search

open-mmlab / mmdetection

OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io
Apache License 2.0
29.21k stars 9.4k forks source link

ERROR - The testing results of the whole dataset is empty #4241

Closed codefabulous closed 3 years ago

codefabulous commented 3 years ago

I am trying to train a new model on my own dataset which is converted to coco style by following the steps in the tutorial2. I added a new config file called 'faster_rcnn_r50_fpn_1x_coco.py', the content is:

_base_ = '../faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py'
model = dict(roi_head=dict(bbox_head=dict(num_classes=3)))
classes = ('fire', 'other', 'smoke')
data = dict(
    train=dict(
        img_prefix = 'data/cocofire/train/',
        classes = classes,
        ann_file = 'data/cocofire/annotations0/instances_train.json'),
    val=dict(
        img_prefix = 'data/cocofire/val/',
        classes = classes,
        ann_file = 'data/cocofire/annotations0/instances_val.json'),
    test=dict(
        img_prefix = 'data/cocofire/val/',
        classes = classes,
        ann_file = 'data/cocofire/annotations0/instances_val.json'))

total_epochs = 2   
workflow = [('train', 1), ('val', 1)]
# load_from = 'https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r50_fpn_1x_20181010-3d1b3351.pth'  # noqa
load_from = 'checkpoints/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth'

And the full config file generated in the work_dirs is:

model = dict(
    type='FasterRCNN',
    pretrained='torchvision://resnet50',
    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=True),
        norm_eval=True,
        style='pytorch'),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        num_outs=5),
    rpn_head=dict(
        type='RPNHead',
        in_channels=256,
        feat_channels=256,
        anchor_generator=dict(
            type='AnchorGenerator',
            scales=[8],
            ratios=[0.5, 1.0, 2.0],
            strides=[4, 8, 16, 32, 64]),
        bbox_coder=dict(
            type='DeltaXYWHBBoxCoder',
            target_means=[0.0, 0.0, 0.0, 0.0],
            target_stds=[1.0, 1.0, 1.0, 1.0]),
        loss_cls=dict(
            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
    roi_head=dict(
        type='StandardRoIHead',
        bbox_roi_extractor=dict(
            type='SingleRoIExtractor',
            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
            out_channels=256,
            featmap_strides=[4, 8, 16, 32]),
        bbox_head=dict(
            type='Shared2FCBBoxHead',
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=3,
            bbox_coder=dict(
                type='DeltaXYWHBBoxCoder',
                target_means=[0.0, 0.0, 0.0, 0.0],
                target_stds=[0.1, 0.1, 0.2, 0.2]),
            reg_class_agnostic=False,
            loss_cls=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
            loss_bbox=dict(type='L1Loss', loss_weight=1.0))))
train_cfg = dict(
    rpn=dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.7,
            neg_iou_thr=0.3,
            min_pos_iou=0.3,
            match_low_quality=True,
            ignore_iof_thr=-1),
        sampler=dict(
            type='RandomSampler',
            num=256,
            pos_fraction=0.5,
            neg_pos_ub=-1,
            add_gt_as_proposals=False),
        allowed_border=-1,
        pos_weight=-1,
        debug=False),
    rpn_proposal=dict(
        nms_across_levels=False,
        nms_pre=2000,
        nms_post=1000,
        max_num=1000,
        nms_thr=0.7,
        min_bbox_size=0),
    rcnn=dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.5,
            neg_iou_thr=0.5,
            min_pos_iou=0.5,
            match_low_quality=False,
            ignore_iof_thr=-1),
        sampler=dict(
            type='RandomSampler',
            num=512,
            pos_fraction=0.25,
            neg_pos_ub=-1,
            add_gt_as_proposals=True),
        pos_weight=-1,
        debug=False))
test_cfg = dict(
    rpn=dict(
        nms_across_levels=False,
        nms_pre=1000,
        nms_post=1000,
        max_num=1000,
        nms_thr=0.7,
        min_bbox_size=0),
    rcnn=dict(
        score_thr=0.05,
        nms=dict(type='nms', iou_threshold=0.5),
        max_per_img=100))
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(1333, 800),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type='CocoDataset',
        ann_file='data/cocofire/annotations0/instances_train.json',
        img_prefix='data/cocofire/train/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
            dict(type='RandomFlip', flip_ratio=0.5),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='DefaultFormatBundle'),
            dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
        ],
        classes=('fire', 'other', 'smoke')),
    val=dict(
        type='CocoDataset',
        ann_file='data/cocofire/annotations0/instances_val.json',
        img_prefix='data/cocofire/val/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(1333, 800),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ],
        classes=('fire', 'other', 'smoke')),
    test=dict(
        type='CocoDataset',
        ann_file='data/cocofire/annotations0/instances_val.json',
        img_prefix='data/cocofire/val/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(1333, 800),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ],
        classes=('fire', 'other', 'smoke')))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.001,
    step=[8, 11])
total_epochs = 2
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = 'checkpoints/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth'
resume_from = None
workflow = [('train', 1), ('val', 1)]
classes = ('fire', 'other', 'smoke')
work_dir = './work_dirs/faster_rcnn_r50_fpn_1x_fire'
gpu_ids = [1]

When I run 

 python tools/train.py configs/fire/faster_rcnn_r50_fpn_1x_fire.py --gpu-ids 1

It has the warning "- WARNING - The model and loaded state dict do not match exactly unexpected key in source state_dict: fc.weight, fc.bias" and the error " - mmdet - ERROR - The testing results of the whole dataset is empty". Could you please help me find the reason why the warning and the error happened? Thank you for your help!

The full training log is as follows.

mmdetection$ python tools/train.py configs/fire/faster_rcnn_r50_fpn_1x_fire.py --gpu-ids 12020-12-07 14:27:20,772 - mmdet - INFO - Environment info:
------------------------------------------------------------
sys.platform: linux
Python: 3.7.9 (default, Aug 31 2020, 12:42:55) [GCC 7.3.0]
CUDA available: True
GPU 0,1: GeForce GTX TITAN X
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 10.2, V10.2.89
GCC: gcc (GCC) 5.4.0
PyTorch: 1.7.0
PyTorch compiling details: PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 10.2
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75
  - CuDNN 7.6.5
  - Magma 2.5.2
  - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, 

TorchVision: 0.8.1
OpenCV: 4.4.0
MMCV: 1.2.1
MMCV Compiler: GCC 5.4
MMCV CUDA Compiler: 10.2
MMDetection: 2.6.0+d7f4198
------------------------------------------------------------

2020-12-07 14:27:21,067 - mmdet - INFO - Distributed training: False
2020-12-07 14:27:21,358 - mmdet - INFO - Config:
model = dict(
    type='FasterRCNN',
    pretrained='torchvision://resnet50',
    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=True),
        norm_eval=True,
        style='pytorch'),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        num_outs=5),
    rpn_head=dict(
        type='RPNHead',
        in_channels=256,
        feat_channels=256,
        anchor_generator=dict(
            type='AnchorGenerator',
            scales=[8],
            ratios=[0.5, 1.0, 2.0],
            strides=[4, 8, 16, 32, 64]),
        bbox_coder=dict(
            type='DeltaXYWHBBoxCoder',
            target_means=[0.0, 0.0, 0.0, 0.0],
            target_stds=[1.0, 1.0, 1.0, 1.0]),
        loss_cls=dict(
            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
    roi_head=dict(
        type='StandardRoIHead',
        bbox_roi_extractor=dict(
            type='SingleRoIExtractor',
            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
            out_channels=256,
            featmap_strides=[4, 8, 16, 32]),
        bbox_head=dict(
            type='Shared2FCBBoxHead',
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=3,
            bbox_coder=dict(
                type='DeltaXYWHBBoxCoder',
                target_means=[0.0, 0.0, 0.0, 0.0],
                target_stds=[0.1, 0.1, 0.2, 0.2]),
            reg_class_agnostic=False,
            loss_cls=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
            loss_bbox=dict(type='L1Loss', loss_weight=1.0))))
train_cfg = dict(
    rpn=dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.7,
            neg_iou_thr=0.3,
            min_pos_iou=0.3,
            match_low_quality=True,
            ignore_iof_thr=-1),
        sampler=dict(
            type='RandomSampler',
            num=256,
            pos_fraction=0.5,
            neg_pos_ub=-1,
            add_gt_as_proposals=False),
        allowed_border=-1,
        pos_weight=-1,
        debug=False),
    rpn_proposal=dict(
        nms_across_levels=False,
        nms_pre=2000,
        nms_post=1000,
        max_num=1000,
        nms_thr=0.7,
        min_bbox_size=0),
    rcnn=dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.5,
            neg_iou_thr=0.5,
            min_pos_iou=0.5,
            match_low_quality=False,
            ignore_iof_thr=-1),
        sampler=dict(
            type='RandomSampler',
            num=512,
            pos_fraction=0.25,
            neg_pos_ub=-1,
            add_gt_as_proposals=True),
        pos_weight=-1,
        debug=False))
test_cfg = dict(
    rpn=dict(
        nms_across_levels=False,
        nms_pre=1000,
        nms_post=1000,
        max_num=1000,
        nms_thr=0.7,
        min_bbox_size=0),
    rcnn=dict(
        score_thr=0.05,
        nms=dict(type='nms', iou_threshold=0.5),
        max_per_img=100))
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(1333, 800),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type='CocoDataset',
        ann_file='data/cocofire/annotations0/instances_train.json',
        img_prefix='data/cocofire/train/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
            dict(type='RandomFlip', flip_ratio=0.5),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='DefaultFormatBundle'),
            dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
        ],
        classes=('fire', 'other', 'smoke')),
    val=dict(
        type='CocoDataset',
        ann_file='data/cocofire/annotations0/instances_val.json',
        img_prefix='data/cocofire/val/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(1333, 800),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ],
        classes=('fire', 'other', 'smoke')),
    test=dict(
        type='CocoDataset',
        ann_file='data/cocofire/annotations0/instances_val.json',
        img_prefix='data/cocofire/val/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(1333, 800),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ],
        classes=('fire', 'other', 'smoke')))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.001,
    step=[8, 11])
total_epochs = 2
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = 'checkpoints/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth'
resume_from = None
workflow = [('train', 1), ('val', 1)]
classes = ('fire', 'other', 'smoke')
work_dir = './work_dirs/faster_rcnn_r50_fpn_1x_fire'
gpu_ids = [1]

2020-12-07 14:27:21,680 - mmdet - INFO - load model from: torchvision://resnet50
2020-12-07 14:27:21,835 - mmdet - WARNING - The model and loaded state dict do not match exactly

unexpected key in source state_dict: fc.weight, fc.bias

loading annotations into memory...
Done (t=0.15s)
creating index...
index created!
loading annotations into memory...
Done (t=0.04s)
creating index...
index created!
loading annotations into memory...
Done (t=0.04s)
creating index...
index created!
2020-12-07 14:27:23,884 - mmdet - INFO - load checkpoint from checkpoints/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth
2020-12-07 14:27:24,067 - mmdet - WARNING - The model and loaded state dict do not match exactly

size mismatch for roi_head.bbox_head.fc_cls.weight: copying a param with shape torch.Size([81, 1024]) from checkpoint, the shape in current model is torch.Size([4, 1024]).
size mismatch for roi_head.bbox_head.fc_cls.bias: copying a param with shape torch.Size([81]) from checkpoint, the shape in current model is torch.Size([4]).
size mismatch for roi_head.bbox_head.fc_reg.weight: copying a param with shape torch.Size([320, 1024]) from checkpoint, the shape in current model is torch.Size([12, 1024]).
size mismatch for roi_head.bbox_head.fc_reg.bias: copying a param with shape torch.Size([320]) from checkpoint, the shape in current model is torch.Size([12]).
2020-12-07 14:27:24,074 - mmdet - INFO - Start running, host: user4@optgtx7, work_dir: /home/user4/fireDetection/mmdetection/work_dirs/faster_rcnn_r50_fpn_1x_fire
2020-12-07 14:27:24,074 - mmdet - INFO - workflow: [('train', 1), ('val', 1)], max: 2 epochs
2020-12-07 14:27:51,410 - mmdet - INFO - Epoch [1][50/3217] lr: 1.978e-03, eta: 0:57:58, time: 0.545, data_time: 0.048, memory: 3784, loss_rpn_cls: 0.0041, loss_rpn_bbox: 0.0000, loss_cls: 0.2836, acc: 89.5488, loss_bbox: 0.0000, loss: 0.2877
2020-12-07 14:28:18,504 - mmdet - INFO - Epoch [1][100/3217]    lr: 3.976e-03, eta: 0:57:20, time: 0.542, data_time: 0.005, memory: 3784, loss_rpn_cls: 0.0007, loss_rpn_bbox: 0.0000, loss_cls: 0.0150, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0156
2020-12-07 14:28:46,997 - mmdet - INFO - Epoch [1][150/3217]    lr: 5.974e-03, eta: 0:57:49, time: 0.570, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0004, loss_rpn_bbox: 0.0000, loss_cls: 0.0169, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0174
2020-12-07 14:29:14,994 - mmdet - INFO - Epoch [1][200/3217]    lr: 7.972e-03, eta: 0:57:32, time: 0.559, data_time: 0.005, memory: 3784, loss_rpn_cls: 0.0004, loss_rpn_bbox: 0.0000, loss_cls: 0.0139, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0143
2020-12-07 14:29:42,970 - mmdet - INFO - Epoch [1][250/3217]    lr: 9.970e-03, eta: 0:57:12, time: 0.560, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0115, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0115
2020-12-07 14:30:11,080 - mmdet - INFO - Epoch [1][300/3217]    lr: 1.197e-02, eta: 0:56:52, time: 0.562, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0001, loss_rpn_bbox: 0.0000, loss_cls: 0.0069, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0069
2020-12-07 14:30:39,862 - mmdet - INFO - Epoch [1][350/3217]    lr: 1.397e-02, eta: 0:56:40, time: 0.575, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0001, loss_rpn_bbox: 0.0000, loss_cls: 0.0045, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0046
2020-12-07 14:31:07,901 - mmdet - INFO - Epoch [1][400/3217]    lr: 1.596e-02, eta: 0:56:14, time: 0.561, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0030, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0030
2020-12-07 14:31:36,301 - mmdet - INFO - Epoch [1][450/3217]    lr: 1.796e-02, eta: 0:55:52, time: 0.569, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0019, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0019
2020-12-07 14:32:04,026 - mmdet - INFO - Epoch [1][500/3217]    lr: 1.996e-02, eta: 0:55:20, time: 0.554, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0013, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0013
2020-12-07 14:32:32,057 - mmdet - INFO - Epoch [1][550/3217]    lr: 2.000e-02, eta: 0:54:53, time: 0.560, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0009, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0009
2020-12-07 14:33:00,241 - mmdet - INFO - Epoch [1][600/3217]    lr: 2.000e-02, eta: 0:54:27, time: 0.565, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0007, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0007
2020-12-07 14:33:28,075 - mmdet - INFO - Epoch [1][650/3217]    lr: 2.000e-02, eta: 0:53:57, time: 0.556, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0006, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0006
2020-12-07 14:33:56,152 - mmdet - INFO - Epoch [1][700/3217]    lr: 2.000e-02, eta: 0:53:30, time: 0.562, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0005, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0005
2020-12-07 14:34:24,335 - mmdet - INFO - Epoch [1][750/3217]    lr: 2.000e-02, eta: 0:53:04, time: 0.565, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0004, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0004
2020-12-07 14:34:52,955 - mmdet - INFO - Epoch [1][800/3217]    lr: 2.000e-02, eta: 0:52:40, time: 0.571, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0004, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0004
2020-12-07 14:35:21,822 - mmdet - INFO - Epoch [1][850/3217]    lr: 2.000e-02, eta: 0:52:17, time: 0.577, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0004, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0004
2020-12-07 14:35:49,766 - mmdet - INFO - Epoch [1][900/3217]    lr: 2.000e-02, eta: 0:51:48, time: 0.559, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0003, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0003
2020-12-07 14:36:18,361 - mmdet - INFO - Epoch [1][950/3217]    lr: 2.000e-02, eta: 0:51:23, time: 0.572, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0003, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0003
2020-12-07 14:36:46,954 - mmdet - INFO - Exp name: faster_rcnn_r50_fpn_1x_fire.py
2020-12-07 14:36:46,954 - mmdet - INFO - Epoch [1][1000/3217]   lr: 2.000e-02, eta: 0:50:57, time: 0.572, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0003, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0003
2020-12-07 14:37:15,969 - mmdet - INFO - Epoch [1][1050/3217]   lr: 2.000e-02, eta: 0:50:34, time: 0.580, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0002, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0002
2020-12-07 14:37:44,386 - mmdet - INFO - Epoch [1][1100/3217]   lr: 2.000e-02, eta: 0:50:07, time: 0.568, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0002, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0002
2020-12-07 14:38:12,427 - mmdet - INFO - Epoch [1][1150/3217]   lr: 2.000e-02, eta: 0:49:38, time: 0.561, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0002, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0002
2020-12-07 14:38:41,489 - mmdet - INFO - Epoch [1][1200/3217]   lr: 2.000e-02, eta: 0:49:13, time: 0.581, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0002, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0002
2020-12-07 14:39:09,877 - mmdet - INFO - Epoch [1][1250/3217]   lr: 2.000e-02, eta: 0:48:46, time: 0.568, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0002, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0002
2020-12-07 14:39:38,265 - mmdet - INFO - Epoch [1][1300/3217]   lr: 2.000e-02, eta: 0:48:18, time: 0.568, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0002, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0002
2020-12-07 14:40:06,905 - mmdet - INFO - Epoch [1][1350/3217]   lr: 2.000e-02, eta: 0:47:52, time: 0.573, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0002, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0002
2020-12-07 14:40:34,445 - mmdet - INFO - Epoch [1][1400/3217]   lr: 2.000e-02, eta: 0:47:21, time: 0.551, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0002, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0002
2020-12-07 14:41:02,508 - mmdet - INFO - Epoch [1][1450/3217]   lr: 2.000e-02, eta: 0:46:52, time: 0.561, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0002, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0002
2020-12-07 14:41:30,203 - mmdet - INFO - Epoch [1][1500/3217]   lr: 2.000e-02, eta: 0:46:22, time: 0.555, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:41:58,774 - mmdet - INFO - Epoch [1][1550/3217]   lr: 2.000e-02, eta: 0:45:55, time: 0.570, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0002, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0002
2020-12-07 14:42:26,584 - mmdet - INFO - Epoch [1][1600/3217]   lr: 2.000e-02, eta: 0:45:26, time: 0.557, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:42:54,845 - mmdet - INFO - Epoch [1][1650/3217]   lr: 2.000e-02, eta: 0:44:58, time: 0.565, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:43:23,202 - mmdet - INFO - Epoch [1][1700/3217]   lr: 2.000e-02, eta: 0:44:30, time: 0.568, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:43:51,663 - mmdet - INFO - Epoch [1][1750/3217]   lr: 2.000e-02, eta: 0:44:02, time: 0.569, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:44:19,847 - mmdet - INFO - Epoch [1][1800/3217]   lr: 2.000e-02, eta: 0:43:34, time: 0.564, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:44:48,807 - mmdet - INFO - Epoch [1][1850/3217]   lr: 2.000e-02, eta: 0:43:08, time: 0.580, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:45:16,927 - mmdet - INFO - Epoch [1][1900/3217]   lr: 2.000e-02, eta: 0:42:39, time: 0.562, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:45:45,568 - mmdet - INFO - Epoch [1][1950/3217]   lr: 2.000e-02, eta: 0:42:12, time: 0.573, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:46:13,729 - mmdet - INFO - Exp name: faster_rcnn_r50_fpn_1x_fire.py
2020-12-07 14:46:13,729 - mmdet - INFO - Epoch [1][2000/3217]   lr: 2.000e-02, eta: 0:41:44, time: 0.563, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:46:41,438 - mmdet - INFO - Epoch [1][2050/3217]   lr: 2.000e-02, eta: 0:41:14, time: 0.554, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:47:09,747 - mmdet - INFO - Epoch [1][2100/3217]   lr: 2.000e-02, eta: 0:40:46, time: 0.566, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:47:37,276 - mmdet - INFO - Epoch [1][2150/3217]   lr: 2.000e-02, eta: 0:40:17, time: 0.550, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:48:05,252 - mmdet - INFO - Epoch [1][2200/3217]   lr: 2.000e-02, eta: 0:39:48, time: 0.560, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:48:33,849 - mmdet - INFO - Epoch [1][2250/3217]   lr: 2.000e-02, eta: 0:39:20, time: 0.572, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:49:02,280 - mmdet - INFO - Epoch [1][2300/3217]   lr: 2.000e-02, eta: 0:38:53, time: 0.569, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:49:30,365 - mmdet - INFO - Epoch [1][2350/3217]   lr: 2.000e-02, eta: 0:38:24, time: 0.562, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:49:57,985 - mmdet - INFO - Epoch [1][2400/3217]   lr: 2.000e-02, eta: 0:37:55, time: 0.552, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:50:26,708 - mmdet - INFO - Epoch [1][2450/3217]   lr: 2.000e-02, eta: 0:37:28, time: 0.574, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:50:54,796 - mmdet - INFO - Epoch [1][2500/3217]   lr: 2.000e-02, eta: 0:36:59, time: 0.562, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:51:23,343 - mmdet - INFO - Epoch [1][2550/3217]   lr: 2.000e-02, eta: 0:36:31, time: 0.571, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:51:51,907 - mmdet - INFO - Epoch [1][2600/3217]   lr: 2.000e-02, eta: 0:36:04, time: 0.571, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:52:19,765 - mmdet - INFO - Epoch [1][2650/3217]   lr: 2.000e-02, eta: 0:35:35, time: 0.557, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:52:47,558 - mmdet - INFO - Epoch [1][2700/3217]   lr: 2.000e-02, eta: 0:35:06, time: 0.556, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:53:16,255 - mmdet - INFO - Epoch [1][2750/3217]   lr: 2.000e-02, eta: 0:34:39, time: 0.574, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:53:45,024 - mmdet - INFO - Epoch [1][2800/3217]   lr: 2.000e-02, eta: 0:34:11, time: 0.575, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:54:12,567 - mmdet - INFO - Epoch [1][2850/3217]   lr: 2.000e-02, eta: 0:33:42, time: 0.551, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:54:40,786 - mmdet - INFO - Epoch [1][2900/3217]   lr: 2.000e-02, eta: 0:33:14, time: 0.564, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:55:09,037 - mmdet - INFO - Epoch [1][2950/3217]   lr: 2.000e-02, eta: 0:32:46, time: 0.565, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:55:37,274 - mmdet - INFO - Exp name: faster_rcnn_r50_fpn_1x_fire.py
2020-12-07 14:55:37,275 - mmdet - INFO - Epoch [1][3000/3217]   lr: 2.000e-02, eta: 0:32:17, time: 0.564, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:56:05,496 - mmdet - INFO - Epoch [1][3050/3217]   lr: 2.000e-02, eta: 0:31:49, time: 0.565, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:56:33,167 - mmdet - INFO - Epoch [1][3100/3217]   lr: 2.000e-02, eta: 0:31:20, time: 0.553, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:57:01,276 - mmdet - INFO - Epoch [1][3150/3217]   lr: 2.000e-02, eta: 0:30:52, time: 0.562, data_time: 0.007, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:57:29,830 - mmdet - INFO - Epoch [1][3200/3217]   lr: 2.000e-02, eta: 0:30:24, time: 0.571, data_time: 0.006, memory: 3784, loss_rpn_cls: 0.0000, loss_rpn_bbox: 0.0000, loss_cls: 0.0001, acc: 100.0000, loss_bbox: 0.0000, loss: 0.0001
2020-12-07 14:57:39,263 - mmdet - INFO - Saving checkpoint at 1 epochs
[>>>>>>>>>>>>>>>>>>>>>>>>>>>] 3028/3028, 8.2 task/s, elapsed: 370s, ETA:     0s2020-12-07 15:03:51,664 - mmdet - INFO - Evaluating bbox...
Loading and preparing results...
2020-12-07 15:03:51,665 - mmdet - ERROR - The testing results of the whole dataset is empty.
2020-12-07 15:03:51,666 - mmdet - INFO - Exp name: faster_rcnn_r50_fpn_1x_fire.py
v-qjqs commented 3 years ago

Hi, it's normal to have the above warning. For the caused error, do you have the correct file path or the ground-truth annotations?

codefabulous commented 3 years ago

Hi, thanks so much for your remind. I recheck the coco transformation code and found area part is wrongly calculated.