Config命名格式：
代码语言：javascript复制{model}_{backbone}_[misc]_[gpu x batch_per_gpu]_{resolution}_{schedule}_{dataset}以下为每一项的具体解释：
- {xxx}是必填字段，[yyy]是可选字段。
- {model}：型号类型等psp，deeplabv3等。
- {backbone}：骨干类型，例如r50（ResNet-50），x101（ResNeXt-101）。
- [misc]：杂项设置/模型的插件，例如dconv，gcb，attention，mstrain。
- [gpu x batch_per_gpu]：8x2默认使用GPU和每个GPU的样本。
- {schedule}：训练时间表，20ki意味着20k次迭代。
- {dataset}：数据集cityscapes，voc12aug，ade
norm_cfg = dict(type='SyncBN', requires_grad=True) # 批归一化
backbone_norm_cfg = dict(type='LN', requires_grad=True) # LayerNorm 层归一话
model = dict(
type='EncoderDecoder', #语义分割模型类型
pretrained='pretrain/swin_base_patch4_window7_224.pth', # 加载ImageNet预训练的backbone,这类为swin base模型
backbone=dict(
type='SwinTransformer', # backone的类型
pretrain_img_size=224,
embed_dims=128,
patch_size=4,
window_size=7,
mlp_ratio=4,
depths=[2, 2, 18, 2],
num_heads=[4, 8, 16, 32],
strides=(4, 2, 2, 2),
out_indices=(0, 1, 2, 3),
qkv_bias=True,
qk_scale=None,
patch_norm=True,
drop_rate=0.0,
attn_drop_rate=0.0,
drop_path_rate=0.3,
use_abs_pos_embed=False,
act_cfg=dict(type='GELU'),
norm_cfg=dict(type='LN', requires_grad=True)),
decode_head=dict(
type='UPerHead', # 解码器类型
in_channels=[128, 256, 512, 1024], # 解码器输入通道个数
in_index=[0, 1, 2, 3], #选择特征图的索引
pool_scales=(1, 2, 3, 6),
channels=512, # 解码器头的中间通道数
dropout_ratio=0.1, #分类层的之前的dropout概率
num_classes=150,#分割类别的数量，
norm_cfg=dict(type='SyncBN', requires_grad=True),
align_corners=False, # 用于在解码时调整大小
loss_decode=dict( # # 解码器损失函数的配置
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),
auxiliary_head=dict( # auxiliary_head（辅助头）的类型，
type='FCNHead',
in_channels=512, # 辅助头输入的通道个数
in_index=2, # 选择特征图索引
channels=256,# 解码器的中间通道
num_convs=1, # FCNHead的卷积数，在auxiliary_head通常是1
concat_input=False, # 是否将convs的输出与分类器之前的输入进行拼接
dropout_ratio=0.1,
num_classes=150,
norm_cfg=dict(type='SyncBN', requires_grad=True),
align_corners=False,
loss_decode=dict(
type='LovaszLoss', classes='present', per_image=True, reduction='mean', loss_weight=0.4)),
train_cfg=dict(),
test_cfg=dict(mode='whole'))
dataset_type = 'SatelliteDataset' # 数据集类型，将用于定义数据集
data_root = 'data/sensing/jpg' # 数据的根路径
img_norm_cfg = dict( # 图像归一化配置以对输入图像进行归一化
mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225], to_rgb=True)
crop_size = (512, 512) #训练时的图像剪裁大小
train_pipeline = [ # # 训练流水线
dict(type='LoadImageFromFile'), # 从文件中加载训练图像
dict(type='LoadAnnotations', reduce_zero_label=False), # 加载标签图像，False代表标签包含0
dict(type='Resize', img_scale=(512, 256), ratio_range=(0.5, 2.0)), # 增强通道以调整图像的大小及其注释
dict(type='RandomCrop', crop_size=(256, 256), cat_max_ratio=0.75), # 从当前图像中随机裁剪一patch
dict(type='RandomFlip', prob=0.5), # 翻转图像以及概率
dict(type='PhotoMetricDistortion'), # 通过多种光度学方法使当前图像失真
dict(
type='Normalize', # 标准化输入图像的增强通道
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
to_rgb=True),
dict(type='Pad', size=(256, 256), pad_val=0, seg_pad_val=255), # 将图像填充到指定大小
dict(type='DefaultFormatBundle'), # 默认格式捆绑包，用于收集管道中的数据
dict(type='Collect', keys=['img', 'gt_semantic_seg']) # 决定将数据中的哪些键传递给分割器
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(512, 256),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
to_rgb=True),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=2, # 单个GPU的批处理大小
workers_per_gpu=4,#
train=dict(
type='SatelliteDataset',
data_root='data/sensing/jpg',
img_dir='images/training',
ann_dir='annotations/training',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', reduce_zero_label=False),
dict(type='Resize', img_scale=(512, 256), ratio_range=(0.5, 2.0)),
dict(type='RandomCrop', crop_size=(256, 256), cat_max_ratio=0.75),
dict(type='RandomFlip', prob=0.5),
dict(type='PhotoMetricDistortion'),
dict(
type='Normalize',
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
to_rgb=True),
dict(type='Pad', size=(256, 256), pad_val=0, seg_pad_val=255),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]),
val=dict(
type='SatelliteDataset',
data_root='data/sensing/jpg',
img_dir='images/validation',
ann_dir='annotations/validation',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(512, 256),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
to_rgb=True),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='SatelliteDataset',
data_root='data/sensing/jpg',
img_dir='images/test',
ann_dir='annotations/test',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(512, 256),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Normalize',
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
to_rgb=True),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]))
log_config = dict(
interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)]) # 间隔打印日志
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)] # Workflow for runner [（'train'，1）]表示只有一个工作流程，名为'train'的工作流程只执行一次。
cudnn_benchmark = True #是否使用cudnn_benchmark加快速度，只适用于固定输入大小
optimizer = dict(
type='AdamW',
lr=6e-05,
betas=(0.9, 0.999),
weight_decay=0.01,
paramwise_cfg=dict(
custom_keys=dict(
absolute_pos_embed=dict(decay_mult=0.0),
relative_position_bias_table=dict(decay_mult=0.0),
norm=dict(decay_mult=0.0))))
optimizer_config = dict()
lr_config = dict(
policy='poly',
# # scheduler的策略还支持Step，CosineAnnealing，Cyclic等。
warmup='linear',
warmup_iters=1500,
warmup_ratio=1e-06,
power=1.0,
min_lr=0.0,
by_epoch=False)
runner = dict(type='IterBasedRunner', max_iters=40000)
checkpoint_config = dict(by_epoch=False, interval=10000)
evaluation = dict(interval=10000, metric='mIoU', pre_eval=True)
work_dir = './work_dirs/swin_tiny_patch4_window7_224'
gpu_ids = range(0, 1)
auto_resume = False
