Skip to content

GitLab

Commit 76168f9c authored by ThangVu's avatar ThangVu
Browse files

resolve conflict GN-dev with master

parents 8a086f02 c5d8f002
Show whitespace changes
Inline Side-by-side
Showing with 1582 additions and 52 deletions
configs/mask_rcnn_r101_fpn_1x.py
View file @ 76168f9c
...@@ -54,34 +54,34 @@ model = dict( ...@@ -54,34 +54,34 @@ model = dict(
train_cfg = dict( train_cfg = dict(
rpn=dict( rpn=dict(
assigner=dict( assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7, pos_iou_thr=0.7,
neg_iou_thr=0.3, neg_iou_thr=0.3,
min_pos_iou=0.3, min_pos_iou=0.3,
ignore_iof_thr=-1), ignore_iof_thr=-1),
sampler=dict( sampler=dict(
type='RandomSampler',
num=256, num=256,
pos_fraction=0.5, pos_fraction=0.5,
neg_pos_ub=-1, neg_pos_ub=-1,
add_gt_as_proposals=False, add_gt_as_proposals=False),
pos_balance_sampling=False,
neg_balance_thr=0),
allowed_border=0, allowed_border=0,
pos_weight=-1, pos_weight=-1,
smoothl1_beta=1 / 9.0, smoothl1_beta=1 / 9.0,
debug=False), debug=False),
rcnn=dict( rcnn=dict(
assigner=dict( assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5, pos_iou_thr=0.5,
neg_iou_thr=0.5, neg_iou_thr=0.5,
min_pos_iou=0.5, min_pos_iou=0.5,
ignore_iof_thr=-1), ignore_iof_thr=-1),
sampler=dict( sampler=dict(
type='RandomSampler',
num=512, num=512,
pos_fraction=0.25, pos_fraction=0.25,
neg_pos_ub=-1, neg_pos_ub=-1,
add_gt_as_proposals=True, add_gt_as_proposals=True),
pos_balance_sampling=False,
neg_balance_thr=0),
mask_size=28, mask_size=28,
pos_weight=-1, pos_weight=-1,
debug=False)) debug=False))
......
configs/mask_rcnn_r50_fpn_1x.py
View file @ 76168f9c
...@@ -54,34 +54,34 @@ model = dict( ...@@ -54,34 +54,34 @@ model = dict(
train_cfg = dict( train_cfg = dict(
rpn=dict( rpn=dict(
assigner=dict( assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7, pos_iou_thr=0.7,
neg_iou_thr=0.3, neg_iou_thr=0.3,
min_pos_iou=0.3, min_pos_iou=0.3,
ignore_iof_thr=-1), ignore_iof_thr=-1),
sampler=dict( sampler=dict(
type='RandomSampler',
num=256, num=256,
pos_fraction=0.5, pos_fraction=0.5,
neg_pos_ub=-1, neg_pos_ub=-1,
add_gt_as_proposals=False, add_gt_as_proposals=False),
pos_balance_sampling=False,
neg_balance_thr=0),
allowed_border=0, allowed_border=0,
pos_weight=-1, pos_weight=-1,
smoothl1_beta=1 / 9.0, smoothl1_beta=1 / 9.0,
debug=False), debug=False),
rcnn=dict( rcnn=dict(
assigner=dict( assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5, pos_iou_thr=0.5,
neg_iou_thr=0.5, neg_iou_thr=0.5,
min_pos_iou=0.5, min_pos_iou=0.5,
ignore_iof_thr=-1), ignore_iof_thr=-1),
sampler=dict( sampler=dict(
type='RandomSampler',
num=512, num=512,
pos_fraction=0.25, pos_fraction=0.25,
neg_pos_ub=-1, neg_pos_ub=-1,
add_gt_as_proposals=True, add_gt_as_proposals=True),
pos_balance_sampling=False,
neg_balance_thr=0),
mask_size=28, mask_size=28,
pos_weight=-1, pos_weight=-1,
debug=False)) debug=False))
......
configs/mask_rcnn_x101_32x4d_fpn_1x.py 0 → 100644
View file @ 76168f9c
# model settings
model = dict(
type='MaskRCNN',
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'),
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=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
use_sigmoid_cls=True),
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=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81))
# 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,
smoothl1_beta=1 / 9.0,
debug=False),
rcnn=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='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
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=100,
mask_thr_binary=0.5))
# 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)
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/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=True,
with_crowd=True,
with_label=True),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=True,
with_crowd=True,
with_label=True),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer
optimizer = dict(type='SGD', lr=0.02, 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
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/mask_rcnn_x101_64x4d_fpn_1x.py 0 → 100644
View file @ 76168f9c
# model settings
model = dict(
type='MaskRCNN',
pretrained='open-mmlab://resnext101_64x4d',
backbone=dict(
type='ResNeXt',
depth=101,
groups=64,
base_width=4,
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,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
use_sigmoid_cls=True),
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=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=81))
# 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,
smoothl1_beta=1 / 9.0,
debug=False),
rcnn=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='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
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=100,
mask_thr_binary=0.5))
# 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)
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/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=True,
with_crowd=True,
with_label=True),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=True,
with_crowd=True,
with_label=True),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer
optimizer = dict(type='SGD', lr=0.02, 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
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/pascal_voc/faster_rcnn_r50_fpn_1x_voc0712.py 0 → 100644
View file @ 76168f9c
# model settings
model = dict(
type='FasterRCNN',
pretrained='modelzoo://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,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
use_sigmoid_cls=True),
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=21,
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
reg_class_agnostic=False))
# 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,
smoothl1_beta=1 / 9.0,
debug=False),
rcnn=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='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_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
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=100)
# soft-nms is also supported for rcnn testing
# e.g., nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.05)
)
# dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
data = dict(
imgs_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='RepeatDataset', # to avoid reloading datasets frequently
times=3,
dataset=dict(
type=dataset_type,
ann_file=[
data_root + 'VOC2007/ImageSets/Main/trainval.txt',
data_root + 'VOC2012/ImageSets/Main/trainval.txt'
],
img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
img_scale=(1000, 600),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=True,
with_label=True)),
val=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
img_scale=(1000, 600),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=True,
with_label=True),
test=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
img_scale=(1000, 600),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# 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', step=[3]) # actual epoch = 3 * 3 = 9
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 = 4 # actual epoch = 4 * 3 = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/faster_rcnn_r50_fpn_1x_voc0712'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/pascal_voc/ssd300_voc.py 0 → 100644
View file @ 76168f9c
# model settings
input_size = 300
model = dict(
type='SingleStageDetector',
pretrained='open-mmlab://vgg16_caffe',
backbone=dict(
type='SSDVGG',
input_size=input_size,
depth=16,
with_last_pool=False,
ceil_mode=True,
out_indices=(3, 4),
out_feature_indices=(22, 34),
l2_norm_scale=20),
neck=None,
bbox_head=dict(
type='SSDHead',
input_size=input_size,
in_channels=(512, 1024, 512, 256, 256, 256),
num_classes=21,
anchor_strides=(8, 16, 32, 64, 100, 300),
basesize_ratio_range=(0.2, 0.9),
anchor_ratios=([2], [2, 3], [2, 3], [2, 3], [2], [2]),
target_means=(.0, .0, .0, .0),
target_stds=(0.1, 0.1, 0.2, 0.2)))
cudnn_benchmark = True
train_cfg = dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.,
ignore_iof_thr=-1,
gt_max_assign_all=False),
smoothl1_beta=1.,
allowed_border=-1,
pos_weight=-1,
neg_pos_ratio=3,
debug=False)
test_cfg = dict(
nms=dict(type='nms', iou_thr=0.45),
min_bbox_size=0,
score_thr=0.02,
max_per_img=200)
# model training and testing settings
# dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
data = dict(
imgs_per_gpu=4,
workers_per_gpu=2,
train=dict(
type='RepeatDataset',
times=10,
dataset=dict(
type=dataset_type,
ann_file=[
data_root + 'VOC2007/ImageSets/Main/trainval.txt',
data_root + 'VOC2012/ImageSets/Main/trainval.txt'
],
img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
img_scale=(300, 300),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0.5,
with_mask=False,
with_crowd=False,
with_label=True,
test_mode=False,
extra_aug=dict(
photo_metric_distortion=dict(
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
expand=dict(
mean=img_norm_cfg['mean'],
to_rgb=img_norm_cfg['to_rgb'],
ratio_range=(1, 4)),
random_crop=dict(
min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
resize_keep_ratio=False)),
val=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
img_scale=(300, 300),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True,
resize_keep_ratio=False),
test=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
img_scale=(300, 300),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True,
resize_keep_ratio=False))
# optimizer
optimizer = dict(type='SGD', lr=1e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[16, 20])
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
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/ssd300_voc'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/pascal_voc/ssd512_voc.py 0 → 100644
View file @ 76168f9c
# model settings
input_size = 512
model = dict(
type='SingleStageDetector',
pretrained='open-mmlab://vgg16_caffe',
backbone=dict(
type='SSDVGG',
input_size=input_size,
depth=16,
with_last_pool=False,
ceil_mode=True,
out_indices=(3, 4),
out_feature_indices=(22, 34),
l2_norm_scale=20),
neck=None,
bbox_head=dict(
type='SSDHead',
input_size=input_size,
in_channels=(512, 1024, 512, 256, 256, 256, 256),
num_classes=21,
anchor_strides=(8, 16, 32, 64, 128, 256, 512),
basesize_ratio_range=(0.15, 0.9),
anchor_ratios=([2], [2, 3], [2, 3], [2, 3], [2, 3], [2], [2]),
target_means=(.0, .0, .0, .0),
target_stds=(0.1, 0.1, 0.2, 0.2)))
cudnn_benchmark = True
train_cfg = dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.,
ignore_iof_thr=-1,
gt_max_assign_all=False),
smoothl1_beta=1.,
allowed_border=-1,
pos_weight=-1,
neg_pos_ratio=3,
debug=False)
test_cfg = dict(
nms=dict(type='nms', iou_thr=0.45),
min_bbox_size=0,
score_thr=0.02,
max_per_img=200)
# model training and testing settings
# dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
data = dict(
imgs_per_gpu=4,
workers_per_gpu=2,
train=dict(
type='RepeatDataset',
times=10,
dataset=dict(
type=dataset_type,
ann_file=[
data_root + 'VOC2007/ImageSets/Main/trainval.txt',
data_root + 'VOC2012/ImageSets/Main/trainval.txt'
],
img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
img_scale=(512, 512),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0.5,
with_mask=False,
with_crowd=False,
with_label=True,
test_mode=False,
extra_aug=dict(
photo_metric_distortion=dict(
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
expand=dict(
mean=img_norm_cfg['mean'],
to_rgb=img_norm_cfg['to_rgb'],
ratio_range=(1, 4)),
random_crop=dict(
min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
resize_keep_ratio=False)),
val=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
img_scale=(512, 512),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True,
resize_keep_ratio=False),
test=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
img_prefix=data_root + 'VOC2007/',
img_scale=(512, 512),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True,
resize_keep_ratio=False))
# optimizer
optimizer = dict(type='SGD', lr=1e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[16, 20])
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
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/ssd512_voc'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/retinanet_r101_fpn_1x.py
View file @ 76168f9c
...@@ -31,7 +31,11 @@ model = dict( ...@@ -31,7 +31,11 @@ model = dict(
# training and testing settings # training and testing settings
train_cfg = dict( train_cfg = dict(
assigner=dict( assigner=dict(
pos_iou_thr=0.5, neg_iou_thr=0.4, min_pos_iou=0, ignore_iof_thr=-1), type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
smoothl1_beta=0.11, smoothl1_beta=0.11,
gamma=2.0, gamma=2.0,
alpha=0.25, alpha=0.25,
......
configs/retinanet_r50_fpn_1x.py
View file @ 76168f9c
...@@ -31,7 +31,11 @@ model = dict( ...@@ -31,7 +31,11 @@ model = dict(
# training and testing settings # training and testing settings
train_cfg = dict( train_cfg = dict(
assigner=dict( assigner=dict(
pos_iou_thr=0.5, neg_iou_thr=0.4, min_pos_iou=0, ignore_iof_thr=-1), type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
smoothl1_beta=0.11, smoothl1_beta=0.11,
gamma=2.0, gamma=2.0,
alpha=0.25, alpha=0.25,
......
configs/retinanet_x101_32x4d_fpn_1x.py 0 → 100644
View file @ 76168f9c
# model settings
model = dict(
type='RetinaNet',
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'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs=True,
num_outs=5),
bbox_head=dict(
type='RetinaHead',
num_classes=81,
in_channels=256,
stacked_convs=4,
feat_channels=256,
octave_base_scale=4,
scales_per_octave=3,
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[8, 16, 32, 64, 128],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]))
# training and testing settings
train_cfg = dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
smoothl1_beta=0.11,
gamma=2.0,
alpha=0.25,
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)
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/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=False,
with_label=True),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=False,
with_label=True),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=False,
with_label=False,
test_mode=True))
# 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/retinanet_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/retinanet_x101_64x4d_fpn_1x.py 0 → 100644
View file @ 76168f9c
# model settings
model = dict(
type='RetinaNet',
pretrained='open-mmlab://resnext101_64x4d',
backbone=dict(
type='ResNeXt',
depth=101,
groups=64,
base_width=4,
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),
bbox_head=dict(
type='RetinaHead',
num_classes=81,
in_channels=256,
stacked_convs=4,
feat_channels=256,
octave_base_scale=4,
scales_per_octave=3,
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[8, 16, 32, 64, 128],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]))
# training and testing settings
train_cfg = dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
smoothl1_beta=0.11,
gamma=2.0,
alpha=0.25,
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)
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/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=False,
with_label=True),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=False,
with_label=True),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=False,
with_label=False,
test_mode=True))
# 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/retinanet_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/rpn_r101_fpn_1x.py
View file @ 76168f9c
...@@ -28,17 +28,17 @@ model = dict( ...@@ -28,17 +28,17 @@ model = dict(
train_cfg = dict( train_cfg = dict(
rpn=dict( rpn=dict(
assigner=dict( assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7, pos_iou_thr=0.7,
neg_iou_thr=0.3, neg_iou_thr=0.3,
min_pos_iou=0.3, min_pos_iou=0.3,
ignore_iof_thr=-1), ignore_iof_thr=-1),
sampler=dict( sampler=dict(
type='RandomSampler',
num=256, num=256,
pos_fraction=0.5, pos_fraction=0.5,
neg_pos_ub=-1, neg_pos_ub=-1,
add_gt_as_proposals=False, add_gt_as_proposals=False),
pos_balance_sampling=False,
neg_balance_thr=0),
allowed_border=0, allowed_border=0,
pos_weight=-1, pos_weight=-1,
smoothl1_beta=1 / 9.0, smoothl1_beta=1 / 9.0,
......
configs/rpn_r50_fpn_1x.py
View file @ 76168f9c
...@@ -28,17 +28,17 @@ model = dict( ...@@ -28,17 +28,17 @@ model = dict(
train_cfg = dict( train_cfg = dict(
rpn=dict( rpn=dict(
assigner=dict( assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7, pos_iou_thr=0.7,
neg_iou_thr=0.3, neg_iou_thr=0.3,
min_pos_iou=0.3, min_pos_iou=0.3,
ignore_iof_thr=-1), ignore_iof_thr=-1),
sampler=dict( sampler=dict(
type='RandomSampler',
num=256, num=256,
pos_fraction=0.5, pos_fraction=0.5,
neg_pos_ub=-1, neg_pos_ub=-1,
add_gt_as_proposals=False, add_gt_as_proposals=False),
pos_balance_sampling=False,
neg_balance_thr=0),
allowed_border=0, allowed_border=0,
pos_weight=-1, pos_weight=-1,
smoothl1_beta=1 / 9.0, smoothl1_beta=1 / 9.0,
......
configs/rpn_x101_32x4d_fpn_1x.py 0 → 100644
View file @ 76168f9c
# model settings
model = dict(
type='RPN',
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'),
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=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
use_sigmoid_cls=True))
# 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,
smoothl1_beta=1 / 9.0,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0))
# 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)
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/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=False,
with_label=False),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=False,
with_label=False),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
# runner configs
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
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
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/rpn_r101_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/rpn_x101_64x4d_fpn_1x.py 0 → 100644
View file @ 76168f9c
# model settings
model = dict(
type='RPN',
pretrained='open-mmlab://resnext101_64x4d',
backbone=dict(
type='ResNeXt',
depth=101,
groups=64,
base_width=4,
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,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
use_sigmoid_cls=True))
# 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,
smoothl1_beta=1 / 9.0,
debug=False))
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=2000,
max_num=2000,
nms_thr=0.7,
min_bbox_size=0))
# 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)
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/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0.5,
with_mask=False,
with_crowd=False,
with_label=False),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_crowd=False,
with_label=False),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(1333, 800),
img_norm_cfg=img_norm_cfg,
size_divisor=32,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
# runner configs
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
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
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/rpn_r101_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/ssd300_coco.py 0 → 100644
View file @ 76168f9c
# model settings
input_size = 300
model = dict(
type='SingleStageDetector',
pretrained='open-mmlab://vgg16_caffe',
backbone=dict(
type='SSDVGG',
input_size=input_size,
depth=16,
with_last_pool=False,
ceil_mode=True,
out_indices=(3, 4),
out_feature_indices=(22, 34),
l2_norm_scale=20),
neck=None,
bbox_head=dict(
type='SSDHead',
input_size=input_size,
in_channels=(512, 1024, 512, 256, 256, 256),
num_classes=81,
anchor_strides=(8, 16, 32, 64, 100, 300),
basesize_ratio_range=(0.15, 0.9),
anchor_ratios=([2], [2, 3], [2, 3], [2, 3], [2], [2]),
target_means=(.0, .0, .0, .0),
target_stds=(0.1, 0.1, 0.2, 0.2)))
cudnn_benchmark = True
train_cfg = dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.,
ignore_iof_thr=-1,
gt_max_assign_all=False),
smoothl1_beta=1.,
allowed_border=-1,
pos_weight=-1,
neg_pos_ratio=3,
debug=False)
test_cfg = dict(
nms=dict(type='nms', iou_thr=0.45),
min_bbox_size=0,
score_thr=0.02,
max_per_img=200)
# model training and testing settings
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
data = dict(
imgs_per_gpu=8,
workers_per_gpu=3,
train=dict(
type='RepeatDataset',
times=5,
dataset=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
img_scale=(300, 300),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0.5,
with_mask=False,
with_crowd=False,
with_label=True,
test_mode=False,
extra_aug=dict(
photo_metric_distortion=dict(
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
expand=dict(
mean=img_norm_cfg['mean'],
to_rgb=img_norm_cfg['to_rgb'],
ratio_range=(1, 4)),
random_crop=dict(
min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
resize_keep_ratio=False)),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(300, 300),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True,
resize_keep_ratio=False),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(300, 300),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True,
resize_keep_ratio=False))
# optimizer
optimizer = dict(type='SGD', lr=2e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
# 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
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/ssd300_coco'
load_from = None
resume_from = None
workflow = [('train', 1)]
configs/ssd512_coco.py 0 → 100644
View file @ 76168f9c
# model settings
input_size = 512
model = dict(
type='SingleStageDetector',
pretrained='open-mmlab://vgg16_caffe',
backbone=dict(
type='SSDVGG',
input_size=input_size,
depth=16,
with_last_pool=False,
ceil_mode=True,
out_indices=(3, 4),
out_feature_indices=(22, 34),
l2_norm_scale=20),
neck=None,
bbox_head=dict(
type='SSDHead',
input_size=input_size,
in_channels=(512, 1024, 512, 256, 256, 256, 256),
num_classes=81,
anchor_strides=(8, 16, 32, 64, 128, 256, 512),
basesize_ratio_range=(0.1, 0.9),
anchor_ratios=([2], [2, 3], [2, 3], [2, 3], [2, 3], [2], [2]),
target_means=(.0, .0, .0, .0),
target_stds=(0.1, 0.1, 0.2, 0.2)))
cudnn_benchmark = True
train_cfg = dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.,
ignore_iof_thr=-1,
gt_max_assign_all=False),
smoothl1_beta=1.,
allowed_border=-1,
pos_weight=-1,
neg_pos_ratio=3,
debug=False)
test_cfg = dict(
nms=dict(type='nms', iou_thr=0.45),
min_bbox_size=0,
score_thr=0.02,
max_per_img=200)
# model training and testing settings
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
data = dict(
imgs_per_gpu=8,
workers_per_gpu=3,
train=dict(
type='RepeatDataset',
times=5,
dataset=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
img_scale=(512, 512),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0.5,
with_mask=False,
with_crowd=False,
with_label=True,
test_mode=False,
extra_aug=dict(
photo_metric_distortion=dict(
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
expand=dict(
mean=img_norm_cfg['mean'],
to_rgb=img_norm_cfg['to_rgb'],
ratio_range=(1, 4)),
random_crop=dict(
min_ious=(0.1, 0.3, 0.5, 0.7, 0.9), min_crop_size=0.3)),
resize_keep_ratio=False)),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(512, 512),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True,
resize_keep_ratio=False),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
img_scale=(512, 512),
img_norm_cfg=img_norm_cfg,
size_divisor=None,
flip_ratio=0,
with_mask=False,
with_label=False,
test_mode=True,
resize_keep_ratio=False))
# optimizer
optimizer = dict(type='SGD', lr=2e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict()
# 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
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/ssd512_coco'
load_from = None
resume_from = None
workflow = [('train', 1)]
mmdet/apis/train.py
View file @ 76168f9c
...@@ -6,8 +6,8 @@ import torch ...@@ -6,8 +6,8 @@ import torch
from mmcv.runner import Runner, DistSamplerSeedHook from mmcv.runner import Runner, DistSamplerSeedHook
from mmcv.parallel import MMDataParallel, MMDistributedDataParallel from mmcv.parallel import MMDataParallel, MMDistributedDataParallel
from mmdet.core import (DistOptimizerHook, CocoDistEvalRecallHook, from mmdet.core import (DistOptimizerHook, DistEvalmAPHook,
CocoDistEvalmAPHook) CocoDistEvalRecallHook, CocoDistEvalmAPHook)
from mmdet.datasets import build_dataloader from mmdet.datasets import build_dataloader
from mmdet.models import RPN from mmdet.models import RPN
from .env import get_root_logger from .env import get_root_logger
...@@ -81,9 +81,13 @@ def _dist_train(model, dataset, cfg, validate=False): ...@@ -81,9 +81,13 @@ def _dist_train(model, dataset, cfg, validate=False):
# register eval hooks # register eval hooks
if validate: if validate:
if isinstance(model.module, RPN): if isinstance(model.module, RPN):
# TODO: implement recall hooks for other datasets
runner.register_hook(CocoDistEvalRecallHook(cfg.data.val)) runner.register_hook(CocoDistEvalRecallHook(cfg.data.val))
elif cfg.data.val.type == 'CocoDataset': else:
if cfg.data.val.type == 'CocoDataset':
runner.register_hook(CocoDistEvalmAPHook(cfg.data.val)) runner.register_hook(CocoDistEvalmAPHook(cfg.data.val))
else:
runner.register_hook(DistEvalmAPHook(cfg.data.val))
if cfg.resume_from: if cfg.resume_from:
runner.resume(cfg.resume_from) runner.resume(cfg.resume_from)
......
mmdet/core/anchor/anchor_generator.py
View file @ 76168f9c
...@@ -3,11 +3,12 @@ import torch ...@@ -3,11 +3,12 @@ import torch
class AnchorGenerator(object): class AnchorGenerator(object):
def __init__(self, base_size, scales, ratios, scale_major=True): def __init__(self, base_size, scales, ratios, scale_major=True, ctr=None):
self.base_size = base_size self.base_size = base_size
self.scales = torch.Tensor(scales) self.scales = torch.Tensor(scales)
self.ratios = torch.Tensor(ratios) self.ratios = torch.Tensor(ratios)
self.scale_major = scale_major self.scale_major = scale_major
self.ctr = ctr
self.base_anchors = self.gen_base_anchors() self.base_anchors = self.gen_base_anchors()
@property @property
...@@ -15,13 +16,13 @@ class AnchorGenerator(object): ...@@ -15,13 +16,13 @@ class AnchorGenerator(object):
return self.base_anchors.size(0) return self.base_anchors.size(0)
def gen_base_anchors(self): def gen_base_anchors(self):
base_anchor = torch.Tensor( w = self.base_size
[0, 0, self.base_size - 1, self.base_size - 1]) h = self.base_size
if self.ctr is None:
w = base_anchor[2] - base_anchor[0] + 1 x_ctr = 0.5 * (w - 1)
h = base_anchor[3] - base_anchor[1] + 1 y_ctr = 0.5 * (h - 1)
x_ctr = base_anchor[0] + 0.5 * (w - 1) else:
y_ctr = base_anchor[1] + 0.5 * (h - 1) x_ctr, y_ctr = self.ctr
h_ratios = torch.sqrt(self.ratios) h_ratios = torch.sqrt(self.ratios)
w_ratios = 1 / h_ratios w_ratios = 1 / h_ratios
......
mmdet/core/anchor/anchor_target.py
View file @ 76168f9c
import torch import torch
from ..bbox import assign_and_sample, BBoxAssigner, SamplingResult, bbox2delta from ..bbox import assign_and_sample, build_assigner, PseudoSampler, bbox2delta
from ..utils import multi_apply from ..utils import multi_apply
...@@ -13,7 +13,8 @@ def anchor_target(anchor_list, ...@@ -13,7 +13,8 @@ def anchor_target(anchor_list,
cfg, cfg,
gt_labels_list=None, gt_labels_list=None,
cls_out_channels=1, cls_out_channels=1,
sampling=True): sampling=True,
unmap_outputs=True):
"""Compute regression and classification targets for anchors. """Compute regression and classification targets for anchors.
Args: Args:
...@@ -54,7 +55,8 @@ def anchor_target(anchor_list, ...@@ -54,7 +55,8 @@ def anchor_target(anchor_list,
target_stds=target_stds, target_stds=target_stds,
cfg=cfg, cfg=cfg,
cls_out_channels=cls_out_channels, cls_out_channels=cls_out_channels,
sampling=sampling) sampling=sampling,
unmap_outputs=unmap_outputs)
# no valid anchors # no valid anchors
if any([labels is None for labels in all_labels]): if any([labels is None for labels in all_labels]):
return None return None
...@@ -94,7 +96,8 @@ def anchor_target_single(flat_anchors, ...@@ -94,7 +96,8 @@ def anchor_target_single(flat_anchors,
target_stds, target_stds,
cfg, cfg,
cls_out_channels=1, cls_out_channels=1,
sampling=True): sampling=True,
unmap_outputs=True):
inside_flags = anchor_inside_flags(flat_anchors, valid_flags, inside_flags = anchor_inside_flags(flat_anchors, valid_flags,
img_meta['img_shape'][:2], img_meta['img_shape'][:2],
cfg.allowed_border) cfg.allowed_border)
...@@ -107,16 +110,12 @@ def anchor_target_single(flat_anchors, ...@@ -107,16 +110,12 @@ def anchor_target_single(flat_anchors,
assign_result, sampling_result = assign_and_sample( assign_result, sampling_result = assign_and_sample(
anchors, gt_bboxes, None, None, cfg) anchors, gt_bboxes, None, None, cfg)
else: else:
bbox_assigner = BBoxAssigner(**cfg.assigner) bbox_assigner = build_assigner(cfg.assigner)
assign_result = bbox_assigner.assign(anchors, gt_bboxes, None, assign_result = bbox_assigner.assign(anchors, gt_bboxes, None,
gt_labels) gt_labels)
pos_inds = torch.nonzero( bbox_sampler = PseudoSampler()
assign_result.gt_inds > 0).squeeze(-1).unique() sampling_result = bbox_sampler.sample(assign_result, anchors,
neg_inds = torch.nonzero( gt_bboxes)
assign_result.gt_inds == 0).squeeze(-1).unique()
gt_flags = anchors.new_zeros(anchors.shape[0], dtype=torch.uint8)
sampling_result = SamplingResult(pos_inds, neg_inds, anchors,
gt_bboxes, assign_result, gt_flags)
num_valid_anchors = anchors.shape[0] num_valid_anchors = anchors.shape[0]
bbox_targets = torch.zeros_like(anchors) bbox_targets = torch.zeros_like(anchors)
...@@ -144,6 +143,7 @@ def anchor_target_single(flat_anchors, ...@@ -144,6 +143,7 @@ def anchor_target_single(flat_anchors,
label_weights[neg_inds] = 1.0 label_weights[neg_inds] = 1.0
# map up to original set of anchors # map up to original set of anchors
if unmap_outputs:
num_total_anchors = flat_anchors.size(0) num_total_anchors = flat_anchors.size(0)
labels = unmap(labels, num_total_anchors, inside_flags) labels = unmap(labels, num_total_anchors, inside_flags)
label_weights = unmap(label_weights, num_total_anchors, inside_flags) label_weights = unmap(label_weights, num_total_anchors, inside_flags)
......
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