博客

mmdetection使用tensorboard可视化训练集与验证集指标参数

  • Post author:
  • Post category:其他


如何使用mmdetection训练自己的数据可以参考这篇文章

https://blog.csdn.net/weicao1990/article/details/93484603

，在这篇文章中只是用训练集进行训练，没有用到验证集验证模型的指标，因此这篇文章中将会讨论如何增加验证集，并且使用tensorboard可视化训练集与验证集的指标参数。

以cascade_rcnn_hrnetv2p_w32_20e.py为例，原始的文件内容如下： 

# model settings
model = dict(
    type='CascadeRCNN',
    num_stages=3,
    pretrained='open-mmlab://msra/hrnetv2_w32',
    backbone=dict(
        type='HRNet',
        extra=dict(
            stage1=dict(
                num_modules=1,
                num_branches=1,
                block='BOTTLENECK',
                num_blocks=(4, ),
                num_channels=(64, )),
            stage2=dict(
                num_modules=1,
                num_branches=2,
                block='BASIC',
                num_blocks=(4, 4),
                num_channels=(32, 64)),
            stage3=dict(
                num_modules=4,
                num_branches=3,
                block='BASIC',
                num_blocks=(4, 4, 4),
                num_channels=(32, 64, 128)),
            stage4=dict(
                num_modules=3,
                num_branches=4,
                block='BASIC',
                num_blocks=(4, 4, 4, 4),
                num_channels=(32, 64, 128, 256)))),
    neck=dict(type='HRFPN', in_channels=[32, 64, 128, 256], out_channels=256),
    rpn_head=dict(
        type='RPNHead',
        in_channels=256,
        feat_channels=256,
        anchor_scales=[8],
        anchor_ratios=[0.5, 1.0, 2.0],
        anchor_strides=[4, 8, 16, 32, 64],
        target_means=[.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='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
    bbox_roi_extractor=dict(
        type='SingleRoIExtractor',
        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
        out_channels=256,
        featmap_strides=[4, 8, 16, 32]),
    bbox_head=[
        dict(
            type='SharedFCBBoxHead',
            num_fcs=2,
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=81,
            target_means=[0., 0., 0., 0.],
            target_stds=[0.1, 0.1, 0.2, 0.2],
            reg_class_agnostic=True,
            loss_cls=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
            loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
        dict(
            type='SharedFCBBoxHead',
            num_fcs=2,
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=81,
            target_means=[0., 0., 0., 0.],
            target_stds=[0.05, 0.05, 0.1, 0.1],
            reg_class_agnostic=True,
            loss_cls=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
            loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
        dict(
            type='SharedFCBBoxHead',
            num_fcs=2,
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=81,
            target_means=[0., 0., 0., 0.],
            target_stds=[0.033, 0.033, 0.067, 0.067],
            reg_class_agnostic=True,
            loss_cls=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
            loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
    ])
# model training and testing settings
train_cfg = dict(
    rpn=dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.7,
            neg_iou_thr=0.3,
            min_pos_iou=0.3,
            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=0,
        pos_weight=-1,
        debug=False),
    rpn_proposal=dict(
        nms_across_levels=False,
        nms_pre=2000,
        nms_post=2000,
        max_num=2000,
        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,
                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),
        dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.6,
                neg_iou_thr=0.6,
                min_pos_iou=0.6,
                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),
        dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.7,
                neg_iou_thr=0.7,
                min_pos_iou=0.7,
                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)
    ],
    stage_loss_weights=[1, 0.5, 0.25])
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_thr=0.5), max_per_img=100),
    keep_all_stages=False)
# dataset settings
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', **img_norm_cfg),
    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', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]
data = dict(
    imgs_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_train2017.json',
        img_prefix=data_root + 'train2017/',
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json',
        img_prefix=data_root + 'val2017/',
        pipeline=test_pipeline),
    test=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json',
        img_prefix=data_root + 'val2017/',
        pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=1.0 / 3,
    step=[16, 19])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=50,
    hooks=[
        dict(type='TextLoggerHook'),
        # dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
# runtime settings
total_epochs = 20
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/cascade_rcnn_hrnetv2p_w32'
load_from = None
resume_from = None
workflow = [('train', 1)]

其中配置文件中的workflow参数的含义是工作流，比如workflow = [(‘train’, 1), (‘val’, 1)]表示按照训练一个epoch，接着再进行一个epoch的验证的策略迭代训练，如果workflow = [(‘train’, 1)]表示训练完一个epoch后接着进行下一个epoch的训练，期间不进行验证。因此，增加验证集需要配置workflow，比如我们期望训练完一个epoch后接着进行验证，从而可以评估当前模型在验证集上的效果，这样我们设置workflow = [(‘train’, 1), (‘val’, 1)]。

仅仅修改了这里，训练完一个epoch接下来进行验证的时候会报如下错误：

这是因为，还缺少验证集pipline的配置，默认配置文件中是没有val_pipeline的配置的，我们需要参考train_pipeline的内容添加val_pipeline,在cascade_rcnn_hrnetv2p_w32_20e.py中的train_pipeline与test_pipeline之间添加val_pipeline的内容： 

val_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', **img_norm_cfg),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]

可以看到val_pipeline的内容与train_pipline的内容是一样的。添加了val_pipeline后，还需要将cascade_rcnn_hrnetv2p_w32_20e.py中验证集的pipeline修改为刚才添加的val_pipeline,修改后如下： 

data = dict(
    imgs_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_train2017.json',
        img_prefix=data_root + 'train2017/',
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json',
        img_prefix=data_root + 'val2017/',
        pipeline=val_pipeline),
    test=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json',
        img_prefix=data_root + 'val2017/',
        pipeline=test_pipeline))

至此，验证集的添加工作就完成了。

接下来添加tensorboard的配置（要使用tensorboard进行可视化需要提前安装tensorboardx，执行sudo pip install tensorboardx即可安装），默认配置文件中是不开启tensorboard的配置的，只需要在log_config中的tensorboard注释取消即可，如下： 

log_config = dict(
    interval=1,
    hooks=[
        dict(type='TextLoggerHook'),
        dict(type='TensorboardLoggerHook')
    ])

至此，所有的配置已完成，修改后的完整的配置文件内容如下： 

# model settings
model = dict(
    type='CascadeRCNN',
    num_stages=3,
    pretrained='open-mmlab://msra/hrnetv2_w32',
    backbone=dict(
        type='HRNet',
        extra=dict(
            stage1=dict(
                num_modules=1,
                num_branches=1,
                block='BOTTLENECK',
                num_blocks=(4, ),
                num_channels=(64, )),
            stage2=dict(
                num_modules=1,
                num_branches=2,
                block='BASIC',
                num_blocks=(4, 4),
                num_channels=(32, 64)),
            stage3=dict(
                num_modules=4,
                num_branches=3,
                block='BASIC',
                num_blocks=(4, 4, 4),
                num_channels=(32, 64, 128)),
            stage4=dict(
                num_modules=3,
                num_branches=4,
                block='BASIC',
                num_blocks=(4, 4, 4, 4),
                num_channels=(32, 64, 128, 256)))),
    neck=dict(type='HRFPN', in_channels=[32, 64, 128, 256], out_channels=256),
    rpn_head=dict(
        type='RPNHead',
        in_channels=256,
        feat_channels=256,
        anchor_scales=[8],
        anchor_ratios=[0.5, 1.0, 2.0],
        anchor_strides=[4, 8, 16, 32, 64],
        target_means=[.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='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
    bbox_roi_extractor=dict(
        type='SingleRoIExtractor',
        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
        out_channels=256,
        featmap_strides=[4, 8, 16, 32]),
    bbox_head=[
        dict(
            type='SharedFCBBoxHead',
            num_fcs=2,
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=20,
            target_means=[0., 0., 0., 0.],
            target_stds=[0.1, 0.1, 0.2, 0.2],
            reg_class_agnostic=True,
            loss_cls=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
            loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
        dict(
            type='SharedFCBBoxHead',
            num_fcs=2,
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=20,
            target_means=[0., 0., 0., 0.],
            target_stds=[0.05, 0.05, 0.1, 0.1],
            reg_class_agnostic=True,
            loss_cls=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
            loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
        dict(
            type='SharedFCBBoxHead',
            num_fcs=2,
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=20,
            target_means=[0., 0., 0., 0.],
            target_stds=[0.033, 0.033, 0.067, 0.067],
            reg_class_agnostic=True,
            loss_cls=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
            loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
    ])
# model training and testing settings
train_cfg = dict(
    rpn=dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.7,
            neg_iou_thr=0.3,
            min_pos_iou=0.3,
            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=0,
        pos_weight=-1,
        debug=False),
    rpn_proposal=dict(
        nms_across_levels=False,
        nms_pre=2000,
        nms_post=2000,
        max_num=2000,
        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,
                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),
        dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.6,
                neg_iou_thr=0.6,
                min_pos_iou=0.6,
                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),
        dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.7,
                neg_iou_thr=0.7,
                min_pos_iou=0.7,
                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)
    ],
    stage_loss_weights=[1, 0.5, 0.25])
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_thr=0.5), max_per_img=100),
    keep_all_stages=False)
# dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
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', **img_norm_cfg),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
val_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', **img_norm_cfg),
    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', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]
data = dict(
    imgs_per_gpu=1,
    workers_per_gpu=8,
    train=dict(
        type=dataset_type,
        ann_file=data_root + 'VOC2007/ImageSets/Main/train.txt',
        img_prefix=data_root + 'VOC2007',
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        ann_file=data_root + 'VOC2007/ImageSets/Main/val.txt',
        img_prefix=data_root + 'VOC2007',
        pipeline=val_pipeline),
    test=dict(
        type=dataset_type,
        ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
        img_prefix=data_root + 'VOC2007',
        pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.0025, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=1.0 / 3,
    step=[16, 19])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=1,
    hooks=[
        dict(type='TextLoggerHook'),
        dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
# runtime settings
total_epochs = 20
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/cascade_rcnn_hrnetv2p_w32'
load_from = None
resume_from = None
workflow = [('train', 1), ('val', 1)]

开启tensorboard，执行如下命令： 

tensorboard --logdir=work_dirs/cascade_rcnn_hrnetv2p_w32/

开启成功可以看到如下现象：

我们可以通过浏览器访问

http://localhost:6006/

，便可以看到tensorboard的信息，但是通常我们训练是在服务器上进行的，可能不方便接显示器，无法通过服务器的浏览器对上述连接进行访问，因此需要端口转发将服务器上的6006端口转发到其它便于访问的主机上，一种简单的方式是通过ssh实现端口转发，在PC上开启命令行模式输入如下指令： 

ssh -p 50000 -L 16006:127.0.0.1:6006 lhy@192.168.3.11

接下来，在PC的浏览器上输入如下链接： 

http://127.0.0.1:16006/

如果一切正常，可以看到tensorboard的界面了：

左边一栏是训练集的指标，右边是验证集的指标。

另外，mmdetection会自动收集log信息，存储在work_dirs/cascade_rcnn_hrnetv2p_w32目录下，官方提供了tools/analyze_logs.py工具可以轻松的可视化日志信息，如可视化损失值并保存为pdf文件，执行如下命令： 

python tools/analyze_logs.py plot_curve work_dirs/cascade_rcnn_hrnetv2p_w32/20191130_125701.log.json  --keys loss --out losses.pdf

结果图：

疑惑：在添加验证集训练时，只看到训练集的日志信息，看不到验证集的日志信息，mmdetection的日志存储目录下也只有训练集的日志信息没有验证集的日志信息，有哪位知悉原因望指教。


版权声明：本文为weicao1990原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。