Skip to content

GitLab

Commit 8885a81b authored by v-zeya's avatar v-zeya
Browse files

add reppoints head, reppoints detector and the config files.

parent c0a4c007
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 2574 additions and 2 deletions
configs/reppoints/bbox_r50_grid_center_fpn_1x.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='minmax',
use_grid_points=True))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(type='PointAssigner', scale=4, pos_num=1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=(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']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/bbox_r50_grid_center_fpn_1x'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
configs/reppoints/bbox_r50_grid_fpn_1x.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='minmax',
use_grid_points=True))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=(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']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/bbox_r50_grid_fpn_1x'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
configs/reppoints/reppoints_minmax_r50_fpn_1x.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='minmax'))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(type='PointAssigner', scale=4, pos_num=1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=(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']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/reppoints_minmax_r50_fpn_1x'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
configs/reppoints/reppoints_moment_r101_dcn_fpn_2x.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='torchvision://resnet101',
backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
dcn=dict(
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,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='moment'))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(type='PointAssigner', scale=4, pos_num=1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=(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']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/reppoints_moment_r101_dcn_fpn_2x'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
configs/reppoints/reppoints_moment_r101_dcn_fpn_2x_mt.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='torchvision://resnet101',
backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
dcn=dict(
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,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='moment'))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(type='PointAssigner', scale=4, pos_num=1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=[(1333, 480), (1333, 960)],
keep_ratio=True,
multiscale_mode='range'),
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=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/reppoints_moment_r101_dcn_fpn_2x_mt'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
configs/reppoints/reppoints_moment_r101_fpn_2x.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='torchvision://resnet101',
backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='moment'))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(type='PointAssigner', scale=4, pos_num=1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=(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']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/reppoints_moment_r101_fpn_2x'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
configs/reppoints/reppoints_moment_r101_fpn_2x_mt.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='torchvision://resnet101',
backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='moment'))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(type='PointAssigner', scale=4, pos_num=1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=[(1333, 480), (1333, 960)],
keep_ratio=True,
multiscale_mode='range'),
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=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/reppoints_moment_r101_fpn_2x_mt'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
configs/reppoints/reppoints_moment_r50_fpn_1x.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='moment'))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(type='PointAssigner', scale=4, pos_num=1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=(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']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/reppoints_moment_r50_fpn_1x'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
configs/reppoints/reppoints_moment_r50_fpn_2x.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='moment'))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(type='PointAssigner', scale=4, pos_num=1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=(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']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/reppoints_moment_r50_fpn_2x'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
configs/reppoints/reppoints_moment_r50_fpn_2x_mt.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='moment'))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(type='PointAssigner', scale=4, pos_num=1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=[(1333, 480), (1333, 960)],
keep_ratio=True,
multiscale_mode='range'),
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=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/reppoints_moment_r50_fpn_2x_mt'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
configs/reppoints/reppoints_moment_x101_dcn_fpn_2x.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='open-mmlab://resnext101_32x4d',
backbone=dict(
type='ResNeXt',
depth=101,
groups=32,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
dcn=dict(
modulated=False,
groups=32,
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,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='moment'))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(type='PointAssigner', scale=4, pos_num=1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=(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']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/reppoints_moment_x101_dcn_fpn_2x'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
configs/reppoints/reppoints_moment_x101_dcn_fpn_2x_mt.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='open-mmlab://resnext101_32x4d',
backbone=dict(
type='ResNeXt',
depth=101,
groups=32,
base_width=4,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch',
dcn=dict(
modulated=False,
groups=32,
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,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='moment'))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(type='PointAssigner', scale=4, pos_num=1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=[(1333, 480), (1333, 960)],
keep_ratio=True,
multiscale_mode='range'),
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=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[16, 22])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 24
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/reppoints_moment_x101_dcn_fpn_2x_mt'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
configs/reppoints/reppoints_partial_minmax_r50_fpn_1x.py 0 → 100644
View file @ 8885a81b
# model settings
norm_cfg = dict(type='GN', num_groups=32, requires_grad=True)
model = dict(
type='RepPointsDetector',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
num_outs=5,
norm_cfg=norm_cfg),
bbox_head=dict(
type='RepPointsHead',
num_classes=81,
in_channels=256,
feat_channels=256,
point_feat_channels=256,
stacked_convs=3,
num_points=9,
gradient_mul=0.1,
point_strides=[8, 16, 32, 64, 128],
point_base_scale=4,
norm_cfg=norm_cfg,
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox_init=dict(type='SmoothL1Loss', beta=0.11, loss_weight=0.5),
loss_bbox_refine=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0),
transform_method='partial_minmax'))
# training and testing settings
train_cfg = dict(
init=dict(
assigner=dict(type='PointAssigner', scale=4, pos_num=1),
allowed_border=-1,
pos_weight=-1,
debug=False),
refine=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
allowed_border=-1,
pos_weight=-1,
debug=False))
test_cfg = dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_thr=0.5),
max_per_img=100)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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=(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']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
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=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
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=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 12
device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/reppoints_partial_minmax_r50_fpn_1x'
load_from = None
resume_from = None
auto_resume = True
workflow = [('train', 1)]
mmdet/models/anchor_heads/__init__.py
View file @ 8885a81b
......@@ -3,11 +3,13 @@ from .fcos_head import FCOSHead
from .ga_retina_head import GARetinaHead
from .ga_rpn_head import GARPNHead
from .guided_anchor_head import FeatureAdaption, GuidedAnchorHead
from .reppoints_head import RepPointsHead
from .retina_head import RetinaHead
from .rpn_head import RPNHead
from .ssd_head import SSDHead
__all__ = [
'AnchorHead', 'GuidedAnchorHead', 'FeatureAdaption', 'RPNHead',
'GARPNHead', 'RetinaHead', 'GARetinaHead', 'SSDHead', 'FCOSHead'
'GARPNHead', 'RetinaHead', 'GARetinaHead', 'SSDHead', 'FCOSHead',
'RepPointsHead'
]
mmdet/models/anchor_heads/reppoints_head.py 0 → 100644
View file @ 8885a81b
This diff is collapsed.
mmdet/models/detectors/__init__.py
View file @ 8885a81b
......@@ -8,6 +8,7 @@ from .grid_rcnn import GridRCNN
from .htc import HybridTaskCascade
from .mask_rcnn import MaskRCNN
from .mask_scoring_rcnn import MaskScoringRCNN
from .reppoints_detector import RepPointsDetector
from .retinanet import RetinaNet
from .rpn import RPN
from .single_stage import SingleStageDetector
......@@ -16,5 +17,6 @@ from .two_stage import TwoStageDetector
__all__ = [
'BaseDetector', 'SingleStageDetector', 'TwoStageDetector', 'RPN',
'FastRCNN', 'FasterRCNN', 'MaskRCNN', 'CascadeRCNN', 'HybridTaskCascade',
'DoubleHeadRCNN', 'RetinaNet', 'FCOS', 'GridRCNN', 'MaskScoringRCNN'
'DoubleHeadRCNN', 'RetinaNet', 'FCOS', 'GridRCNN', 'MaskScoringRCNN',
'RepPointsDetector'
]
mmdet/models/detectors/reppoints_detector.py 0 → 100644
View file @ 8885a81b
import torch
from mmdet.core import bbox2result, bbox_mapping_back, multiclass_nms
from ..registry import DETECTORS
from .single_stage import SingleStageDetector
@DETECTORS.register_module
class RepPointsDetector(SingleStageDetector):
"""RepPoints: Point Set Representation for Object Detection.
This detector is the implementation of:
- RepPoints detector (https://arxiv.org/pdf/1904.11490)
"""
def __init__(self,
backbone,
neck,
bbox_head,
train_cfg=None,
test_cfg=None,
pretrained=None):
super(RepPointsDetector,
self).__init__(backbone, neck, bbox_head, train_cfg, test_cfg,
pretrained)
def merge_aug_results(self, aug_bboxes, aug_scores, img_metas):
"""Merge augmented detection bboxes and scores.
Args:
aug_bboxes (list[Tensor]): shape (n, 4*#class)
aug_scores (list[Tensor] or None): shape (n, #class)
img_shapes (list[Tensor]): shape (3, ).
Returns:
tuple: (bboxes, scores)
"""
recovered_bboxes = []
for bboxes, img_info in zip(aug_bboxes, img_metas):
img_shape = img_info[0]['img_shape']
scale_factor = img_info[0]['scale_factor']
flip = img_info[0]['flip']
bboxes = bbox_mapping_back(bboxes, img_shape, scale_factor, flip)
recovered_bboxes.append(bboxes)
bboxes = torch.cat(recovered_bboxes, dim=0)
if aug_scores is None:
return bboxes
else:
scores = torch.cat(aug_scores, dim=0)
return bboxes, scores
def aug_test(self, imgs, img_metas, rescale=False):
# recompute feats to save memory
feats = self.extract_feats(imgs)
aug_bboxes = []
aug_scores = []
for x, img_meta in zip(feats, img_metas):
# only one image in the batch
outs = self.bbox_head(x)
bbox_inputs = outs + (img_meta, self.test_cfg, False, False)
det_bboxes, det_scores = self.bbox_head.get_bboxes(*bbox_inputs)[0]
aug_bboxes.append(det_bboxes)
aug_scores.append(det_scores)
# after merging, bboxes will be rescaled to the original image size
merged_bboxes, merged_scores = self.merge_aug_results(
aug_bboxes, aug_scores, img_metas)
det_bboxes, det_labels = multiclass_nms(merged_bboxes, merged_scores,
self.test_cfg.score_thr,
self.test_cfg.nms,
self.test_cfg.max_per_img)
if rescale:
_det_bboxes = det_bboxes
else:
_det_bboxes = det_bboxes.clone()
_det_bboxes[:, :4] *= img_metas[0][0]['scale_factor']
bbox_results = bbox2result(_det_bboxes, det_labels,
self.bbox_head.num_classes)
return bbox_results
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment