resnet18_8xb16_cifar10
18层 8卡 b16:batch(8×16) cifar10:数据集 mixup:数据增强 coslr:学习率衰减
_base__ 网络结构models、数据集定义datasets、学习策略schedules、常规训练方式
model = dict(
type='ImageClassifier',
backbone=dict(
type='ResNet',
depth=18,
num_stages=4,
out_indices=(3, ),
style='pytorch'),
neck=dict(type='GlobalAveragePooling'),
head=dict(
type='LinearClsHead',
num_classes=1000,
in_channels=512,
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
topk=(1, 5),
))
type:mmcls--models--classifiers--image.py--ImageClassifier(forward train)
backbone:mmcls--models--backbones--resnet.py 提特征
neck:融合策略 GlobalAveragePooling大小相等
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', size=224),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='Resize', size=(256, -1)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
samples_per_gpu=32,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_prefix='data/imagenet/train',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline),
test=dict(
# replace `data/val` with `data/test` for standard test
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='accuracy')
dataset_type:mmcls--datasets--imagenet.py
img_norm_cfg:标准化,均值、标准差 x-μ/σ
train_pipeline、test_pipeline:数据预处理
type:是调用mmcls中的--datasets--pipelines中的方法
data = dict(
samples_per_gpu=32, 单卡的batchsize,或多卡每个卡的batchsize
workers_per_gpu=2,
train=dict( 训练集
type=dataset_type,
data_prefix='data/imagenet/train', 读取路径,不指定标签,以标签文件夹为标签
pipeline=train_pipeline),
val=dict( 验证集
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt', 指定标签文件路径名,则以文件中标签
pipeline=test_pipeline),
test=dict( 测试集
# replace `data/val` with `data/test` for standard test
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='accuracy') 评估,interval经过1epoch后走验证集,metric要打印哪些指标
# optimizer
optimizer = dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(policy='step', step=[30, 60, 90])
runner = dict(type='EpochBasedRunner', max_epochs=100)
optimizer:优化器 学习率 动量 学习率衰减
lr_config:迭代30、60、90次衰减
runner:最终迭代多少次
# checkpoint saving
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=100,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
checkpoint_config:多少个后进行保存
log_config:保存日志,迭代多少次保存信息