200/6924] lr: 1.667e-03, eta: 0:18:25, time: 0.189, data_time: 0.008, memory: 11396, loss_cls: 0.1218, loss_bbox: 0.4642, loss_centerness: 0.3922, loss: 0.9782, grad_norm: 5.2318 2022-11-26 15:40:19,655 - mmdet - INFO - Iter [2250/6924] lr: 1.667e-03, eta: 0:18:10, time: 0.204, data_time: 0.009, memory: 11396, loss_cls: 0.1815, loss_bbox: 0.4287, loss_centerness: 0.3876, loss: 0.9977, grad_norm: 6.0440 2022-11-26 15:40:29,369 - mmdet - INFO - Iter [2300/6924] lr: 1.667e-03, eta: 0:17:54, time: 0.194, data_time: 0.009, memory: 11396, loss_cls: 0.1031, loss_bbox: 0.3911, loss_centerness: 0.4055, loss: 0.8997, grad_norm: 5.4925 2022-11-26 15:40:31,329 - mmdet - INFO - Saving checkpoint at 4 epochs 2022-11-26 15:40:45,868 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1722 | 0.973 | 0.877 | +-------+-----+------+--------+-------+ | mAP | | | | 0.877 | +-------+-----+------+--------+-------+ 2022-11-26 15:40:49,557 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1722 | 0.953 | 0.864 | +-------+-----+------+--------+-------+ | mAP | | | | 0.864 | +-------+-----+------+--------+-------+ 2022-11-26 15:40:54,927 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1722 | 0.933 | 0.837 | +-------+-----+------+--------+-------+ | mAP | | | | 0.837 | +-------+-----+------+--------+-------+ 2022-11-26 15:40:58,416 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1722 | 0.920 | 0.821 | +-------+-----+------+--------+-------+ | mAP | | | | 0.821 | +-------+-----+------+--------+-------+ 2022-11-26 15:41:02,229 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1722 | 0.913 | 0.787 | +-------+-----+------+--------+-------+ | mAP | | | | 0.787 | +-------+-----+------+--------+-------+ 2022-11-26 15:41:05,450 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1722 | 0.880 | 0.719 | +-------+-----+------+--------+-------+ | mAP | | | | 0.719 | +-------+-----+------+--------+-------+ 2022-11-26 15:41:09,269 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1722 | 0.853 | 0.665 | +-------+-----+------+--------+-------+ | mAP | | | | 0.665 | +-------+-----+------+--------+-------+ 2022-11-26 15:41:15,607 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1722 | 0.753 | 0.513 | +-------+-----+------+--------+-------+ | mAP | | | | 0.513 | +-------+-----+------+--------+-------+ 2022-11-26 15:41:18,882 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1722 | 0.607 | 0.345 | +-------+-----+------+--------+-------+ | mAP | | | | 0.345 | +-------+-----+------+--------+-------+ 2022-11-26 15:41:18,887 - mmdet - INFO - Iter(val) [256] NoCoAP10: 0.8770, NoCoAP20: 0.8640, NoCoAP30: 0.8370, NoCoAP40: 0.8210, NoCoAP50: 0.7870, NoCoAP60: 0.7190, NoCoAP70: 0.6650, NoCoAP80: 0.5130, NoCoAP90: 0.3450, mNoCoAP: 0.7141 2022-11-26 15:41:30,465 - mmdet - INFO - Iter [2350/6924] lr: 1.667e-03, eta: 0:17:47, time: 0.275, data_time: 0.089, memory: 11396, loss_cls: 0.1201, loss_bbox: 0.3838, loss_centerness: 0.3747, loss: 0.8786, grad_norm: 5.4078 2022-11-26 15:41:39,728 - mmdet - INFO - Iter [2400/6924] lr: 1.667e-03, eta: 0:17:31, time: 0.185, data_time: 0.007, memory: 11396, loss_cls: 0.1114, loss_bbox: 0.3683, loss_centerness: 0.3922, loss: 0.8720, grad_norm: 6.0106 2022-11-26 15:41:49,904 - mmdet - INFO - Iter [2450/6924] lr: 1.667e-03, eta: 0:17:16, time: 0.204, data_time: 0.008, memory: 11396, loss_cls: 0.1262, loss_bbox: 0.3707, loss_centerness: 0.3942, loss: 0.8912, grad_norm: 5.8150 2022-11-26 15:41:59,269 - mmdet - INFO - Iter [2500/6924] lr: 1.667e-03, eta: 0:17:01, time: 0.187, data_time: 0.007, memory: 11396, loss_cls: 0.0924, loss_bbox: 0.3291, loss_centerness: 0.3735, loss: 0.7950, grad_norm: 5.2601 2022-11-26 15:42:08,438 - mmdet - INFO - Iter [2550/6924] lr: 1.667e-03, eta: 0:16:45, time: 0.183, data_time: 0.008, memory: 11396, loss_cls: 0.1713, loss_bbox: 0.3861, loss_centerness: 0.3738, loss: 0.9312, grad_norm: 7.3161 2022-11-26 15:42:17,554 - mmdet - INFO - Iter [2600/6924] lr: 1.667e-03, eta: 0:16:30, time: 0.182, data_time: 0.008, memory: 11396, loss_cls: 0.1413, loss_bbox: 0.4110, loss_centerness: 0.3601, loss: 0.9125, grad_norm: 6.6474 2022-11-26 15:42:27,624 - mmdet - INFO - Iter [2650/6924] lr: 1.667e-03, eta: 0:16:16, time: 0.201, data_time: 0.007, memory: 11396, loss_cls: 0.1402, loss_bbox: 0.3904, loss_centerness: 0.3765, loss: 0.9071, grad_norm: 6.8744 2022-11-26 15:42:37,260 - mmdet - INFO - Iter [2700/6924] lr: 1.667e-03, eta: 0:16:02, time: 0.193, data_time: 0.008, memory: 11396, loss_cls: 0.1217, loss_bbox: 0.3999, loss_centerness: 0.3853, loss: 0.9068, grad_norm: 6.0849 2022-11-26 15:42:47,122 - mmdet - INFO - Iter [2750/6924] lr: 1.667e-03, eta: 0:15:48, time: 0.197, data_time: 0.008, memory: 11396, loss_cls: 0.1235, loss_bbox: 0.3873, loss_centerness: 0.3668, loss: 0.8776, grad_norm: 6.3654 2022-11-26 15:42:57,115 - mmdet - INFO - Iter [2800/6924] lr: 1.667e-03, eta: 0:15:35, time: 0.200, data_time: 0.008, memory: 11396, loss_cls: 0.1115, loss_bbox: 0.3435, loss_centerness: 0.4193, loss: 0.8744, grad_norm: 5.8415 2022-11-26 15:43:06,575 - mmdet - INFO - Iter [2850/6924] lr: 1.667e-03, eta: 0:15:21, time: 0.189, data_time: 0.008, memory: 11396, loss_cls: 0.1612, loss_bbox: 0.3583, loss_centerness: 0.3820, loss: 0.9015, grad_norm: 7.6913 2022-11-26 15:43:13,890 - mmdet - INFO - Saving checkpoint at 5 epochs 2022-11-26 15:43:28,274 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2063 | 0.980 | 0.885 | +-------+-----+------+--------+-------+ | mAP | | | | 0.885 | +-------+-----+------+--------+-------+ 2022-11-26 15:43:32,042 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2063 | 0.973 | 0.883 | +-------+-----+------+--------+-------+ | mAP | | | | 0.883 | +-------+-----+------+--------+-------+ 2022-11-26 15:43:35,907 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2063 | 0.960 | 0.849 | +-------+-----+------+--------+-------+ | mAP | | | | 0.849 | +-------+-----+------+--------+-------+ 2022-11-26 15:43:41,640 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2063 | 0.940 | 0.830 | +-------+-----+------+--------+-------+ | mAP | | | | 0.830 | +-------+-----+------+--------+-------+ 2022-11-26 15:43:45,340 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2063 | 0.907 | 0.753 | +-------+-----+------+--------+-------+ | mAP | | | | 0.753 | +-------+-----+------+--------+-------+ 2022-11-26 15:43:48,968 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2063 | 0.893 | 0.721 | +-------+-----+------+--------+-------+ | mAP | | | | 0.721 | +-------+-----+------+--------+-------+ 2022-11-26 15:43:55,400 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2063 | 0.867 | 0.650 | +-------+-----+------+--------+-------+ | mAP | | | | 0.650 | +-------+-----+------+--------+-------+ 2022-11-26 15:43:58,739 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2063 | 0.820 | 0.528 | +-------+-----+------+--------+-------+ | mAP | | | | 0.528 | +-------+-----+------+--------+-------+ 2022-11-26 15:44:02,897 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2063 | 0.633 | 0.326 | +-------+-----+------+--------+-------+ | mAP | | | | 0.326 | +-------+-----+------+--------+-------+ 2022-11-26 15:44:02,902 - mmdet - INFO - Iter(val) [256] NoCoAP10: 0.8850, NoCoAP20: 0.8830, NoCoAP30: 0.8490, NoCoAP40: 0.8300, NoCoAP50: 0.7530, NoCoAP60: 0.7210, NoCoAP70: 0.6500, NoCoAP80: 0.5280, NoCoAP90: 0.3260, mNoCoAP: 0.7140 2022-11-26 15:44:10,202 - mmdet - INFO - Iter [2900/6924] lr: 1.667e-03, eta: 0:15:27, time: 0.484, data_time: 0.250, memory: 11396, loss_cls: 0.1328, loss_bbox: 0.3288, loss_centerness: 0.3235, loss: 0.7850, grad_norm: 4.4004 2022-11-26 15:44:20,113 - mmdet - INFO - Iter [2950/6924] lr: 1.667e-03, eta: 0:15:14, time: 0.198, data_time: 0.009, memory: 11396, loss_cls: 0.0952, loss_bbox: 0.3070, loss_centerness: 0.3756, loss: 0.7779, grad_norm: 5.1312 2022-11-26 15:44:29,786 - mmdet - INFO - Exp name: sirstv2_fcos_rfla_r50_kld_1x.py 2022-11-26 15:44:29,787 - mmdet - INFO - Iter [3000/6924] lr: 1.667e-03, eta: 0:15:00, time: 0.193, data_time: 0.009, memory: 11396, loss_cls: 0.1004, loss_bbox: 0.3707, loss_centerness: 0.4252, loss: 0.8962, grad_norm: 5.4394 2022-11-26 15:44:39,838 - mmdet - INFO - Iter [3050/6924] lr: 1.667e-03, eta: 0:14:46, time: 0.201, data_time: 0.009, memory: 11396, loss_cls: 0.0942, loss_bbox: 0.3205, loss_centerness: 0.3803, loss: 0.7950, grad_norm: 4.8847 2022-11-26 15:44:49,699 - mmdet - INFO - Iter [3100/6924] lr: 1.667e-03, eta: 0:14:33, time: 0.197, data_time: 0.008, memory: 11396, loss_cls: 0.0830, loss_bbox: 0.3423, loss_centerness: 0.3778, loss: 0.8031, grad_norm: 5.1532 2022-11-26 15:44:59,624 - mmdet - INFO - Iter [3150/6924] lr: 1.667e-03, eta: 0:14:20, time: 0.198, data_time: 0.008, memory: 11396, loss_cls: 0.1162, loss_bbox: 0.3250, loss_centerness: 0.3998, loss: 0.8411, grad_norm: 5.3996 2022-11-26 15:45:09,287 - mmdet - INFO - Iter [3200/6924] lr: 1.667e-03, eta: 0:14:06, time: 0.193, data_time: 0.008, memory: 11396, loss_cls: 0.0966, loss_bbox: 0.3576, loss_centerness: 0.3550, loss: 0.8091, grad_norm: 5.1002 2022-11-26 15:45:19,505 - mmdet - INFO - Iter [3250/6924] lr: 1.667e-03, eta: 0:13:54, time: 0.204, data_time: 0.009, memory: 11396, loss_cls: 0.1022, loss_bbox: 0.3519, loss_centerness: 0.3600, loss: 0.8140, grad_norm: 5.7114 2022-11-26 15:45:29,963 - mmdet - INFO - Iter [3300/6924] lr: 1.667e-03, eta: 0:13:41, time: 0.209, data_time: 0.008, memory: 11396, loss_cls: 0.1565, loss_bbox: 0.3335, loss_centerness: 0.3472, loss: 0.8372, grad_norm: 6.0475 2022-11-26 15:45:39,825 - mmdet - INFO - Iter [3350/6924] lr: 1.667e-03, eta: 0:13:28, time: 0.197, data_time: 0.008, memory: 11396, loss_cls: 0.1139, loss_bbox: 0.3214, loss_centerness: 0.3516, loss: 0.7868, grad_norm: 5.4690 2022-11-26 15:45:49,521 - mmdet - INFO - Iter [3400/6924] lr: 1.667e-03, eta: 0:13:15, time: 0.194, data_time: 0.008, memory: 11396, loss_cls: 0.0744, loss_bbox: 0.3119, loss_centerness: 0.3595, loss: 0.7458, grad_norm: 5.0346 2022-11-26 15:45:59,305 - mmdet - INFO - Iter [3450/6924] lr: 1.667e-03, eta: 0:13:03, time: 0.196, data_time: 0.008, memory: 11396, loss_cls: 0.0950, loss_bbox: 0.2947, loss_centerness: 0.3786, loss: 0.7683, grad_norm: 5.9947 2022-11-26 15:46:01,985 - mmdet - INFO - Saving checkpoint at 6 epochs 2022-11-26 15:46:16,658 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1395 | 0.947 | 0.861 | +-------+-----+------+--------+-------+ | mAP | | | | 0.861 | +-------+-----+------+--------+-------+ 2022-11-26 15:46:21,301 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1395 | 0.940 | 0.858 | +-------+-----+------+--------+-------+ | mAP | | | | 0.858 | +-------+-----+------+--------+-------+ 2022-11-26 15:46:25,023 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1395 | 0.920 | 0.826 | +-------+-----+------+--------+-------+ | mAP | | | | 0.826 | +-------+-----+------+--------+-------+ 2022-11-26 15:46:28,399 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1395 | 0.913 | 0.802 | +-------+-----+------+--------+-------+ | mAP | | | | 0.802 | +-------+-----+------+--------+-------+ 2022-11-26 15:46:32,537 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1395 | 0.900 | 0.751 | +-------+-----+------+--------+-------+ | mAP | | | | 0.751 | +-------+-----+------+--------+-------+ 2022-11-26 15:46:36,468 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1395 | 0.893 | 0.688 | +-------+-----+------+--------+-------+ | mAP | | | | 0.688 | +-------+-----+------+--------+-------+ 2022-11-26 15:46:39,779 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1395 | 0.880 | 0.641 | +-------+-----+------+--------+-------+ | mAP | | | | 0.641 | +-------+-----+------+--------+-------+ 2022-11-26 15:46:43,264 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1395 | 0.813 | 0.522 | +-------+-----+------+--------+-------+ | mAP | | | | 0.522 | +-------+-----+------+--------+-------+ 2022-11-26 15:46:46,662 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1395 | 0.667 | 0.316 | +-------+-----+------+--------+-------+ | mAP | | | | 0.316 | +-------+-----+------+--------+-------+ 2022-11-26 15:46:46,670 - mmdet - INFO - Iter(val) [256] NoCoAP10: 0.8610, NoCoAP20: 0.8580, NoCoAP30: 0.8260, NoCoAP40: 0.8020, NoCoAP50: 0.7510, NoCoAP60: 0.6880, NoCoAP70: 0.6410, NoCoAP80: 0.5220, NoCoAP90: 0.3160, mNoCoAP: 0.6961 2022-11-26 15:46:57,717 - mmdet - INFO - Iter [3500/6924] lr: 1.667e-03, eta: 0:12:55, time: 0.290, data_time: 0.100, memory: 11396, loss_cls: 0.1576, loss_bbox: 0.3455, loss_centerness: 0.3870, loss: 0.8901, grad_norm: 6.9315 2022-11-26 15:47:06,994 - mmdet - INFO - Iter [3550/6924] lr: 1.667e-03, eta: 0:12:41, time: 0.186, data_time: 0.009, memory: 11396, loss_cls: 0.1182, loss_bbox: 0.3255, loss_centerness: 0.3818, loss: 0.8255, grad_norm: 5.9179 2022-11-26 15:47:16,178 - mmdet - INFO - Iter [3600/6924] lr: 1.667e-03, eta: 0:12:28, time: 0.184, data_time: 0.007, memory: 11396, loss_cls: 0.1086, loss_bbox: 0.3079, loss_centerness: 0.3385, loss: 0.7550, grad_norm: 6.1168 2022-11-26 15:47:26,110 - mmdet - INFO - Iter [3650/6924] lr: 1.667e-03, eta: 0:12:16, time: 0.199, data_time: 0.008, memory: 11396, loss_cls: 0.0791, loss_bbox: 0.3357, loss_centerness: 0.4264, loss: 0.8413, grad_norm: 5.6596 2022-11-26 15:47:36,323 - mmdet - INFO - Iter [3700/6924] lr: 1.667e-03, eta: 0:12:03, time: 0.204, data_time: 0.008, memory: 11396, loss_cls: 0.1435, loss_bbox: 0.3383, loss_centerness: 0.3685, loss: 0.8504, grad_norm: 7.1854 2022-11-26 15:47:46,355 - mmdet - INFO - Iter [3750/6924] lr: 1.667e-03, eta: 0:11:51, time: 0.201, data_time: 0.008, memory: 11396, loss_cls: 0.0843, loss_bbox: 0.3021, loss_centerness: 0.3622, loss: 0.7486, grad_norm: 5.1051 2022-11-26 15:47:56,089 - mmdet - INFO - Iter [3800/6924] lr: 1.667e-03, eta: 0:11:39, time: 0.195, data_time: 0.008, memory: 11396, loss_cls: 0.0815, loss_bbox: 0.3319, loss_centerness: 0.3814, loss: 0.7948, grad_norm: 4.9241 2022-11-26 15:48:05,471 - mmdet - INFO - Iter [3850/6924] lr: 1.667e-03, eta: 0:11:26, time: 0.188, data_time: 0.008, memory: 11396, loss_cls: 0.0827, loss_bbox: 0.3101, loss_centerness: 0.3368, loss: 0.7296, grad_norm: 5.1997 2022-11-26 15:48:14,790 - mmdet - INFO - Iter [3900/6924] lr: 1.667e-03, eta: 0:11:14, time: 0.186, data_time: 0.008, memory: 11396, loss_cls: 0.0829, loss_bbox: 0.3039, loss_centerness: 0.3988, loss: 0.7856, grad_norm: 5.8320 2022-11-26 15:48:24,817 - mmdet - INFO - Iter [3950/6924] lr: 1.667e-03, eta: 0:11:02, time: 0.201, data_time: 0.008, memory: 11396, loss_cls: 0.1203, loss_bbox: 0.3267, loss_centerness: 0.3641, loss: 0.8111, grad_norm: 5.7177 2022-11-26 15:48:34,613 - mmdet - INFO - Exp name: sirstv2_fcos_rfla_r50_kld_1x.py 2022-11-26 15:48:34,614 - mmdet - INFO - Iter [4000/6924] lr: 1.667e-03, eta: 0:10:49, time: 0.196, data_time: 0.007, memory: 11396, loss_cls: 0.1081, loss_bbox: 0.3496, loss_centerness: 0.4044, loss: 0.8621, grad_norm: 6.1066 2022-11-26 15:48:41,793 - mmdet - INFO - Saving checkpoint at 7 epochs 2022-11-26 15:48:54,805 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 993 | 0.940 | 0.902 | +-------+-----+------+--------+-------+ | mAP | | | | 0.902 | +-------+-----+------+--------+-------+ 2022-11-26 15:48:57,987 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 993 | 0.940 | 0.900 | +-------+-----+------+--------+-------+ | mAP | | | | 0.900 | +-------+-----+------+--------+-------+ 2022-11-26 15:49:04,351 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 993 | 0.920 | 0.878 | +-------+-----+------+--------+-------+ | mAP | | | | 0.878 | +-------+-----+------+--------+-------+ 2022-11-26 15:49:07,816 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 993 | 0.913 | 0.874 | +-------+-----+------+--------+-------+ | mAP | | | | 0.874 | +-------+-----+------+--------+-------+ 2022-11-26 15:49:11,663 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 993 | 0.893 | 0.829 | +-------+-----+------+--------+-------+ | mAP | | | | 0.829 | +-------+-----+------+--------+-------+ 2022-11-26 15:49:15,295 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 993 | 0.873 | 0.756 | +-------+-----+------+--------+-------+ | mAP | | | | 0.756 | +-------+-----+------+--------+-------+ 2022-11-26 15:49:19,179 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 993 | 0.860 | 0.728 | +-------+-----+------+--------+-------+ | mAP | | | | 0.728 | +-------+-----+------+--------+-------+ 2022-11-26 15:49:24,719 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 993 | 0.787 | 0.598 | +-------+-----+------+--------+-------+ | mAP | | | | 0.598 | +-------+-----+------+--------+-------+ 2022-11-26 15:49:28,114 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 993 | 0.600 | 0.397 | +-------+-----+------+--------+-------+ | mAP | | | | 0.397 | +-------+-----+------+--------+-------+ 2022-11-26 15:49:28,120 - mmdet - INFO - Iter(val) [256] NoCoAP10: 0.9020, NoCoAP20: 0.9000, NoCoAP30: 0.8780, NoCoAP40: 0.8740, NoCoAP50: 0.8290, NoCoAP60: 0.7560, NoCoAP70: 0.7280, NoCoAP80: 0.5980, NoCoAP90: 0.3970, mNoCoAP: 0.7624 2022-11-26 15:49:33,725 - mmdet - INFO - Iter [4050/6924] lr: 1.667e-03, eta: 0:10:48, time: 0.507, data_time: 0.340, memory: 11396, loss_cls: 0.0930, loss_bbox: 0.3624, loss_centerness: 0.3387, loss: 0.7941, grad_norm: 6.0575 2022-11-26 15:49:43,328 - mmdet - INFO - Iter [4100/6924] lr: 1.667e-03, eta: 0:10:36, time: 0.192, data_time: 0.007, memory: 11396, loss_cls: 0.0852, loss_bbox: 0.3165, loss_centerness: 0.4036, loss: 0.8053, grad_norm: 4.9159 2022-11-26 15:49:52,797 - mmdet - INFO - Iter [4150/6924] lr: 1.667e-03, eta: 0:10:23, time: 0.189, data_time: 0.007, memory: 11396, loss_cls: 0.0872, loss_bbox: 0.3398, loss_centerness: 0.3772, loss: 0.8041, grad_norm: 4.7402 2022-11-26 15:50:02,100 - mmdet - INFO - Iter [4200/6924] lr: 1.667e-03, eta: 0:10:11, time: 0.186, data_time: 0.007, memory: 11396, loss_cls: 0.0692, loss_bbox: 0.3281, loss_centerness: 0.3480, loss: 0.7453, grad_norm: 4.7181 2022-11-26 15:50:11,925 - mmdet - INFO - Iter [4250/6924] lr: 1.667e-03, eta: 0:09:59, time: 0.197, data_time: 0.007, memory: 11396, loss_cls: 0.1693, loss_bbox: 0.3402, loss_centerness: 0.3655, loss: 0.8750, grad_norm: 9.0703 2022-11-26 15:50:21,755 - mmdet - INFO - Iter [4300/6924] lr: 1.667e-03, eta: 0:09:47, time: 0.197, data_time: 0.007, memory: 11396, loss_cls: 0.1418, loss_bbox: 0.3295, loss_centerness: 0.3953, loss: 0.8666, grad_norm: 7.0591 2022-11-26 15:50:32,133 - mmdet - INFO - Iter [4350/6924] lr: 1.667e-03, eta: 0:09:35, time: 0.208, data_time: 0.007, memory: 11396, loss_cls: 0.0950, loss_bbox: 0.2915, loss_centerness: 0.3551, loss: 0.7415, grad_norm: 4.9860 2022-11-26 15:50:41,489 - mmdet - INFO - Iter [4400/6924] lr: 1.667e-03, eta: 0:09:23, time: 0.187, data_time: 0.008, memory: 11396, loss_cls: 0.0737, loss_bbox: 0.2906, loss_centerness: 0.3840, loss: 0.7483, grad_norm: 4.5237 2022-11-26 15:50:50,917 - mmdet - INFO - Iter [4450/6924] lr: 1.667e-03, eta: 0:09:11, time: 0.189, data_time: 0.007, memory: 11396, loss_cls: 0.0832, loss_bbox: 0.2943, loss_centerness: 0.3664, loss: 0.7439, grad_norm: 5.3607 2022-11-26 15:51:00,190 - mmdet - INFO - Iter [4500/6924] lr: 1.667e-03, eta: 0:08:59, time: 0.185, data_time: 0.008, memory: 11396, loss_cls: 0.0643, loss_bbox: 0.3161, loss_centerness: 0.3877, loss: 0.7680, grad_norm: 4.6917 2022-11-26 15:51:10,162 - mmdet - INFO - Iter [4550/6924] lr: 1.667e-03, eta: 0:08:47, time: 0.199, data_time: 0.008, memory: 11396, loss_cls: 0.1009, loss_bbox: 0.3262, loss_centerness: 0.3633, loss: 0.7904, grad_norm: 4.8745 2022-11-26 15:51:19,038 - mmdet - INFO - Iter [4600/6924] lr: 1.667e-03, eta: 0:08:35, time: 0.178, data_time: 0.008, memory: 11396, loss_cls: 0.0618, loss_bbox: 0.3203, loss_centerness: 0.3693, loss: 0.7514, grad_norm: 5.1043 2022-11-26 15:51:22,489 - mmdet - INFO - Saving checkpoint at 8 epochs 2022-11-26 15:51:37,753 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1459 | 0.953 | 0.918 | +-------+-----+------+--------+-------+ | mAP | | | | 0.918 | +-------+-----+------+--------+-------+ 2022-11-26 15:51:44,107 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1459 | 0.953 | 0.908 | +-------+-----+------+--------+-------+ | mAP | | | | 0.908 | +-------+-----+------+--------+-------+ 2022-11-26 15:51:49,922 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1459 | 0.947 | 0.895 | +-------+-----+------+--------+-------+ | mAP | | | | 0.895 | +-------+-----+------+--------+-------+ 2022-11-26 15:51:57,452 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1459 | 0.927 | 0.868 | +-------+-----+------+--------+-------+ | mAP | | | | 0.868 | +-------+-----+------+--------+-------+ 2022-11-26 15:52:01,683 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1459 | 0.900 | 0.847 | +-------+-----+------+--------+-------+ | mAP | | | | 0.847 | +-------+-----+------+--------+-------+ 2022-11-26 15:52:06,577 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1459 | 0.880 | 0.802 | +-------+-----+------+--------+-------+ | mAP | | | | 0.802 | +-------+-----+------+--------+-------+ 2022-11-26 15:52:10,586 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1459 | 0.860 | 0.702 | +-------+-----+------+--------+-------+ | mAP | | | | 0.702 | +-------+-----+------+--------+-------+ 2022-11-26 15:52:14,424 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1459 | 0.793 | 0.614 | +-------+-----+------+--------+-------+ | mAP | | | | 0.614 | +-------+-----+------+--------+-------+ 2022-11-26 15:52:18,042 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1459 | 0.673 | 0.460 | +-------+-----+------+--------+-------+ | mAP | | | | 0.460 | +-------+-----+------+--------+-------+ 2022-11-26 15:52:18,050 - mmdet - INFO - Iter(val) [256] NoCoAP10: 0.9180, NoCoAP20: 0.9080, NoCoAP30: 0.8950, NoCoAP40: 0.8680, NoCoAP50: 0.8470, NoCoAP60: 0.8020, NoCoAP70: 0.7020, NoCoAP80: 0.6140, NoCoAP90: 0.4600, mNoCoAP: 0.7796 2022-11-26 15:52:28,177 - mmdet - INFO - Iter [4650/6924] lr: 1.667e-04, eta: 0:08:25, time: 0.297, data_time: 0.113, memory: 11396, loss_cls: 0.0617, loss_bbox: 0.2872, loss_centerness: 0.3419, loss: 0.6908, grad_norm: 4.6058 2022-11-26 15:52:37,628 - mmdet - INFO - Iter [4700/6924] lr: 1.667e-04, eta: 0:08:14, time: 0.189, data_time: 0.008, memory: 11396, loss_cls: 0.0501, loss_bbox: 0.2601, loss_centerness: 0.3626, loss: 0.6728, grad_norm: 4.1774 2022-11-26 15:52:47,234 - mmdet - INFO - Iter [4750/6924] lr: 1.667e-04, eta: 0:08:02, time: 0.192, data_time: 0.009, memory: 11396, loss_cls: 0.0711, loss_bbox: 0.2767, loss_centerness: 0.3633, loss: 0.7111, grad_norm: 4.7251 2022-11-26 15:52:56,880 - mmdet - INFO - Iter [4800/6924] lr: 1.667e-04, eta: 0:07:50, time: 0.193, data_time: 0.008, memory: 11396, loss_cls: 0.0620, loss_bbox: 0.2387, loss_centerness: 0.3628, loss: 0.6635, grad_norm: 4.0699 2022-11-26 15:53:06,391 - mmdet - INFO - Iter [4850/6924] lr: 1.667e-04, eta: 0:07:38, time: 0.190, data_time: 0.009, memory: 11396, loss_cls: 0.0458, loss_bbox: 0.2357, loss_centerness: 0.3508, loss: 0.6324, grad_norm: 3.9059 2022-11-26 15:53:16,364 - mmdet - INFO - Iter [4900/6924] lr: 1.667e-04, eta: 0:07:27, time: 0.199, data_time: 0.008, memory: 11396, loss_cls: 0.0615, loss_bbox: 0.2423, loss_centerness: 0.3691, loss: 0.6729, grad_norm: 5.1695 2022-11-26 15:53:25,629 - mmdet - INFO - Iter [4950/6924] lr: 1.667e-04, eta: 0:07:15, time: 0.185, data_time: 0.010, memory: 11396, loss_cls: 0.0528, loss_bbox: 0.2506, loss_centerness: 0.4080, loss: 0.7114, grad_norm: 4.7617 2022-11-26 15:53:34,825 - mmdet - INFO - Exp name: sirstv2_fcos_rfla_r50_kld_1x.py 2022-11-26 15:53:34,826 - mmdet - INFO - Iter [5000/6924] lr: 1.667e-04, eta: 0:07:03, time: 0.184, data_time: 0.008, memory: 11396, loss_cls: 0.0468, loss_bbox: 0.2162, loss_centerness: 0.3529, loss: 0.6159, grad_norm: 4.1643 2022-11-26 15:53:45,496 - mmdet - INFO - Iter [5050/6924] lr: 5.000e-04, eta: 0:06:52, time: 0.213, data_time: 0.010, memory: 11396, loss_cls: 0.0465, loss_bbox: 0.2606, loss_centerness: 0.3703, loss: 0.6774, grad_norm: 4.6454 2022-11-26 15:53:54,989 - mmdet - INFO - Iter [5100/6924] lr: 5.000e-04, eta: 0:06:41, time: 0.190, data_time: 0.008, memory: 11396, loss_cls: 0.0562, loss_bbox: 0.2368, loss_centerness: 0.3587, loss: 0.6517, grad_norm: 4.2083 2022-11-26 15:54:04,431 - mmdet - INFO - Iter [5150/6924] lr: 5.000e-04, eta: 0:06:29, time: 0.189, data_time: 0.008, memory: 11396, loss_cls: 0.0514, loss_bbox: 0.2504, loss_centerness: 0.3073, loss: 0.6091, grad_norm: 4.3746 2022-11-26 15:54:13,431 - mmdet - INFO - Saving checkpoint at 9 epochs 2022-11-26 15:54:28,942 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1668 | 0.960 | 0.923 | +-------+-----+------+--------+-------+ | mAP | | | | 0.923 | +-------+-----+------+--------+-------+ 2022-11-26 15:54:33,925 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1668 | 0.960 | 0.912 | +-------+-----+------+--------+-------+ | mAP | | | | 0.912 | +-------+-----+------+--------+-------+ 2022-11-26 15:54:38,569 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1668 | 0.953 | 0.898 | +-------+-----+------+--------+-------+ | mAP | | | | 0.898 | +-------+-----+------+--------+-------+ 2022-11-26 15:54:42,985 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1668 | 0.933 | 0.866 | +-------+-----+------+--------+-------+ | mAP | | | | 0.866 | +-------+-----+------+--------+-------+ 2022-11-26 15:54:48,499 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1668 | 0.920 | 0.811 | +-------+-----+------+--------+-------+ | mAP | | | | 0.811 | +-------+-----+------+--------+-------+ 2022-11-26 15:54:56,235 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1668 | 0.900 | 0.731 | +-------+-----+------+--------+-------+ | mAP | | | | 0.731 | +-------+-----+------+--------+-------+ 2022-11-26 15:55:04,567 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1668 | 0.847 | 0.652 | +-------+-----+------+--------+-------+ | mAP | | | | 0.652 | +-------+-----+------+--------+-------+ 2022-11-26 15:55:08,463 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1668 | 0.733 | 0.490 | +-------+-----+------+--------+-------+ | mAP | | | | 0.490 | +-------+-----+------+--------+-------+ 2022-11-26 15:55:13,063 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1668 | 0.553 | 0.288 | +-------+-----+------+--------+-------+ | mAP | | | | 0.288 | +-------+-----+------+--------+-------+ 2022-11-26 15:55:13,068 - mmdet - INFO - Iter(val) [256] NoCoAP10: 0.9230, NoCoAP20: 0.9120, NoCoAP30: 0.8980, NoCoAP40: 0.8660, NoCoAP50: 0.8110, NoCoAP60: 0.7310, NoCoAP70: 0.6520, NoCoAP80: 0.4900, NoCoAP90: 0.2880, mNoCoAP: 0.7301 2022-11-26 15:55:17,700 - mmdet - INFO - Iter [5200/6924] lr: 5.000e-04, eta: 0:06:25, time: 0.657, data_time: 0.487, memory: 11396, loss_cls: 0.0324, loss_bbox: 0.1571, loss_centerness: 0.2978, loss: 0.4874, grad_norm: 4.7503 2022-11-26 15:55:27,676 - mmdet - INFO - Iter [5250/6924] lr: 5.000e-04, eta: 0:06:14, time: 0.199, data_time: 0.009, memory: 11396, loss_cls: 0.0580, loss_bbox: 0.2404, loss_centerness: 0.3835, loss: 0.6819, grad_norm: 4.8361 2022-11-26 15:55:37,245 - mmdet - INFO - Iter [5300/6924] lr: 5.000e-04, eta: 0:06:02, time: 0.191, data_time: 0.009, memory: 11396, loss_cls: 0.0609, loss_bbox: 0.2500, loss_centerness: 0.3765, loss: 0.6874, grad_norm: 5.2440 2022-11-26 15:55:47,101 - mmdet - INFO - Iter [5350/6924] lr: 5.000e-04, eta: 0:05:51, time: 0.197, data_time: 0.008, memory: 11396, loss_cls: 0.0605, loss_bbox: 0.2217, loss_centerness: 0.3698, loss: 0.6520, grad_norm: 4.7438 2022-11-26 15:55:56,476 - mmdet - INFO - Iter [5400/6924] lr: 5.000e-04, eta: 0:05:39, time: 0.188, data_time: 0.009, memory: 11396, loss_cls: 0.0542, loss_bbox: 0.2690, loss_centerness: 0.3692, loss: 0.6924, grad_norm: 4.7085 2022-11-26 15:56:06,176 - mmdet - INFO - Iter [5450/6924] lr: 5.000e-04, eta: 0:05:27, time: 0.194, data_time: 0.008, memory: 11396, loss_cls: 0.0422, loss_bbox: 0.2414, loss_centerness: 0.3455, loss: 0.6291, grad_norm: 5.3644 2022-11-26 15:56:17,266 - mmdet - INFO - Iter [5500/6924] lr: 5.000e-04, eta: 0:05:16, time: 0.222, data_time: 0.010, memory: 11396, loss_cls: 0.0442, loss_bbox: 0.2478, loss_centerness: 0.3626, loss: 0.6545, grad_norm: 4.6933 2022-11-26 15:56:27,580 - mmdet - INFO - Iter [5550/6924] lr: 5.000e-04, eta: 0:05:05, time: 0.206, data_time: 0.009, memory: 11396, loss_cls: 0.0493, loss_bbox: 0.2450, loss_centerness: 0.3746, loss: 0.6690, grad_norm: 4.5329 2022-11-26 15:56:36,950 - mmdet - INFO - Iter [5600/6924] lr: 5.000e-04, eta: 0:04:53, time: 0.187, data_time: 0.008, memory: 11396, loss_cls: 0.0463, loss_bbox: 0.2477, loss_centerness: 0.3163, loss: 0.6103, grad_norm: 4.4271 2022-11-26 15:56:45,833 - mmdet - INFO - Iter [5650/6924] lr: 5.000e-04, eta: 0:04:42, time: 0.178, data_time: 0.008, memory: 11396, loss_cls: 0.0414, loss_bbox: 0.2201, loss_centerness: 0.3773, loss: 0.6388, grad_norm: 4.7961 2022-11-26 15:56:55,814 - mmdet - INFO - Iter [5700/6924] lr: 5.000e-04, eta: 0:04:30, time: 0.200, data_time: 0.009, memory: 11396, loss_cls: 0.0501, loss_bbox: 0.2307, loss_centerness: 0.3720, loss: 0.6528, grad_norm: 4.4307 2022-11-26 15:57:05,691 - mmdet - INFO - Iter [5750/6924] lr: 5.000e-04, eta: 0:04:19, time: 0.198, data_time: 0.008, memory: 11396, loss_cls: 0.0643, loss_bbox: 0.2563, loss_centerness: 0.3618, loss: 0.6824, grad_norm: 5.4826 2022-11-26 15:57:09,793 - mmdet - INFO - Saving checkpoint at 10 epochs 2022-11-26 15:57:26,876 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2110 | 0.973 | 0.925 | +-------+-----+------+--------+-------+ | mAP | | | | 0.925 | +-------+-----+------+--------+-------+ 2022-11-26 15:57:31,448 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2110 | 0.973 | 0.907 | +-------+-----+------+--------+-------+ | mAP | | | | 0.907 | +-------+-----+------+--------+-------+ 2022-11-26 15:57:36,894 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2110 | 0.953 | 0.891 | +-------+-----+------+--------+-------+ | mAP | | | | 0.891 | +-------+-----+------+--------+-------+ 2022-11-26 15:57:43,624 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2110 | 0.927 | 0.874 | +-------+-----+------+--------+-------+ | mAP | | | | 0.874 | +-------+-----+------+--------+-------+ 2022-11-26 15:57:47,863 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2110 | 0.913 | 0.835 | +-------+-----+------+--------+-------+ | mAP | | | | 0.835 | +-------+-----+------+--------+-------+ 2022-11-26 15:57:52,340 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2110 | 0.873 | 0.776 | +-------+-----+------+--------+-------+ | mAP | | | | 0.776 | +-------+-----+------+--------+-------+ 2022-11-26 15:57:56,815 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2110 | 0.853 | 0.699 | +-------+-----+------+--------+-------+ | mAP | | | | 0.699 | +-------+-----+------+--------+-------+ 2022-11-26 15:58:03,458 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2110 | 0.753 | 0.555 | +-------+-----+------+--------+-------+ | mAP | | | | 0.555 | +-------+-----+------+--------+-------+ 2022-11-26 15:58:06,872 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 2110 | 0.587 | 0.360 | +-------+-----+------+--------+-------+ | mAP | | | | 0.360 | +-------+-----+------+--------+-------+ 2022-11-26 15:58:06,878 - mmdet - INFO - Iter(val) [256] NoCoAP10: 0.9250, NoCoAP20: 0.9070, NoCoAP30: 0.8910, NoCoAP40: 0.8740, NoCoAP50: 0.8350, NoCoAP60: 0.7760, NoCoAP70: 0.6990, NoCoAP80: 0.5550, NoCoAP90: 0.3600, mNoCoAP: 0.7580 2022-11-26 15:58:15,979 - mmdet - INFO - Iter [5800/6924] lr: 5.000e-04, eta: 0:04:09, time: 0.302, data_time: 0.123, memory: 11396, loss_cls: 0.0527, loss_bbox: 0.2623, loss_centerness: 0.3872, loss: 0.7022, grad_norm: 5.4070 2022-11-26 15:58:25,960 - mmdet - INFO - Iter [5850/6924] lr: 5.000e-04, eta: 0:03:58, time: 0.200, data_time: 0.008, memory: 11396, loss_cls: 0.0422, loss_bbox: 0.2505, loss_centerness: 0.3917, loss: 0.6844, grad_norm: 5.1429 2022-11-26 15:58:35,466 - mmdet - INFO - Iter [5900/6924] lr: 5.000e-04, eta: 0:03:46, time: 0.190, data_time: 0.009, memory: 11396, loss_cls: 0.0424, loss_bbox: 0.2472, loss_centerness: 0.3761, loss: 0.6656, grad_norm: 4.9799 2022-11-26 15:58:45,152 - mmdet - INFO - Iter [5950/6924] lr: 5.000e-04, eta: 0:03:35, time: 0.194, data_time: 0.008, memory: 11396, loss_cls: 0.0453, loss_bbox: 0.1940, loss_centerness: 0.3080, loss: 0.5473, grad_norm: 4.1503 2022-11-26 15:58:54,605 - mmdet - INFO - Exp name: sirstv2_fcos_rfla_r50_kld_1x.py 2022-11-26 15:58:54,606 - mmdet - INFO - Iter [6000/6924] lr: 5.000e-04, eta: 0:03:24, time: 0.189, data_time: 0.009, memory: 11396, loss_cls: 0.0427, loss_bbox: 0.2281, loss_centerness: 0.3903, loss: 0.6612, grad_norm: 4.7293 2022-11-26 15:59:04,196 - mmdet - INFO - Iter [6050/6924] lr: 5.000e-04, eta: 0:03:12, time: 0.192, data_time: 0.008, memory: 11396, loss_cls: 0.0408, loss_bbox: 0.2160, loss_centerness: 0.3336, loss: 0.5904, grad_norm: 4.7361 2022-11-26 15:59:13,043 - mmdet - INFO - Iter [6100/6924] lr: 5.000e-04, eta: 0:03:01, time: 0.177, data_time: 0.008, memory: 11396, loss_cls: 0.0468, loss_bbox: 0.2244, loss_centerness: 0.4041, loss: 0.6753, grad_norm: 4.9425 2022-11-26 15:59:22,608 - mmdet - INFO - Iter [6150/6924] lr: 5.000e-04, eta: 0:02:50, time: 0.191, data_time: 0.007, memory: 11396, loss_cls: 0.0353, loss_bbox: 0.2193, loss_centerness: 0.3675, loss: 0.6221, grad_norm: 4.7346 2022-11-26 15:59:31,765 - mmdet - INFO - Iter [6200/6924] lr: 5.000e-04, eta: 0:02:39, time: 0.183, data_time: 0.008, memory: 11396, loss_cls: 0.0524, loss_bbox: 0.2358, loss_centerness: 0.3413, loss: 0.6295, grad_norm: 5.6143 2022-11-26 15:59:41,095 - mmdet - INFO - Iter [6250/6924] lr: 5.000e-04, eta: 0:02:27, time: 0.187, data_time: 0.008, memory: 11396, loss_cls: 0.0631, loss_bbox: 0.2286, loss_centerness: 0.3568, loss: 0.6484, grad_norm: 4.7646 2022-11-26 15:59:50,734 - mmdet - INFO - Iter [6300/6924] lr: 5.000e-04, eta: 0:02:16, time: 0.193, data_time: 0.008, memory: 11396, loss_cls: 0.0435, loss_bbox: 0.2673, loss_centerness: 0.3359, loss: 0.6466, grad_norm: 5.0616 2022-11-26 16:00:00,696 - mmdet - INFO - Saving checkpoint at 11 epochs 2022-11-26 16:00:17,182 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1294 | 0.953 | 0.925 | +-------+-----+------+--------+-------+ | mAP | | | | 0.925 | +-------+-----+------+--------+-------+ 2022-11-26 16:00:23,121 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1294 | 0.953 | 0.915 | +-------+-----+------+--------+-------+ | mAP | | | | 0.915 | +-------+-----+------+--------+-------+ 2022-11-26 16:00:26,625 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1294 | 0.947 | 0.902 | +-------+-----+------+--------+-------+ | mAP | | | | 0.902 | +-------+-----+------+--------+-------+ 2022-11-26 16:00:31,517 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1294 | 0.940 | 0.881 | +-------+-----+------+--------+-------+ | mAP | | | | 0.881 | +-------+-----+------+--------+-------+ 2022-11-26 16:00:37,202 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1294 | 0.920 | 0.840 | +-------+-----+------+--------+-------+ | mAP | | | | 0.840 | +-------+-----+------+--------+-------+ 2022-11-26 16:00:42,147 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1294 | 0.900 | 0.799 | +-------+-----+------+--------+-------+ | mAP | | | | 0.799 | +-------+-----+------+--------+-------+ 2022-11-26 16:00:46,569 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1294 | 0.873 | 0.728 | +-------+-----+------+--------+-------+ | mAP | | | | 0.728 | +-------+-----+------+--------+-------+ 2022-11-26 16:00:51,934 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1294 | 0.807 | 0.637 | +-------+-----+------+--------+-------+ | mAP | | | | 0.637 | +-------+-----+------+--------+-------+ 2022-11-26 16:00:59,851 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1294 | 0.667 | 0.466 | +-------+-----+------+--------+-------+ | mAP | | | | 0.466 | +-------+-----+------+--------+-------+ 2022-11-26 16:00:59,860 - mmdet - INFO - Iter(val) [256] NoCoAP10: 0.9250, NoCoAP20: 0.9150, NoCoAP30: 0.9020, NoCoAP40: 0.8810, NoCoAP50: 0.8400, NoCoAP60: 0.7990, NoCoAP70: 0.7280, NoCoAP80: 0.6370, NoCoAP90: 0.4660, mNoCoAP: 0.7882 2022-11-26 16:01:04,087 - mmdet - INFO - Iter [6350/6924] lr: 5.000e-05, eta: 0:02:11, time: 1.399, data_time: 1.145, memory: 11396, loss_cls: 0.0343, loss_bbox: 0.2062, loss_centerness: 0.4089, loss: 0.6494, grad_norm: 3.2985 2022-11-26 16:01:14,409 - mmdet - INFO - Iter [6400/6924] lr: 5.000e-05, eta: 0:01:59, time: 0.206, data_time: 0.008, memory: 11396, loss_cls: 0.0398, loss_bbox: 0.2013, loss_centerness: 0.3918, loss: 0.6330, grad_norm: 4.9216 2022-11-26 16:01:23,737 - mmdet - INFO - Iter [6450/6924] lr: 5.000e-05, eta: 0:01:48, time: 0.187, data_time: 0.010, memory: 11396, loss_cls: 0.0389, loss_bbox: 0.2045, loss_centerness: 0.3575, loss: 0.6008, grad_norm: 4.8665 2022-11-26 16:01:33,226 - mmdet - INFO - Iter [6500/6924] lr: 5.000e-05, eta: 0:01:36, time: 0.190, data_time: 0.009, memory: 11396, loss_cls: 0.0499, loss_bbox: 0.2142, loss_centerness: 0.3604, loss: 0.6245, grad_norm: 5.0820 2022-11-26 16:01:42,968 - mmdet - INFO - Iter [6550/6924] lr: 5.000e-05, eta: 0:01:25, time: 0.195, data_time: 0.009, memory: 11396, loss_cls: 0.0411, loss_bbox: 0.2151, loss_centerness: 0.3335, loss: 0.5898, grad_norm: 5.0491 2022-11-26 16:01:52,782 - mmdet - INFO - Iter [6600/6924] lr: 5.000e-05, eta: 0:01:13, time: 0.196, data_time: 0.009, memory: 11396, loss_cls: 0.0461, loss_bbox: 0.2032, loss_centerness: 0.3676, loss: 0.6168, grad_norm: 4.8741 2022-11-26 16:02:02,234 - mmdet - INFO - Iter [6650/6924] lr: 5.000e-05, eta: 0:01:02, time: 0.189, data_time: 0.010, memory: 11396, loss_cls: 0.0455, loss_bbox: 0.2087, loss_centerness: 0.3820, loss: 0.6361, grad_norm: 4.8558 2022-11-26 16:02:12,001 - mmdet - INFO - Iter [6700/6924] lr: 5.000e-05, eta: 0:00:50, time: 0.195, data_time: 0.010, memory: 11396, loss_cls: 0.0394, loss_bbox: 0.2045, loss_centerness: 0.3679, loss: 0.6118, grad_norm: 4.4986 2022-11-26 16:02:21,308 - mmdet - INFO - Iter [6750/6924] lr: 5.000e-05, eta: 0:00:39, time: 0.186, data_time: 0.010, memory: 11396, loss_cls: 0.0421, loss_bbox: 0.2170, loss_centerness: 0.3789, loss: 0.6380, grad_norm: 5.1053 2022-11-26 16:02:30,761 - mmdet - INFO - Iter [6800/6924] lr: 5.000e-05, eta: 0:00:28, time: 0.189, data_time: 0.008, memory: 11396, loss_cls: 0.0353, loss_bbox: 0.2136, loss_centerness: 0.3611, loss: 0.6100, grad_norm: 4.6205 2022-11-26 16:02:40,763 - mmdet - INFO - Iter [6850/6924] lr: 5.000e-05, eta: 0:00:16, time: 0.200, data_time: 0.009, memory: 11396, loss_cls: 0.0535, loss_bbox: 0.1936, loss_centerness: 0.3502, loss: 0.5973, grad_norm: 5.1825 2022-11-26 16:02:51,079 - mmdet - INFO - Iter [6900/6924] lr: 5.000e-05, eta: 0:00:05, time: 0.206, data_time: 0.008, memory: 11396, loss_cls: 0.0472, loss_bbox: 0.2373, loss_centerness: 0.3454, loss: 0.6298, grad_norm: 5.3077 2022-11-26 16:02:55,837 - mmdet - INFO - Saving checkpoint at 12 epochs 2022-11-26 16:03:11,424 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1167 | 0.953 | 0.922 | +-------+-----+------+--------+-------+ | mAP | | | | 0.922 | +-------+-----+------+--------+-------+ 2022-11-26 16:03:15,197 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1167 | 0.953 | 0.914 | +-------+-----+------+--------+-------+ | mAP | | | | 0.914 | +-------+-----+------+--------+-------+ 2022-11-26 16:03:18,693 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1167 | 0.940 | 0.903 | +-------+-----+------+--------+-------+ | mAP | | | | 0.903 | +-------+-----+------+--------+-------+ 2022-11-26 16:03:23,501 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1167 | 0.920 | 0.879 | +-------+-----+------+--------+-------+ | mAP | | | | 0.879 | +-------+-----+------+--------+-------+ 2022-11-26 16:03:28,497 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1167 | 0.900 | 0.835 | +-------+-----+------+--------+-------+ | mAP | | | | 0.835 | +-------+-----+------+--------+-------+ 2022-11-26 16:03:31,949 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1167 | 0.880 | 0.766 | +-------+-----+------+--------+-------+ | mAP | | | | 0.766 | +-------+-----+------+--------+-------+ 2022-11-26 16:03:35,275 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1167 | 0.840 | 0.667 | +-------+-----+------+--------+-------+ | mAP | | | | 0.667 | +-------+-----+------+--------+-------+ 2022-11-26 16:03:38,613 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1167 | 0.720 | 0.517 | +-------+-----+------+--------+-------+ | mAP | | | | 0.517 | +-------+-----+------+--------+-------+ 2022-11-26 16:03:43,019 - mmdet - INFO - +-------+-----+------+--------+-------+ | class | gts | dets | recall | ap | +-------+-----+------+--------+-------+ | 0 | 150 | 1167 | 0.560 | 0.326 | +-------+-----+------+--------+-------+ | mAP | | | | 0.326 | +-------+-----+------+--------+-------+ 2022-11-26 16:03:43,025 - mmdet - INFO - Iter(val) [256] NoCoAP10: 0.9220, NoCoAP20: 0.9140, NoCoAP30: 0.9030, NoCoAP40: 0.8790, NoCoAP50: 0.8350, NoCoAP60: 0.7660, NoCoAP70: 0.6670, NoCoAP80: 0.5170, NoCoAP90: 0.3260, mNoCoAP: 0.7479