MMsegmentation自定义Config配置文件逐段解读

历史记录

清除记录

猜你想搜

AcWing热点
App
登录/注册

MMsegmentation自定义Config配置文件逐段解读

作者：

dsc182 , 2024-11-13 15:36:01 , 所有人可见 , 阅读 2

# 图像剪裁大小
crop_size = (
    512,
    512,
)

data_preprocessor = dict(
    bgr_to_rgb=True,
    # 转换图像颜色通道（BGR->RGB）,因为OpenCV读取图像时使用BGR顺序，转换为RGB以适应大多数深度学习框架。
    mean=[
        123.675,
        116.28,
        103.53,
    ],
    # mean表示输入图像的均值（针对每个颜色通道）。用于数据标准化，减少不同图像间的光照差异。
    pad_val=0,
    seg_pad_val=255,
    size=(
        512,
        1024,
    ),
    std=[
        58.395,
        57.12,
        57.375,
    ], # std输入图像的标准差
    type='SegDataPreProcessor')

data_root = 'Watermelon87_Semantic_Seg_Mask/' # 数据集地址
dataset_type = 'ZihaoDataset' # 数据集类名

default_hooks = dict(
    checkpoint=dict(
        by_epoch=False,
        interval=20,
        max_keep_ckpts=2,
        save_best='mIoU',
        type='CheckpointHook'),
    logger=dict(interval=20, log_metric_by_epoch=False, type='LoggerHook'),
    param_scheduler=dict(type='ParamSchedulerHook'),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    timer=dict(type='IterTimerHook'),
    visualization=dict(type='SegVisualizationHook'))
# checkpoint: 定义检查点保存策略，例如每20个epoch保存一次模型，并保持最新的两个检查点。
# logger: 设置日志记录的频率，interval=20表示每20个步骤记录一次日志。
# param_scheduler: 用于调整学习率的调度器。
# sampler_seed: 用于分布式训练时的种子配置。
# timer: 计时器，用于训练过程中的时间统计。
# visualization: 用于每个训练步骤可视化分割结果。

default_scope = 'mmseg'
env_cfg = dict(
    cudnn_benchmark=True,
    dist_cfg=dict(backend='nccl'),
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
img_ratios = [
    0.5,
    0.75,
    1.0,
    1.25,
    1.5,
    1.75,
]
load_from = None
log_level = 'INFO'
log_processor = dict(by_epoch=False)

model = dict(
    auxiliary_head=[
        dict(
            align_corners=False,
            channels=32,
            concat_input=False,
            in_channels=128,
            in_index=-2,
            loss_decode=dict(
                loss_weight=0.4, type='CrossEntropyLoss', use_sigmoid=True),
            norm_cfg=dict(requires_grad=True, type='BN'),
            num_classes=6,
            num_convs=1,
            type='FCNHead'),
        dict(
            align_corners=False,
            channels=32,
            concat_input=False,
            in_channels=64,
            in_index=-3,
            loss_decode=dict(
                loss_weight=0.4, type='CrossEntropyLoss', use_sigmoid=True),
            norm_cfg=dict(requires_grad=True, type='BN'),
            num_classes=6,
            num_convs=1,
            type='FCNHead'),
    ],
    backbone=dict(
        align_corners=False,
        downsample_dw_channels=(
            32,
            48,
        ),
        fusion_out_channels=128,
        global_block_channels=(
            64,
            96,
            128,
        ),
        global_block_strides=(
            2,
            2,
            1,
        ),
        global_in_channels=64,
        global_out_channels=128,
        higher_in_channels=64,
        lower_in_channels=128,
        norm_cfg=dict(requires_grad=True, type='BN'),
        out_indices=(
            0,
            1,
            2,
        ),
        type='FastSCNN'),
    data_preprocessor=dict(
        bgr_to_rgb=True,
        mean=[
            123.675,
            116.28,
            103.53,
        ],
        pad_val=0,
        seg_pad_val=255,
        size=(
            512,
            1024,
        ),
        std=[
            58.395,
            57.12,
            57.375,
        ],
        type='SegDataPreProcessor'),
    decode_head=dict(
        align_corners=False,
        channels=128,
        concat_input=False,
        in_channels=128,
        in_index=-1,
        loss_decode=dict(
            loss_weight=1, type='CrossEntropyLoss', use_sigmoid=True),
        norm_cfg=dict(requires_grad=True, type='BN'),
        num_classes=6,
        type='DepthwiseSeparableFCNHead'),
    test_cfg=dict(mode='whole'),
    train_cfg=dict(),
    type='EncoderDecoder')
# auxiliary_head: 定义了两个辅助头部，通常用于多尺度或多任务学习，每个头部用于不同尺度特征的处理。FCNHead是全卷积网络头部，采用交叉熵损失函数（CrossEntropyLoss）来进行分类。
# backbone: 主干网络使用 FastSCNN，这是一种轻量级的卷积神经网络，适用于实时分割任务。定义了多个模块的输出通道数、步幅等。
# decode_head: 解码头部，通常用于生成分割图，采用DepthwiseSeparableFCNHead，它通过深度可分离卷积来减少计算量。
# test_cfg: 定义测试配置，这里采用了全图推理模式（mode='whole'），即整个图像进行推理。

norm_cfg = dict(requires_grad=True, type='BN')
optim_wrapper = dict(
    clip_grad=None,
    optimizer=dict(lr=0.12, momentum=0.9, type='SGD', weight_decay=4e-05),
    type='OptimWrapper')
optimizer = dict(lr=0.12, momentum=0.9, type='SGD', weight_decay=4e-05)
param_scheduler = [
    dict(
        begin=0,
        by_epoch=False,
        end=160000,
        eta_min=0.0001,
        power=0.9,
        type='PolyLR'),
]
randomness = dict(seed=0)
resume = False
test_cfg = dict(type='TestLoop')
test_dataloader = dict(
    batch_size=1,
    dataset=dict(
        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
        data_root='Watermelon87_Semantic_Seg_Mask/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(
                2048,
                1024,
            ), type='Resize'),
            dict(type='LoadAnnotations'),
            dict(type='PackSegInputs'),
        ],
        type='ZihaoDataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
test_evaluator = dict(
    iou_metrics=[
        'mIoU',
        'mDice',
        'mFscore',
    ], type='IoUMetric')
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(keep_ratio=True, scale=(
        2048,
        1024,
    ), type='Resize'),
    dict(type='LoadAnnotations'),
    dict(type='PackSegInputs'),
]
train_cfg = dict(max_iters=500, type='IterBasedTrainLoop', val_interval=20)
train_dataloader = dict(
    batch_size=3,
    dataset=dict(
        data_prefix=dict(
            img_path='img_dir/train', seg_map_path='ann_dir/train'),
        data_root='Watermelon87_Semantic_Seg_Mask/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations'),
            dict(
                keep_ratio=True,
                ratio_range=(
                    0.5,
                    2.0,
                ),
                scale=(
                    2048,
                    1024,
                ),
                type='RandomResize'),
            dict(
                cat_max_ratio=0.75, crop_size=(
                    512,
                    512,
                ), type='RandomCrop'),
            dict(prob=0.5, type='RandomFlip'),
            dict(type='PhotoMetricDistortion'),
            dict(type='PackSegInputs'),
        ],
        type='ZihaoDataset'),
    num_workers=2,
    persistent_workers=True,
    sampler=dict(shuffle=True, type='InfiniteSampler'))
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations'),
    dict(
        keep_ratio=True,
        ratio_range=(
            0.5,
            2.0,
        ),
        scale=(
            2048,
            1024,
        ),
        type='RandomResize'),
    dict(cat_max_ratio=0.75, crop_size=(
        512,
        512,
    ), type='RandomCrop'),
    dict(prob=0.5, type='RandomFlip'),
    dict(type='PhotoMetricDistortion'),
    dict(type='PackSegInputs'),
]
tta_model = dict(type='SegTTAModel')
tta_pipeline = [
    dict(file_client_args=dict(backend='disk'), type='LoadImageFromFile'),
    dict(
        transforms=[
            [
                dict(keep_ratio=True, scale_factor=0.5, type='Resize'),
                dict(keep_ratio=True, scale_factor=0.75, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.0, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.25, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.5, type='Resize'),
                dict(keep_ratio=True, scale_factor=1.75, type='Resize'),
            ],
            [
                dict(direction='horizontal', prob=0.0, type='RandomFlip'),
                dict(direction='horizontal', prob=1.0, type='RandomFlip'),
            ],
            [
                dict(type='LoadAnnotations'),
            ],
            [
                dict(type='PackSegInputs'),
            ],
        ],
        type='TestTimeAug'),
]
val_cfg = dict(type='ValLoop')
val_dataloader = dict(
    batch_size=1,
    dataset=dict(
        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
        data_root='Watermelon87_Semantic_Seg_Mask/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(
                2048,
                1024,
            ), type='Resize'),
            dict(type='LoadAnnotations'),
            dict(type='PackSegInputs'),
        ],
        type='ZihaoDataset'),
    num_workers=4,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
val_evaluator = dict(
    iou_metrics=[
        'mIoU',
        'mDice',
        'mFscore',
    ], type='IoUMetric')
vis_backends = [
    dict(type='LocalVisBackend'),
]
visualizer = dict(
    name='visualizer',
    type='SegLocalVisualizer',
    vis_backends=[
        dict(type='LocalVisBackend'),
    ])
work_dir = './work_dirs/ZihaoDataset-FastSCNN'

0 评论

App 内打开