SoftTeacher
SoftTeacher copied to clipboard
Published
20 hours ago •
microsoft
microsoft
TypeError: SoftTeacher: __init__() got an unexpected keyword argument 'pretrained'
在使用dist_test.sh进行infer的时候报这个错误改怎么处理呢
Traceback (most recent call last):
File "/root/factory/mmdetection2_16/mmdet2.16/tools/test.py", line 264, in <module>
main()
File "/root/factory/mmdetection2_16/mmdet2.16/tools/test.py", line 207, in main
model = build_detector(cfg.model, test_cfg=cfg.get("test_cfg"))
File "/root/factory/mmdetection2_16/mmdet2.16/mmdet/models/builder.py", line 59, in build_detector
cfg, default_args=dict(train_cfg=train_cfg, test_cfg=test_cfg))
File "/root/environment/anaconda3/envs/mmdet2.16/lib/python3.7/site-packages/mmcv/utils/registry.py", line 210, in build
return self.build_func(*args, **kwargs, registry=self)
File "/root/environment/anaconda3/envs/mmdet2.16/lib/python3.7/site-packages/mmcv/cnn/builder.py", line 26, in build_model_from_cfg
return build_from_cfg(cfg, registry, default_args)
File "/root/environment/anaconda3/envs/mmdet2.16/lib/python3.7/site-packages/mmcv/utils/registry.py", line 54, in build_from_cfg
raise type(e)(f'{obj_cls.__name__}: {e}')
TypeError: SoftTeacher: __init__() got an unexpected keyword argument 'pretrained'
Traceback (most recent call last):
File "/root/environment/anaconda3/envs/mmdet2.16/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/root/environment/anaconda3/envs/mmdet2.16/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/root/environment/anaconda3/envs/mmdet2.16/lib/python3.7/site-packages/torch/distributed/launch.py", line 261, in <module>
main()
File "/root/environment/anaconda3/envs/mmdet2.16/lib/python3.7/site-packages/torch/distributed/launch.py", line 257, in main
cmd=cmd)
subprocess.CalledProcessError: Command '['/root/environment/anaconda3/envs/mmdet2.16/bin/python', '-u', '/root/factory/mmdetection2_16/mmdet2.16/tools/test.py', '--local_rank=0', '/root/factory/mmdetection2_16/project/terror/model/semi/faster_rcnn_swin_transformer_fpn_30e_coco_semi_all.py', '/root/factory/terror_infer/faster_rcnn_swin_transformer_fpn_30e_coco_semi_all/output/epoch_30.pth', '--launcher', 'pytorch', '--work-dir', '/root/factory/mmdetection2_16/work_dirs/', '--out', '/root/tmp/1.pkl']' returned non-zero exit status 1.
Hi, it seems that you use old style of setting pretrained weights like
pretrained=...
Instead of this try like in the new version of mmdetection
https://github.com/open-mmlab/mmdetection/blob/master/configs/base/models/faster_rcnn_r50_fpn.py#L13
in backbone like this:
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
我设置的预训练权重确实是新版的init_cfg=dict(type='Pretrained',checkpoint='/root/factory/pre_trained/swin_tiny_224_b16x64_300e_imagenet_20210616_090925-66df6be6.pth') 训练的时候可以正常创建检测器，但是测试就报错了，我的配置文件如下：
model = dict(
type='SoftTeacher',
model=dict(
type='FasterRCNN',
backbone=dict(
type='SwinTransformer',
embed_dims=96,
depths=[2, 2, 6, 2],
num_heads=[3, 6, 12, 24],
window_size=7,
mlp_ratio=4,
qkv_bias=True,
qk_scale=None,
drop_rate=0.0,
attn_drop_rate=0.0,
drop_path_rate=0.2,
patch_norm=True,
out_indices=(0, 1, 2, 3),
with_cp=False,
init_cfg=dict(
type='Pretrained',
checkpoint=
'/root/factory/pre_trained/swin_tiny_224_b16x64_300e_imagenet_20210616_090925-66df6be6.pth'
)),
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=71,
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))),
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=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)),
test_cfg=dict(
rpn=dict(
nms_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100))),
train_cfg=dict(
use_teacher_proposal=False,
pseudo_label_initial_score_thr=0.5,
rpn_pseudo_threshold=0.9,
cls_pseudo_threshold=0.9,
reg_pseudo_threshold=0.01,
jitter_times=10,
jitter_scale=0.06,
min_pseduo_box_size=0,
unsup_weight=2.0),
test_cfg=dict(inference_on='student'))
img_norm_cfg = dict(
mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
])
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='sup'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
'pad_shape', 'scale_factor', 'tag'))
]
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=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
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='SemiDataset',
sup=dict(
type='CocoDataset',
ann_file = '/root/dataset/train_terror/coco_anno.json',
img_prefix = '/root/dataset/train_terror/images',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
])
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='sup'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape', 'scale_factor',
'tag'))
]),
unsup=dict(
type='CocoDataset',
ann_file = '/root/dataset/train_terror/coco_anno.json',
img_prefix = '/root/dataset/train_terror/images',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='PseudoSamples', with_bbox=True),
dict(
type='MultiBranch',
unsup_teacher=[
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='ShuffledSequential',
transforms=[
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
]),
dict(
type='OneOf',
transforms=[{
'type': 'RandTranslate',
'x': (-0.1, 0.1)
}, {
'type': 'RandTranslate',
'y': (-0.1, 0.1)
}, {
'type': 'RandRotate',
'angle': (-30, 30)
},
[{
'type':
'RandShear',
'x': (-30, 30)
}, {
'type':
'RandShear',
'y': (-30, 30)
}]])
]),
dict(
type='RandErase',
n_iterations=(1, 5),
size=[0, 0.2],
squared=True)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_student'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape',
'scale_factor', 'tag',
'transform_matrix'))
],
unsup_student=[
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_teacher'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape',
'scale_factor', 'tag',
'transform_matrix'))
])
],
filter_empty_gt=False)),
val=dict(
type='CocoDataset',
ann_file = '/root/dataset/train_terror/coco_anno.json',
img_prefix = '/root/dataset/train_terror/images',
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=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CocoDataset',
ann_file = '/root/dataset/train_terror/coco_anno.json',
img_prefix = '/root/dataset/train_terror/images',
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=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
sampler=dict(
train=dict(
type='SemiBalanceSampler',
sample_ratio=[1, 1],
by_prob=True,
epoch_length=7330)))
evaluation = dict(interval=100, 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)
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[27, 29])
runner = dict(type='EpochBasedRunner', max_epochs=30)
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [
dict(type='NumClassCheckHook'),
dict(type='WeightSummary'),
dict(type='MeanTeacher', momentum=0.999, interval=1, warm_up=0)
]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
mmdet_base = '../../thirdparty/mmdetection/configs/_base_'
strong_pipeline = [
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='ShuffledSequential',
transforms=[
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
]),
dict(
type='OneOf',
transforms=[{
'type': 'RandTranslate',
'x': (-0.1, 0.1)
}, {
'type': 'RandTranslate',
'y': (-0.1, 0.1)
}, {
'type': 'RandRotate',
'angle': (-30, 30)
},
[{
'type': 'RandShear',
'x': (-30, 30)
}, {
'type': 'RandShear',
'y': (-30, 30)
}]])
]),
dict(
type='RandErase',
n_iterations=(1, 5),
size=[0, 0.2],
squared=True)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_student'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
'pad_shape', 'scale_factor', 'tag', 'transform_matrix'))
]
weak_pipeline = [
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_teacher'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
'pad_shape', 'scale_factor', 'tag', 'transform_matrix'))
]
unsup_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='PseudoSamples', with_bbox=True),
dict(
type='MultiBranch',
unsup_teacher=[
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='ShuffledSequential',
transforms=[
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
]),
dict(
type='OneOf',
transforms=[{
'type': 'RandTranslate',
'x': (-0.1, 0.1)
}, {
'type': 'RandTranslate',
'y': (-0.1, 0.1)
}, {
'type': 'RandRotate',
'angle': (-30, 30)
},
[{
'type': 'RandShear',
'x': (-30, 30)
}, {
'type': 'RandShear',
'y': (-30, 30)
}]])
]),
dict(
type='RandErase',
n_iterations=(1, 5),
size=[0, 0.2],
squared=True)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_student'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape', 'scale_factor', 'tag',
'transform_matrix'))
],
unsup_student=[
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_teacher'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape', 'scale_factor', 'tag',
'transform_matrix'))
])
]
fp16 = dict(loss_scale='dynamic')
fold = 1
percent = 10
work_dir = './work_dirs/soft_teacher_faster_rcnn_r50_caffe_fpn_coco_full_720k'
cfg_name = 'soft_teacher_faster_rcnn_r50_caffe_fpn_coco_full_720k'
gpu_ids = range(0, 2)
主要原因在于你改了config之后，它会在
https://github.com/microsoft/SoftTeacher/blob/4c053b32d30f3685e553a386dc5234145e494713/tools/test.py#L144
试图为model加入pretrained属性.
要么你可以改成我们之前的写法，
https://github.com/microsoft/SoftTeacher/blob/4c053b32d30f3685e553a386dc5234145e494713/configs/soft_teacher/base.py#L239
要么你需要注释掉这部分的代码。
我现在更换为原始的config，还是出现相同的错误 TypeError: SoftTeacher: init() got an unexpected keyword argument 'pretrained'
model = dict(
type='SoftTeacher',
model=dict(
type='FasterRCNN',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 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=71,
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))),
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=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)),
test_cfg=dict(
rpn=dict(
nms_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100))),
train_cfg=dict(
use_teacher_proposal=False,
pseudo_label_initial_score_thr=0.5,
rpn_pseudo_threshold=0.9,
cls_pseudo_threshold=0.9,
reg_pseudo_threshold=0.01,
jitter_times=10,
jitter_scale=0.06,
min_pseduo_box_size=0,
unsup_weight=2.0),
test_cfg=dict(inference_on='student'))
dataset_type = 'CocoDataset'
data_root = '/root/dataset/coco/'
img_norm_cfg = dict(
mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
])
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='sup'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
'pad_shape', 'scale_factor', 'tag'))
]
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=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
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='SemiDataset',
sup=dict(
type='CocoDataset',
ann_file='/tmp/train/train_terror/coco_anno@1%.json',
img_prefix='/tmp/train/train_terror/images',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
])
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='sup'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape', 'scale_factor',
'tag'))
]),
unsup=dict(
type='CocoDataset',
ann_file='/tmp/train/semi_unlabeled/unlabeled_coco_anno.json',
img_prefix='/tmp/train/semi_unlabeled/images',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='PseudoSamples', with_bbox=True),
dict(
type='MultiBranch',
unsup_teacher=[
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='ShuffledSequential',
transforms=[
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
]),
dict(
type='OneOf',
transforms=[{
'type': 'RandTranslate',
'x': (-0.1, 0.1)
}, {
'type': 'RandTranslate',
'y': (-0.1, 0.1)
}, {
'type': 'RandRotate',
'angle': (-30, 30)
},
[{
'type':
'RandShear',
'x': (-30, 30)
}, {
'type':
'RandShear',
'y': (-30, 30)
}]])
]),
dict(
type='RandErase',
n_iterations=(1, 5),
size=[0, 0.2],
squared=True)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_student'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape',
'scale_factor', 'tag',
'transform_matrix'))
],
unsup_student=[
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_teacher'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape',
'scale_factor', 'tag',
'transform_matrix'))
])
],
filter_empty_gt=False)),
val=dict(
type='CocoDataset',
ann_file='/tmp/train/train_terror/coco_anno@1%.json',
img_prefix='/tmp/train/train_terror/images',
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=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CocoDataset',
ann_file='/tmp/train/train_terror/coco_anno@1%.json',
img_prefix='/tmp/train/train_terror/images',
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=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
sampler=dict(
train=dict(
type='SemiBalanceSampler',
sample_ratio=[1, 1],
by_prob=True,
epoch_length=7330)))
evaluation = dict(interval=100, metric='bbox')
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[17, 19])
runner = dict(type='EpochBasedRunner', max_epochs=20)
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [
dict(type='NumClassCheckHook'),
dict(type='WeightSummary'),
dict(type='MeanTeacher', momentum=0.999, interval=1, warm_up=0)
]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
strong_pipeline = [
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='ShuffledSequential',
transforms=[
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
]),
dict(
type='OneOf',
transforms=[{
'type': 'RandTranslate',
'x': (-0.1, 0.1)
}, {
'type': 'RandTranslate',
'y': (-0.1, 0.1)
}, {
'type': 'RandRotate',
'angle': (-30, 30)
},
[{
'type': 'RandShear',
'x': (-30, 30)
}, {
'type': 'RandShear',
'y': (-30, 30)
}]])
]),
dict(
type='RandErase',
n_iterations=(1, 5),
size=[0, 0.2],
squared=True)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_student'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
'pad_shape', 'scale_factor', 'tag', 'transform_matrix'))
]
weak_pipeline = [
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_teacher'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
'pad_shape', 'scale_factor', 'tag', 'transform_matrix'))
]
unsup_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='PseudoSamples', with_bbox=True),
dict(
type='MultiBranch',
unsup_teacher=[
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5),
dict(
type='ShuffledSequential',
transforms=[
dict(
type='OneOf',
transforms=[
dict(type='Identity'),
dict(type='AutoContrast'),
dict(type='RandEqualize'),
dict(type='RandSolarize'),
dict(type='RandColor'),
dict(type='RandContrast'),
dict(type='RandBrightness'),
dict(type='RandSharpness'),
dict(type='RandPosterize')
]),
dict(
type='OneOf',
transforms=[{
'type': 'RandTranslate',
'x': (-0.1, 0.1)
}, {
'type': 'RandTranslate',
'y': (-0.1, 0.1)
}, {
'type': 'RandRotate',
'angle': (-30, 30)
},
[{
'type': 'RandShear',
'x': (-30, 30)
}, {
'type': 'RandShear',
'y': (-30, 30)
}]])
]),
dict(
type='RandErase',
n_iterations=(1, 5),
size=[0, 0.2],
squared=True)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_student'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape', 'scale_factor', 'tag',
'transform_matrix'))
],
unsup_student=[
dict(
type='Sequential',
transforms=[
dict(
type='RandResize',
img_scale=[(1333, 400), (1333, 1200)],
multiscale_mode='range',
keep_ratio=True),
dict(type='RandFlip', flip_ratio=0.5)
],
record=True),
dict(type='Pad', size_divisor=32),
dict(
type='Normalize',
mean=[103.53, 116.28, 123.675],
std=[1.0, 1.0, 1.0],
to_rgb=False),
dict(type='ExtraAttrs', tag='unsup_teacher'),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels'],
meta_keys=('filename', 'ori_shape', 'img_shape',
'img_norm_cfg', 'pad_shape', 'scale_factor', 'tag',
'transform_matrix'))
])
]
fp16 = dict(loss_scale='dynamic')
fold = 1
percent = 10
work_dir = './work_dirs/soft_teacher_faster_rcnn_r50_caffe_fpn_coco_full_720k'
cfg_name = 'soft_teacher_faster_rcnn_r50_caffe_fpn_coco_full_720k'
gpu_ids = range(0, 2)
你这个不是原始的config啊，
原始的config里面没有 model=dict(type='SoftTeacher')，而是通过semi_wrapper实现的。
The code has been updated to be compatible with your config file. Could you have a test?