使用co_dino_5scale_swin_large_3x_coco配置训练不收敛

[hhitdata]

用7000多张的数据训练这个模型可以收敛，但换了十万多的不同类别的数据训练12个epoch后推理结果都为空，loss一直在80左右，下面是配置文件，4张3090的卡，想问下是哪里的问题。

dataset_type = 'CocoDataset'
data_root = '/mnt/disk3/Co-DETR/dataset/wxcl/'
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='RandomFlip', flip_ratio=0.5),
dict(
type='AutoAugment',
policies=[[{
'type':
'Resize',
'img_scale': [(480, 1280), (512, 1280), (544, 1280), (576, 1280),
(608, 1280), (640, 1280), (672, 1280), (704, 1280),
(736, 1280), (768, 1280), (800, 1280)],
'multiscale_mode':
'value',
'keep_ratio':
True
}],
[{
'type': 'Resize',
'img_scale': [(400, 4200), (500, 4200), (600, 4200)],
'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, 1280), (512, 1280), (544, 1280),
(576, 1280), (608, 1280), (640, 1280),
(672, 1280), (704, 1280), (736, 1280),
(768, 1280), (800, 1280)],
'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=1),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1280, 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=1),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=1,
train=dict(
type='CocoDataset',
ann_file='/mnt/disk3/Co-DETR/dataset/wxcl/Annotations/train.json',
img_prefix='/mnt/disk3/Co-DETR/dataset/wxcl/Images/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='AutoAugment',
policies=[[{
'type':
'Resize',
'img_scale': [(480, 1280), (512, 1280), (544, 1280),
(576, 1280), (608, 1280), (640, 1280),
(672, 1280), (704, 1280), (736, 1280),
(768, 1280), (800, 1280)],
'multiscale_mode':
'value',
'keep_ratio':
True
}],
[{
'type': 'Resize',
'img_scale': [(400, 4200), (500, 4200),
(600, 4200)],
'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, 1280), (512, 1280),
(544, 1280), (576, 1280),
(608, 1280), (640, 1280),
(672, 1280), (704, 1280),
(736, 1280), (768, 1280),
(800, 1280)],
'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=1),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
],
filter_empty_gt=False),
val=dict(
type='CocoDataset',
ann_file=
'/mnt/disk3/Co-DETR/dataset/wxcl/realistic_application_2/val.json',
img_prefix='/mnt/disk3/Co-DETR/dataset/wxcl/realistic_application_2/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1280, 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=1),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='CocoDataset',
ann_file=
'/mnt/disk3/Co-DETR/dataset/wxcl/realistic_application_2/val.json',
img_prefix='/mnt/disk3/Co-DETR/dataset/wxcl/realistic_application_2/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1280, 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=1),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]))
evaluation = dict(interval=1, metric='bbox')
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)]
opencv_num_threads = 2
mp_start_method = 'fork'
auto_scale_lr = dict(enable=False, base_batch_size=16)
num_dec_layer = 4
lambda_2 = 2.0
model = dict(
type='CoDETR',
backbone=dict(
type='SwinTransformerV1',
embed_dim=192,
depths=[2, 2, 18, 2],
num_heads=[6, 12, 24, 48],
out_indices=(0, 1, 2, 3),
window_size=12,
ape=False,
drop_path_rate=0.3,
patch_norm=True,
use_checkpoint=False,
pretrained=
'/mnt/disk3/Co-DETR/models/co_dino_5scale_swin_large_3x_coco.pth'),
neck=dict(
type='ChannelMapper',
in_channels=[192, 384, 768, 1536],
kernel_size=1,
out_channels=256,
act_cfg=None,
norm_cfg=dict(type='GN', num_groups=32),
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
octave_base_scale=4,
scales_per_octave=3,
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64, 128]),
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=12.0),
loss_bbox=dict(type='L1Loss', loss_weight=12.0)),
query_head=dict(
type='CoDINOHead',
num_query=900,
num_classes=8,
num_feature_levels=5,
in_channels=2048,
sync_cls_avg_factor=True,
as_two_stage=True,
with_box_refine=True,
mixed_selection=True,
dn_cfg=dict(
type='CdnQueryGenerator',
noise_scale=dict(label=0.5, box=1.0),
group_cfg=dict(dynamic=True, num_groups=None, num_dn_queries=100)),
transformer=dict(
type='CoDinoTransformer',
with_pos_coord=True,
with_coord_feat=False,
num_co_heads=2,
num_feature_levels=5,
encoder=dict(
type='DetrTransformerEncoder',
num_layers=6,
with_cp=6,
transformerlayers=dict(
type='BaseTransformerLayer',
attn_cfgs=dict(
type='MultiScaleDeformableAttention',
embed_dims=256,
num_levels=5,
dropout=0.0),
feedforward_channels=2048,
ffn_dropout=0.0,
operation_order=('self_attn', 'norm', 'ffn', 'norm'))),
decoder=dict(
type='DinoTransformerDecoder',
num_layers=6,
return_intermediate=True,
transformerlayers=dict(
type='DetrTransformerDecoderLayer',
attn_cfgs=[
dict(
type='MultiheadAttention',
embed_dims=256,
num_heads=8,
dropout=0.0),
dict(
type='MultiScaleDeformableAttention',
embed_dims=256,
num_levels=5,
dropout=0.0)
],
feedforward_channels=2048,
ffn_dropout=0.0,
operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
'ffn', 'norm')))),
positional_encoding=dict(
type='SinePositionalEncoding',
num_feats=128,
temperature=20,
normalize=True),
loss_cls=dict(
type='QualityFocalLoss',
use_sigmoid=True,
beta=2.0,
loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=5.0),
loss_iou=dict(type='GIoULoss', loss_weight=2.0)),
roi_head=[
dict(
type='CoStandardRoIHead',
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, 64],
finest_scale=56),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=8,
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,
reg_decoded_bbox=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=12.0),
loss_bbox=dict(type='GIoULoss', loss_weight=120.0)))
],
bbox_head=[
dict(
type='CoATSSHead',
num_classes=8,
in_channels=256,
stacked_convs=1,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
ratios=[1.0],
octave_base_scale=8,
scales_per_octave=1,
strides=[4, 8, 16, 32, 64, 128]),
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]),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=12.0),
loss_bbox=dict(type='GIoULoss', loss_weight=24.0),
loss_centerness=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=12.0))
],
train_cfg=[
dict(
assigner=dict(
type='HungarianAssigner',
cls_cost=dict(type='FocalLossCost', weight=2.0),
reg_cost=dict(
type='BBoxL1Cost', weight=5.0, box_format='xywh'),
iou_cost=dict(type='IoUCost', iou_mode='giou', weight=2.0))),
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=4000,
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)),
dict(
assigner=dict(type='ATSSAssigner', topk=9),
allowed_border=-1,
pos_weight=-1,
debug=False)
],
test_cfg=[
dict(max_per_img=300, nms=dict(type='soft_nms', iou_threshold=0.8)),
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=0.0,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)),
dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.0,
nms=dict(type='nms', iou_threshold=0.6),
max_per_img=100)
])
optimizer = dict(
type='AdamW',
lr=0.0004,
weight_decay=0.0001,
paramwise_cfg=dict(custom_keys=dict(backbone=dict(lr_mult=0.1))))
optimizer_config = dict(grad_clip=dict(max_norm=0.1, norm_type=2))
lr_config = dict(policy='step', step=[9])
runner = dict(type='EpochBasedRunner', max_epochs=12)
pretrained = '/mnt/disk3/Co-DETR/models/co_dino_5scale_swin_large_3x_coco.pth'
work_dir = './run3'
auto_resume = False
gpu_ids = range(0, 4)

[TempleX98]

如果用mmdetection里的faster-rcnn来训会收敛吗。如果还是不收敛，那要么是你的十万多数据噪音比较大，要么是自定义数据集那部分不对

[hhitdata]

如果用mmdetection里的faster-rcnn来训会收敛吗。如果还是不收敛，那要么是你的十万多数据噪音比较大，要么是自定义数据集那部分不对

之前这批数据用yolo5跑过是可以收敛的，我再看看自定义数据集的设置