I have already tried tiny and small version, none of them can run.
When train without pretrained weight, it is works fine, but time is a problem.
The following is the configs :
model = dict(
type='MaskRCNN',
pretrained='mask_rcnn_swin_tiny_patch4_window7.pth',
backbone=dict(
type='SwinTransformer',
embed_dim=96,
depths=[2, 2, 6, 2],
num_heads=[3, 6, 12, 24],
window_size=7,
mlp_ratio=4.0,
qkv_bias=True,
qk_scale=None,
drop_rate=0.0,
attn_drop_rate=0.0,
drop_path_rate=0.2,
ape=False,
patch_norm=True,
out_indices=(0, 1, 2, 3),
use_checkpoint=False),
neck=dict(
type='FPN',
in_channels=[96, 192, 384, 768],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 0.0, 0.0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=43,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 0.0, 0.0],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
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=43,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=True,
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_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
customed = [
'speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
'speedlimit-70', 'speedlimit-80', 'restrict-end-80', 'speedlimit-100',
'speedlimit-120', 'no-overtake', 'no-overtake-truck',
'priority-next-intersect', 'priority-road', 'giveaway', 'stop',
'no-traffic-bothways', 'no-truck', 'no-entry', 'danger', 'bend-left',
'bend-right', 'bend', 'uneven-road', 'slippery-road', 'road-narrow',
'construction', 'traffic-signal', 'pedestrian-crossing', 'school-crossing',
'cycle-crossing', 'snow', 'animals', 'restriction-ends', 'go-right',
'go-left', 'go-straight', 'go-right-straight', 'go-left-straight',
'keep-right', 'keep-left', 'roundabout', 'restrict-ends-overtaking',
'restrict-ends-overtaking-truck'
]
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, with_mask=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='AutoAugment',
policies=[[{
'type':
'Resize',
'img_scale': [(480, 1333), (512, 1333), (544, 1333), (576, 1333),
(608, 1333), (640, 1333), (672, 1333), (704, 1333),
(736, 1333), (768, 1333), (800, 1333)],
'multiscale_mode':
'value',
'keep_ratio':
True
}],
[{
'type': 'Resize',
'img_scale': [(400, 1333), (500, 1333), (600, 1333)],
'multiscale_mode': 'value',
'keep_ratio': True
}, {
'type': 'RandomCrop',
'crop_type': 'absolute_range',
'crop_size': (384, 600),
'allow_negative_crop': True
}, {
'type':
'Resize',
'img_scale': [(480, 1333), (512, 1333), (544, 1333),
(576, 1333), (608, 1333), (640, 1333),
(672, 1333), (704, 1333), (736, 1333),
(768, 1333), (800, 1333)],
'multiscale_mode':
'value',
'override':
True,
'keep_ratio':
True
}]]),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'])
]
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_train2017.json',
img_prefix='data/coco/train2017/',
classes=[
'speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
'speedlimit-70', 'speedlimit-80', 'restrict-end-80',
'speedlimit-100', 'speedlimit-120', 'no-overtake',
'no-overtake-truck', 'priority-next-intersect', 'priority-road',
'giveaway', 'stop', 'no-traffic-bothways', 'no-truck', 'no-entry',
'danger', 'bend-left', 'bend-right', 'bend', 'uneven-road',
'slippery-road', 'road-narrow', 'construction', 'traffic-signal',
'pedestrian-crossing', 'school-crossing', 'cycle-crossing', 'snow',
'animals', 'restriction-ends', 'go-right', 'go-left',
'go-straight', 'go-right-straight', 'go-left-straight',
'keep-right', 'keep-left', 'roundabout',
'restrict-ends-overtaking', 'restrict-ends-overtaking-truck'
],
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='AutoAugment',
policies=[[{
'type':
'Resize',
'img_scale': [(480, 1333), (512, 1333), (544, 1333),
(576, 1333), (608, 1333), (640, 1333),
(672, 1333), (704, 1333), (736, 1333),
(768, 1333), (800, 1333)],
'multiscale_mode':
'value',
'keep_ratio':
True
}],
[{
'type': 'Resize',
'img_scale': [(400, 1333), (500, 1333),
(600, 1333)],
'multiscale_mode': 'value',
'keep_ratio': True
}, {
'type': 'RandomCrop',
'crop_type': 'absolute_range',
'crop_size': (384, 600),
'allow_negative_crop': True
}, {
'type':
'Resize',
'img_scale': [(480, 1333), (512, 1333),
(544, 1333), (576, 1333),
(608, 1333), (640, 1333),
(672, 1333), (704, 1333),
(736, 1333), (768, 1333),
(800, 1333)],
'multiscale_mode':
'value',
'override':
True,
'keep_ratio':
True
}]]),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'])
]),
val=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_val2017.json',
img_prefix='data/coco/val2017/',
classes=[
'speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
'speedlimit-70', 'speedlimit-80', 'restrict-end-80',
'speedlimit-100', 'speedlimit-120', 'no-overtake',
'no-overtake-truck', 'priority-next-intersect', 'priority-road',
'giveaway', 'stop', 'no-traffic-bothways', 'no-truck', 'no-entry',
'danger', 'bend-left', 'bend-right', 'bend', 'uneven-road',
'slippery-road', 'road-narrow', 'construction', 'traffic-signal',
'pedestrian-crossing', 'school-crossing', 'cycle-crossing', 'snow',
'animals', 'restriction-ends', 'go-right', 'go-left',
'go-straight', 'go-right-straight', 'go-left-straight',
'keep-right', 'keep-left', 'roundabout',
'restrict-ends-overtaking', 'restrict-ends-overtaking-truck'
],
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CocoDataset',
ann_file='data/coco/annotations/instances_val2017.json',
img_prefix='data/coco/val2017/',
classes=[
'speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
'speedlimit-70', 'speedlimit-80', 'restrict-end-80',
'speedlimit-100', 'speedlimit-120', 'no-overtake',
'no-overtake-truck', 'priority-next-intersect', 'priority-road',
'giveaway', 'stop', 'no-traffic-bothways', 'no-truck', 'no-entry',
'danger', 'bend-left', 'bend-right', 'bend', 'uneven-road',
'slippery-road', 'road-narrow', 'construction', 'traffic-signal',
'pedestrian-crossing', 'school-crossing', 'cycle-crossing', 'snow',
'animals', 'restriction-ends', 'go-right', 'go-left',
'go-straight', 'go-right-straight', 'go-left-straight',
'keep-right', 'keep-left', 'roundabout',
'restrict-ends-overtaking', 'restrict-ends-overtaking-truck'
],
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',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(
type='AdamW',
lr=0.0001,
betas=(0.9, 0.999),
weight_decay=0.05,
paramwise_cfg=dict(
custom_keys=dict(
absolute_pos_embed=dict(decay_mult=0.0),
relative_position_bias_table=dict(decay_mult=0.0),
norm=dict(decay_mult=0.0))))
optimizer_config = dict(
grad_clip=None,
type='DistOptimizerHook',
update_interval=1,
coalesce=True,
bucket_size_mb=-1,
use_fp16=True)
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[27, 33])
runner = dict(type='EpochBasedRunnerAmp', max_epochs=36)
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
fp16 = None
work_dir = './work_dirs/mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_3x_coco'
gpu_ids = range(0, 1)