mmdetection进阶之相关技巧汇总
mmdetection检测相关技巧
- albumentations数据增强
- 多尺度训练
- OHEM 在线难例挖掘
- softnms
- cascade rcnn
albumentations数据增强
alb的数据增强方式输入输出和mmdetection一致所以可以很好的嵌入到框架中
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Albu', transforms = [{"type": 'RandomRotate90'}]),# 数据增强
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
多尺度训练
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=[(1333, 800),(1333,640)] keep_ratio=True), #这里可以更换多尺度[(),()]
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
主要看 dict(type=‘Resize’, img_scale=[(1333, 800),(1333,640)] keep_ratio=True),参数，这里代表的意义是最大边不能超过1333，最小边在640-800之间选择。当keep_ratio=False时，img_scale的多尺度可以为任意多个。假设多尺度为[(2000, 1200), (1666, 1000),(1333, 800)]，则代表的含义为：随机从三个尺度中选取一个作为图像的尺寸进行训练。
OHEM 在线难例挖掘
rcnn=[
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.4, # 更换
neg_iou_thr=0.4,
min_pos_iou=0.4,
ignore_iof_thr=-1),
sampler=dict(
type='OHEMSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='OHEMSampler', # 解决难易样本，也解决了正负样本比例问题。
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
ignore_iof_thr=-1),
sampler=dict(
type='OHEMSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)
],
stage_loss_weights=[1, 0.5, 0.25])
主要是用于两阶段目标检测中正样本的proposal，对应的修改其sampler的type为OHEMSampler即可。
softnms
softnms一般使用在test中
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.001) # soft_nms参数
)
cascade rcnn
fp16 = dict(loss_scale=512.)
# model settings
model = dict(
type='CascadeRCNN',
num_stages=3,
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
#dcn=dict( #在最后三个block加入可变形卷积
# modulated=False, deformable_groups=1, fallback_on_stride=False),
# stage_with_dcn=(False, True, True, True)
),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.2, 0.5, 1.0, 2.0, 5.0], # 添加了0.2，5，过两天发图
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
loss_cls=dict(
type='FocalLoss', use_sigmoid=True, loss_weight=1.0), # 修改了loss，为了调控难易样本与正负样本比例
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=11,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=11,
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 0.1],
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=11,
target_means=[0., 0., 0., 0.],
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
])
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=[
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.4, # 更换
neg_iou_thr=0.4,
min_pos_iou=0.4,
ignore_iof_thr=-1),
sampler=dict(
type='OHEMSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
type='OHEMSampler', # 解决难易样本，也解决了正负样本比例问题。
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
ignore_iof_thr=-1),
sampler=dict(
type='OHEMSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)
],
stage_loss_weights=[1, 0.5, 0.25])
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=20)) # 这里可以换为soft_nms
# dataset settings
dataset_type = 'CocoDataset'
data_root = '../../data/chongqing1_round1_train1_20191223/'
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='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=(492,658), keep_ratio=True), #这里可以更换多尺度[(),()]
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(492,658),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=8, # 有的同学不知道batchsize在哪修改，其实就是修改这里，每个gpu同时处理的images数目。
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'fixed_annotations.json', # 更换自己的json文件
img_prefix=data_root + 'images/', # images目录
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'fixed_annotations.json',
img_prefix=data_root + 'images/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'fixed_annotations.json',
img_prefix=data_root + 'images/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001) # lr = 0.00125*batch_size，不能过大，否则梯度爆炸。
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[6, 12, 19])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=64,
hooks=[
dict(type='TextLoggerHook'), # 控制台输出信息的风格
# dict(type='TensorboardLoggerHook') # 需要安装tensorflow and tensorboard才可以使用
])
# yapf:enable
# runtime settings
total_epochs = 20
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = '../work_dirs/cascade_rcnn_r50_fpn_1x' # 日志目录
load_from = '../work_dirs/cascade_rcnn_r50_fpn_1x/latest.pth' # 模型加载目录文件
#load_from = '../work_dirs/cascade_rcnn_r50_fpn_1x/cascade_rcnn_r50_coco_pretrained_weights_classes_11.pth'
resume_from = None
workflow = [('train', 1)]