【OpenMMLab AI实战营第二期】MMSegmentation简单使用及配置文件介绍

MMSegmentation介绍

代码仓地址：https://github.com/open-mmlab/mmsegmentation
文档库地址：[https://mmsegmentation.readthedocs.io/en/latest/overview.html](https://mmsegmentation.readthedocs.io/en/latest/overview.html]

安装MMSegmentation

安装mmcv和mmengine

pip install -U openmim
mim install mmengine
mim install "mmcv>=2.0.0"

安装mmsegementation

git clone -b main https://github.com/open-mmlab/mmsegmentation.git
cd mmsegmentation
pip install -v -e .

验证安装

下载config文件

mim download mmsegmentation --config pspnet_r50-d8_4xb2-40k_cityscapes-512x1024 --dest .

验证推理demo

python demo/image_demo.py demo/demo.png configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth --device cuda:0 --out-file result.jpg

配置文件（以PSNET50为例）

这部分参考官方文档：https://mmsegmentation.readthedocs.io/

基本配置文件

_base_ = [
    '../_base_/models/pspnet_r50-d8.py', '../_base_/datasets/cityscapes.py',
    '../_base_/default_runtime.py', '../_base_/schedules/schedule_40k.py'
] # base config file which we build new config file on.
crop_size = (512, 1024)
data_preprocessor = dict(size=crop_size)
model = dict(data_preprocessor=data_preprocessor)

模型配置文件

base/models/pspnet_r50-d8.py

# model settings
norm_cfg = dict(type='SyncBN', requires_grad=True)  # Segmentation usually uses SyncBN
data_preprocessor = dict(  # The config of data preprocessor, usually includes image normalization and augmentation.
    type='SegDataPreProcessor',  # The type of data preprocessor.
    mean=[123.675, 116.28, 103.53],  # Mean values used for normalizing the input images.
    std=[58.395, 57.12, 57.375],  # Standard variance used for normalizing the input images.
    bgr_to_rgb=True,  # Whether to convert image from BGR to RGB.
    pad_val=0,  # Padding value of image.
    seg_pad_val=255)  # Padding value of segmentation map.
model = dict(
    type='EncoderDecoder',  # Name of segmentor
    data_preprocessor=data_preprocessor,
    pretrained='open-mmlab://resnet50_v1c',  # The ImageNet pretrained backbone to be loaded
    backbone=dict(
        type='ResNetV1c',  # The type of backbone. Please refer to mmseg/models/backbones/resnet.py for details.
        depth=50,  # Depth of backbone. Normally 50, 101 are used.
        num_stages=4,  # Number of stages of backbone.
        out_indices=(0, 1, 2, 3),  # The index of output feature maps produced in each stages.
        dilations=(1, 1, 2, 4),  # The dilation rate of each layer.
        strides=(1, 2, 1, 1),  # The stride of each layer.
        norm_cfg=norm_cfg,  # The configuration of norm layer.
        norm_eval=False,  # Whether to freeze the statistics in BN
        style='pytorch',  # The style of backbone, 'pytorch' means that stride 2 layers are in 3x3 conv, 'caffe' means stride 2 layers are in 1x1 convs.
        contract_dilation=True),  # When dilation > 1, whether contract first layer of dilation.
    decode_head=dict(
        type='PSPHead',  # Type of decode head. Please refer to mmseg/models/decode_heads for available options.
        in_channels=2048,  # Input channel of decode head.
        in_index=3,  # The index of feature map to select.
        channels=512,  # The intermediate channels of decode head.
        pool_scales=(1, 2, 3, 6),  # The avg pooling scales of PSPHead. Please refer to paper for details.
        dropout_ratio=0.1,  # The dropout ratio before final classification layer.
        num_classes=19,  # Number of segmentation class. Usually 19 for cityscapes, 21 for VOC, 150 for ADE20k.
        norm_cfg=norm_cfg,  # The configuration of norm layer.
        align_corners=False,  # The align_corners argument for resize in decoding.
        loss_decode=dict(  # Config of loss function for the decode_head.
            type='CrossEntropyLoss',  # Type of loss used for segmentation.
            use_sigmoid=False,  # Whether use sigmoid activation for segmentation.
            loss_weight=1.0)),  # Loss weight of decode_head.
    auxiliary_head=dict(
        type='FCNHead',  # Type of auxiliary head. Please refer to mmseg/models/decode_heads for available options.
        in_channels=1024,  # Input channel of auxiliary head.
        in_index=2,  # The index of feature map to select.
        channels=256,  # The intermediate channels of decode head.
        num_convs=1,  # Number of convs in FCNHead. It is usually 1 in auxiliary head.
        concat_input=False,  # Whether concat output of convs with input before classification layer.
        dropout_ratio=0.1,  # The dropout ratio before final classification layer.
        num_classes=19,  # Number of segmentation class. Usually 19 for cityscapes, 21 for VOC, 150 for ADE20k.
        norm_cfg=norm_cfg,  # The configuration of norm layer.
        align_corners=False,  # The align_corners argument for resize in decoding.
        loss_decode=dict(  # Config of loss function for the auxiliary_head.
            type='CrossEntropyLoss',  # Type of loss used for segmentation.
            use_sigmoid=False,  # Whether use sigmoid activation for segmentation.
            loss_weight=0.4)),  # Loss weight of auxiliary_head.
    # model training and testing settings
    train_cfg=dict(),  # train_cfg is just a place holder for now.
    test_cfg=dict(mode='whole'))  # The test mode, options are 'whole' and 'slide'. 'whole': whole image fully-convolutional test. 'slide': sliding crop window on the image.

数据配置文件

base_/datasets/cityscapes.py

# dataset settings
dataset_type = 'CityscapesDataset'  # Dataset type, this will be used to define the dataset.
data_root = 'data/cityscapes/'  # Root path of data.
crop_size = (512, 1024)  # The crop size during training.
train_pipeline = [  # Training pipeline.
    dict(type='LoadImageFromFile'),  # First pipeline to load images from file path.
    dict(type='LoadAnnotations'),  # Second pipeline to load annotations for current image.
    dict(type='RandomResize',  # Augmentation pipeline that resize the images and their annotations.
        scale=(2048, 1024),  # The scale of image.
        ratio_range=(0.5, 2.0),  # The augmented scale range as ratio.
        keep_ratio=True),  # Whether to keep the aspect ratio when resizing the image.
    dict(type='RandomCrop',  # Augmentation pipeline that randomly crop a patch from current image.
        crop_size=crop_size,  # The crop size of patch.
        cat_max_ratio=0.75),  # The max area ratio that could be occupied by single category.
    dict(type='RandomFlip',  # Augmentation pipeline that flip the images and their annotations
        prob=0.5),  # The ratio or probability to flip
    dict(type='PhotoMetricDistortion'),  # Augmentation pipeline that distort current image with several photo metric methods.
    dict(type='PackSegInputs')  # Pack the inputs data for the semantic segmentation.
]
test_pipeline = [
    dict(type='LoadImageFromFile'),  # First pipeline to load images from file path
    dict(type='Resize',  # Use resize augmentation
        scale=(2048, 1024),  # Images scales for resizing.
        keep_ratio=True),  # Whether to keep the aspect ratio when resizing the image.
    # add loading annotation after ``Resize`` because ground truth
    # does not need to do resize data transform
    dict(type='LoadAnnotations'),  # Load annotations for semantic segmentation provided by dataset.
    dict(type='PackSegInputs')  # Pack the inputs data for the semantic segmentation.
]
train_dataloader = dict(  # Train dataloader config
    batch_size=2,  # Batch size of a single GPU
    num_workers=2,  # Worker to pre-fetch data for each single GPU
    persistent_workers=True,  # Shut down the worker processes after an epoch end, which can accelerate training speed.
    sampler=dict(type='InfiniteSampler', shuffle=True),  # Randomly shuffle during training.
    dataset=dict(  # Train dataset config
        type=dataset_type,  # Type of dataset, refer to mmseg/datasets/ for details.
        data_root=data_root,  # The root of dataset.
        data_prefix=dict(
            img_path='leftImg8bit/train', seg_map_path='gtFine/train'),  # Prefix for training data.
        pipeline=train_pipeline)) # Processing pipeline. This is passed by the train_pipeline created before.
val_dataloader = dict(
    batch_size=1,  # Batch size of a single GPU
    num_workers=4,  # Worker to pre-fetch data for each single GPU
    persistent_workers=True,  # Shut down the worker processes after an epoch end, which can accelerate testing speed.
    sampler=dict(type='DefaultSampler', shuffle=False),  # Not shuffle during validation and testing.
    dataset=dict(  # Test dataset config
        type=dataset_type,  # Type of dataset, refer to mmseg/datasets/ for details.
        data_root=data_root,  # The root of dataset.
        data_prefix=dict(
            img_path='leftImg8bit/val', seg_map_path='gtFine/val'),  # Prefix for testing data.
        pipeline=test_pipeline))  # Processing pipeline. This is passed by the test_pipeline created before.
test_dataloader = val_dataloader
# The metric to measure the accuracy. Here, we use IoUMetric.
val_evaluator = dict(type='IoUMetric', iou_metrics=['mIoU'])
test_evaluator = val_evaluator

base/schedules/schedule_40k.py

# optimizer
optimizer = dict(type='SGD', # Type of optimizers, refer to https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/optimizer/default_constructor.py for more details
                lr=0.01,  # Learning rate of optimizers, see detail usages of the parameters in the documentation of PyTorch
                momentum=0.9,  # Momentum
                weight_decay=0.0005)  # Weight decay of SGD
optim_wrapper = dict(type='OptimWrapper',  # Optimizer wrapper provides a common interface for updating parameters.
                    optimizer=optimizer,  # Optimizer used to update model parameters.
                    clip_grad=None)  # If ``clip_grad`` is not None, it will be the arguments of ``torch.nn.utils.clip_grad``.
# learning policy
param_scheduler = [
    dict(
        type='PolyLR',  # The policy of scheduler, also support Step, CosineAnnealing, Cyclic, etc. Refer to details of supported LrUpdater from https://github.com/open-mmlab/mmengine/blob/main/mmengine/optim/scheduler/lr_scheduler.py
        eta_min=1e-4,  # Minimum learning rate at the end of scheduling.
        power=0.9,  # The power of polynomial decay.
        begin=0,  # Step at which to start updating the parameters.
        end=40000,  # Step at which to stop updating the parameters.
        by_epoch=False)  # Whether count by epoch or not.
]
# training schedule for 40k iteration
train_cfg = dict(type='IterBasedTrainLoop', max_iters=40000, val_interval=4000)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
# default hooks
default_hooks = dict(
    timer=dict(type='IterTimerHook'),  # Log the time spent during iteration.
    logger=dict(type='LoggerHook', interval=50, log_metric_by_epoch=False),  # Collect and write logs from different components of ``Runner``.
    param_scheduler=dict(type='ParamSchedulerHook'),  # update some hyper-parameters in optimizer, e.g., learning rate.
    checkpoint=dict(type='CheckpointHook', by_epoch=False, interval=4000),  # Save checkpoints periodically.
    sampler_seed=dict(type='DistSamplerSeedHook'))  # Data-loading sampler for distributed training.

base/default_runtime.py

# Set the default scope of the registry to mmseg.
default_scope = 'mmseg'
# environment
env_cfg = dict(
    cudnn_benchmark=True,
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    dist_cfg=dict(backend='nccl'),
)
log_level = 'INFO'
log_processor = dict(by_epoch=False)
load_from = None  # Load checkpoint from file.
resume = False  # Whether to resume from existed model.

使用mmengine调用config文件

from mmengine.config import Config

cfg = Config.fromfile('configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py')
print(cfg.train_dataloader)