OpenMMLab AI实战训练营day9MMsegmentation代码实战-CSDN博客

本文链接：https://blog.csdn.net/lgwwslgw/article/details/131214990

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