OpenMMLab AI实战训练营day9MMsegmentation代码实战

原创 于 2023-06-14 20:06:16 发布 · 223 阅读 · 0 ·
CC 4.0 BY-SA版权
版权声明：本文为博主原创文章，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。
文章标签：

#人工智能 #python #数学建模

文章介绍了如何在OpenMMLab框架中创建自定义数据集类，注册该数据集，并编写配置文件以进行模型训练。具体步骤包括定义数据集类，指定图像和标注文件的扩展名，以及设置训练过程中的数据预处理参数。此外，还展示了模型结构和训练配置，如ResNetV1c作为backbone，PSPHead和FCNHead作为解码头，以及训练和验证的pipeline。

摘要生成于 C知道 ，由 DeepSeek-R1 满血版支持， 前往体验 >

OpenMMLab AI实战训练营day9MMsegmentation代码实战

书写自己的数据集类

from mmseg.registry import DATASETS
from .basesegdataset import BaseSegDataset

@DATASETS.register_module()
class MyDataset(BaseSegDataset):
    # 类别和对应的可视化配色
    METAINFO = {
        'classes':['Red', 'Green', 'White', 'Seed-black', 'Seed-white', 'Unlabeled'],
        'palette':[[132,41,246], [228,193,110], [152,16,60], [58,221,254], [41,169,226], [155,155,155]]
    }
    
    # 指定图像扩展名、标注扩展名
    def __init__(self,
                 img_suffix='.jpg',
                 seg_map_suffix='.png',
                 reduce_zero_label=False, # 类别ID为0的类别是否需要除去
                 **kwargs) -> None:
        super().__init__(
            img_suffix=img_suffix,
            seg_map_suffix=seg_map_suffix,
            reduce_zero_label=reduce_zero_label,
            **kwargs)

注册数据集类

# Copyright (c) OpenMMLab. All rights reserved.
# yapf: disable
from .ade import ADE20KDataset
from .basesegdataset import BaseCDDataset, BaseSegDataset
from .chase_db1 import ChaseDB1Dataset
from .cityscapes import CityscapesDataset
from .coco_stuff import COCOStuffDataset
from .dark_zurich import DarkZurichDataset
from .dataset_wrappers import MultiImageMixDataset
from .decathlon import DecathlonDataset
from .drive import DRIVEDataset
from .dsdl import DSDLSegDataset
from .hrf import HRFDataset
from .isaid import iSAIDDataset
from .isprs import ISPRSDataset
from .levir import LEVIRCDDataset
from .lip import LIPDataset
from .loveda import LoveDADataset
from .mapillary import MapillaryDataset_v1, MapillaryDataset_v2
from .night_driving import NightDrivingDataset
from .pascal_context import PascalContextDataset, PascalContextDataset59
from .potsdam import PotsdamDataset
from .refuge import REFUGEDataset
from .stare import STAREDataset
from .synapse import SynapseDataset
from .MyDataset import MyDataset
# yapf: disable
from .transforms import (CLAHE, AdjustGamma, Albu, BioMedical3DPad,
                         BioMedical3DRandomCrop, BioMedical3DRandomFlip,
                         BioMedicalGaussianBlur, BioMedicalGaussianNoise,
                         BioMedicalRandomGamma, ConcatCDInput, GenerateEdge,
                         LoadAnnotations, LoadBiomedicalAnnotation,
                         LoadBiomedicalData, LoadBiomedicalImageFromFile,
                         LoadImageFromNDArray, LoadMultipleRSImageFromFile,
                         LoadSingleRSImageFromFile, PackSegInputs,
                         PhotoMetricDistortion, RandomCrop, RandomCutOut,
                         RandomMosaic, RandomRotate, RandomRotFlip, Rerange,
                         ResizeShortestEdge, ResizeToMultiple, RGB2Gray,
                         SegRescale)
from .voc import PascalVOCDataset

# yapf: enable
__all__ = [
    'BaseSegDataset', 'BioMedical3DRandomCrop', 'BioMedical3DRandomFlip',
    'CityscapesDataset', 'PascalVOCDataset', 'ADE20KDataset',
    'PascalContextDataset', 'PascalContextDataset59', 'ChaseDB1Dataset',
    'DRIVEDataset', 'HRFDataset', 'STAREDataset', 'DarkZurichDataset',
    'NightDrivingDataset', 'COCOStuffDataset', 'LoveDADataset',
    'MultiImageMixDataset', 'iSAIDDataset', 'ISPRSDataset', 'PotsdamDataset',
    'LoadAnnotations', 'RandomCrop', 'SegRescale', 'PhotoMetricDistortion',
    'RandomRotate', 'AdjustGamma', 'CLAHE', 'Rerange', 'RGB2Gray',
    'RandomCutOut', 'RandomMosaic', 'PackSegInputs', 'ResizeToMultiple',
    'LoadImageFromNDArray', 'LoadBiomedicalImageFromFile',
    'LoadBiomedicalAnnotation', 'LoadBiomedicalData', 'GenerateEdge',
    'DecathlonDataset', 'LIPDataset', 'ResizeShortestEdge',
    'BioMedicalGaussianNoise', 'BioMedicalGaussianBlur',
    'BioMedicalRandomGamma', 'BioMedical3DPad', 'RandomRotFlip',
    'SynapseDataset', 'REFUGEDataset', 'MapillaryDataset_v1',
    'MapillaryDataset_v2', 'Albu', 'LEVIRCDDataset',
    'LoadMultipleRSImageFromFile', 'LoadSingleRSImageFromFile',
    'ConcatCDInput', 'BaseCDDataset', 'DSDLSegDataset','MyDataset'
]

自定义config文件

norm_cfg = dict(type='BN', requires_grad=True)
data_preprocessor = dict(
    type='SegDataPreProcessor',
    mean=[123.675, 116.28, 103.53],
    std=[58.395, 57.12, 57.375],
    bgr_to_rgb=True,
    pad_val=0,
    seg_pad_val=255,
    size=(64, 64))
model = dict(
    type='EncoderDecoder',
    data_preprocessor=dict(
        type='SegDataPreProcessor',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        bgr_to_rgb=True,
        pad_val=0,
        seg_pad_val=255,
        size=(256, 256)),
    pretrained='open-mmlab://resnet50_v1c',
    backbone=dict(
        type='ResNetV1c',
        depth=50,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        dilations=(1, 1, 2, 4),
        strides=(1, 2, 1, 1),
        norm_cfg=dict(type='BN', requires_grad=True),
        norm_eval=False,
        style='pytorch',
        contract_dilation=True),
    decode_head=dict(
        type='PSPHead',
        in_channels=2048,
        in_index=3,
        channels=512,
        pool_scales=(1, 2, 3, 6),
        dropout_ratio=0.1,
        num_classes=6,
        norm_cfg=dict(type='BN', requires_grad=True),
        align_corners=False,
        loss_decode=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
    auxiliary_head=dict(
        type='FCNHead',
        in_channels=1024,
        in_index=2,
        channels=256,
        num_convs=1,
        concat_input=False,
        dropout_ratio=0.1,
        num_classes=6,
        norm_cfg=dict(type='BN', requires_grad=True),
        align_corners=False,
        loss_decode=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
    train_cfg=dict(),
    test_cfg=dict(mode='whole'))
dataset_type = 'MyDataset'
data_root = 'E:\\github\\MyOpenMMLab\\homework_4_mmseg\\dataset\\Watermelon87_Semantic_Seg_Mask\\'
crop_size = (256, 256)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations'),
    dict(
        type='RandomResize',
        scale=(2048, 1024),
        ratio_range=(0.5, 2.0),
        keep_ratio=True),
    dict(type='RandomCrop', crop_size=(64, 64), cat_max_ratio=0.75),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PhotoMetricDistortion'),
    dict(type='PackSegInputs')
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
    dict(type='LoadAnnotations'),
    dict(type='PackSegInputs')
]
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
tta_pipeline = [
    dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
    dict(
        type='TestTimeAug',
        transforms=[[{
            'type': 'Resize',
            'scale_factor': 0.5,
            'keep_ratio': True
        }, {
            'type': 'Resize',
            'scale_factor': 0.75,
            'keep_ratio': True
        }, {
            'type': 'Resize',
            'scale_factor': 1.0,
            'keep_ratio': True
        }, {
            'type': 'Resize',
            'scale_factor': 1.25,
            'keep_ratio': True
        }, {
            'type': 'Resize',
            'scale_factor': 1.5,
            'keep_ratio': True
        }, {
            'type': 'Resize',
            'scale_factor': 1.75,
            'keep_ratio': True
        }],
                    [{
                        'type': 'RandomFlip',
                        'prob': 0.0,
                        'direction': 'horizontal'
                    }, {
                        'type': 'RandomFlip',
                        'prob': 1.0,
                        'direction': 'horizontal'
                    }], [{
                        'type': 'LoadAnnotations'
                    }], [{
                        'type': 'PackSegInputs'
                    }]])
]
train_dataloader = dict(
    batch_size=8,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(type='InfiniteSampler', shuffle=True),
    dataset=dict(
        type='MyDataset',
        data_root=data_root,
        data_prefix=dict(
            img_path='img_dir/train', seg_map_path='ann_dir/train'),
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations'),
            dict(
                type='RandomResize',
                scale=(2048, 1024),
                ratio_range=(0.5, 2.0),
                keep_ratio=True),
            dict(type='RandomCrop', crop_size=(64, 64), cat_max_ratio=0.75),
            dict(type='RandomFlip', prob=0.5),
            dict(type='PhotoMetricDistortion'),
            dict(type='PackSegInputs')
        ]))
val_dataloader = dict(
    batch_size=1,
    num_workers=4,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type='MyDataset',
        data_root=data_root,
        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
            dict(type='LoadAnnotations'),
            dict(type='PackSegInputs')
        ]))
test_dataloader = dict(
    batch_size=1,
    num_workers=4,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type='MyDataset',
        data_root=data_root,
        data_prefix=dict(img_path='img_dir/val', seg_map_path='ann_dir/val'),
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
            dict(type='LoadAnnotations'),
            dict(type='PackSegInputs')
        ]))
val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
test_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
default_scope = 'mmseg'
env_cfg = dict(
    cudnn_benchmark=True,
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    dist_cfg=dict(backend='nccl'))
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
    type='SegLocalVisualizer',
    vis_backends=[dict(type='LocalVisBackend')],
    name='visualizer')
log_processor = dict(by_epoch=False)
log_level = 'INFO'
load_from = None
resume = False
tta_model = dict(type='SegTTAModel')
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005),
    clip_grad=None)
param_scheduler = [
    dict(
        type='PolyLR',
        eta_min=0.0001,
        power=0.9,
        begin=0,
        end=40000,
        by_epoch=False)
]
train_cfg = dict(type='IterBasedTrainLoop', max_iters=3000, val_interval=400)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
default_hooks = dict(
    timer=dict(type='IterTimerHook'),
    logger=dict(type='LoggerHook', interval=100, log_metric_by_epoch=False),
    param_scheduler=dict(type='ParamSchedulerHook'),
    checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=1500),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    visualization=dict(type='SegVisualizationHook'))
work_dir = './work_dirs/mydataset'
randomness = dict(seed=0)

训练

调用api进行训练

WeiZi.
关注
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值