mirror of https://github.com/open-mmlab/mmpose
271 lines
8.9 KiB
Python
271 lines
8.9 KiB
Python
# runtime settings
|
|
default_scope = 'mmdet'
|
|
|
|
default_hooks = dict(
|
|
timer=dict(type='IterTimerHook'),
|
|
logger=dict(type='LoggerHook', interval=50),
|
|
param_scheduler=dict(type='ParamSchedulerHook'),
|
|
checkpoint=dict(type='CheckpointHook', interval=1),
|
|
sampler_seed=dict(type='DistSamplerSeedHook'),
|
|
visualization=dict(type='DetVisualizationHook'))
|
|
|
|
env_cfg = dict(
|
|
cudnn_benchmark=False,
|
|
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
|
|
dist_cfg=dict(backend='nccl'),
|
|
)
|
|
|
|
vis_backends = [dict(type='LocalVisBackend')]
|
|
visualizer = dict(
|
|
type='DetLocalVisualizer', vis_backends=vis_backends, name='visualizer')
|
|
log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
|
|
|
|
log_level = 'INFO'
|
|
load_from = None
|
|
resume = False
|
|
|
|
# model settings
|
|
model = dict(
|
|
type='CascadeRCNN',
|
|
data_preprocessor=dict(
|
|
type='DetDataPreprocessor',
|
|
mean=[123.675, 116.28, 103.53],
|
|
std=[58.395, 57.12, 57.375],
|
|
bgr_to_rgb=True,
|
|
pad_mask=True,
|
|
pad_size_divisor=32),
|
|
backbone=dict(
|
|
type='ResNeXt',
|
|
depth=101,
|
|
groups=64,
|
|
base_width=4,
|
|
num_stages=4,
|
|
out_indices=(0, 1, 2, 3),
|
|
frozen_stages=1,
|
|
norm_cfg=dict(type='BN', requires_grad=True),
|
|
style='pytorch',
|
|
init_cfg=dict(
|
|
type='Pretrained', checkpoint='open-mmlab://resnext101_64x4d')),
|
|
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_generator=dict(
|
|
type='AnchorGenerator',
|
|
scales=[8],
|
|
ratios=[0.5, 1.0, 2.0],
|
|
strides=[4, 8, 16, 32, 64]),
|
|
bbox_coder=dict(
|
|
type='DeltaXYWHBBoxCoder',
|
|
target_means=[.0, .0, .0, .0],
|
|
target_stds=[1.0, 1.0, 1.0, 1.0]),
|
|
loss_cls=dict(
|
|
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
|
|
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
|
|
roi_head=dict(
|
|
type='CascadeRoIHead',
|
|
num_stages=3,
|
|
stage_loss_weights=[1, 0.5, 0.25],
|
|
bbox_roi_extractor=dict(
|
|
type='SingleRoIExtractor',
|
|
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
|
|
out_channels=256,
|
|
featmap_strides=[4, 8, 16, 32]),
|
|
bbox_head=[
|
|
dict(
|
|
type='Shared2FCBBoxHead',
|
|
in_channels=256,
|
|
fc_out_channels=1024,
|
|
roi_feat_size=7,
|
|
num_classes=1,
|
|
bbox_coder=dict(
|
|
type='DeltaXYWHBBoxCoder',
|
|
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='Shared2FCBBoxHead',
|
|
in_channels=256,
|
|
fc_out_channels=1024,
|
|
roi_feat_size=7,
|
|
num_classes=1,
|
|
bbox_coder=dict(
|
|
type='DeltaXYWHBBoxCoder',
|
|
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='Shared2FCBBoxHead',
|
|
in_channels=256,
|
|
fc_out_channels=1024,
|
|
roi_feat_size=7,
|
|
num_classes=1,
|
|
bbox_coder=dict(
|
|
type='DeltaXYWHBBoxCoder',
|
|
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,
|
|
match_low_quality=True,
|
|
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_pre=2000,
|
|
max_per_img=2000,
|
|
nms=dict(type='nms', iou_threshold=0.7),
|
|
min_bbox_size=0),
|
|
rcnn=[
|
|
dict(
|
|
assigner=dict(
|
|
type='MaxIoUAssigner',
|
|
pos_iou_thr=0.5,
|
|
neg_iou_thr=0.5,
|
|
min_pos_iou=0.5,
|
|
match_low_quality=False,
|
|
ignore_iof_thr=-1),
|
|
sampler=dict(
|
|
type='RandomSampler',
|
|
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,
|
|
match_low_quality=False,
|
|
ignore_iof_thr=-1),
|
|
sampler=dict(
|
|
type='RandomSampler',
|
|
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=0.7,
|
|
neg_iou_thr=0.7,
|
|
min_pos_iou=0.7,
|
|
match_low_quality=False,
|
|
ignore_iof_thr=-1),
|
|
sampler=dict(
|
|
type='RandomSampler',
|
|
num=512,
|
|
pos_fraction=0.25,
|
|
neg_pos_ub=-1,
|
|
add_gt_as_proposals=True),
|
|
pos_weight=-1,
|
|
debug=False)
|
|
]),
|
|
test_cfg=dict(
|
|
rpn=dict(
|
|
nms_pre=1000,
|
|
max_per_img=1000,
|
|
nms=dict(type='nms', iou_threshold=0.7),
|
|
min_bbox_size=0),
|
|
rcnn=dict(
|
|
score_thr=0.05,
|
|
nms=dict(type='nms', iou_threshold=0.5),
|
|
max_per_img=100)))
|
|
|
|
# dataset settings
|
|
dataset_type = 'CocoDataset'
|
|
data_root = 'data/coco/'
|
|
|
|
train_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='LoadAnnotations', with_bbox=True),
|
|
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
|
|
dict(type='RandomFlip', prob=0.5),
|
|
dict(type='PackDetInputs')
|
|
]
|
|
test_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
|
|
# If you don't have a gt annotation, delete the pipeline
|
|
dict(type='LoadAnnotations', with_bbox=True),
|
|
dict(
|
|
type='PackDetInputs',
|
|
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
|
|
'scale_factor'))
|
|
]
|
|
train_dataloader = dict(
|
|
batch_size=2,
|
|
num_workers=2,
|
|
persistent_workers=True,
|
|
sampler=dict(type='DefaultSampler', shuffle=True),
|
|
batch_sampler=dict(type='AspectRatioBatchSampler'),
|
|
dataset=dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
ann_file='annotations/instances_train2017.json',
|
|
data_prefix=dict(img='train2017/'),
|
|
filter_cfg=dict(filter_empty_gt=True, min_size=32),
|
|
pipeline=train_pipeline))
|
|
val_dataloader = dict(
|
|
batch_size=1,
|
|
num_workers=2,
|
|
persistent_workers=True,
|
|
drop_last=False,
|
|
sampler=dict(type='DefaultSampler', shuffle=False),
|
|
dataset=dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
ann_file='annotations/instances_val2017.json',
|
|
data_prefix=dict(img='val2017/'),
|
|
test_mode=True,
|
|
pipeline=test_pipeline))
|
|
test_dataloader = val_dataloader
|
|
|
|
val_evaluator = dict(
|
|
type='CocoMetric',
|
|
ann_file=data_root + 'annotations/instances_val2017.json',
|
|
metric='bbox',
|
|
format_only=False)
|
|
test_evaluator = val_evaluator
|