在ssdd上的测试map接近0

[cowqer]

你好，请问这种小数据集是不是不太适合DETR系列的模型呢？我尝试在ARS-DETR上复现，结果也接近0，但是类似的配置参数在mmrotate的官方仓库能达到ap50：0.90左右。

2025-01-04 16:47:44,565 - mmrotate - INFO - Environment info:

sys.platform: linux
Python: 3.8.20 | packaged by conda-forge | (default, Sep 30 2024, 17:52:49) [GCC 13.3.0]
CUDA available: True
GPU 0: NVIDIA GeForce RTX 3090
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.3, V11.3.58
GCC: gcc (Ubuntu 7.5.0-6ubuntu2) 7.5.0
PyTorch: 1.12.1+cu113
PyTorch compiling details: PyTorch built with:

• GCC 9.3
• C++ Version: 201402
• Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
• OpenMP 201511 (a.k.a. OpenMP 4.5)
• LAPACK is enabled (usually provided by MKL)
• NNPACK is enabled
• CPU capability usage: AVX2
• CUDA Runtime 11.3
• NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86
• CuDNN 8.3.2 (built against CUDA 11.5)
• Magma 2.5.2
• Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,

TorchVision: 0.13.1+cu113
OpenCV: 4.10.0
MMCV: 1.7.2
MMCV Compiler: GCC 9.3
MMCV CUDA Compiler: 11.3
MMRotate: 0.1.0+f6da5ee

2025-01-04 16:47:44,879 - mmrotate - INFO - Distributed training: False
2025-01-04 16:47:45,188 - mmrotate - INFO - Config:
dataset_type = 'SARDataset'
data_root = '/data/seekyou/ssdd/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RResize', img_scale=(608, 608)),
dict(
type='RRandomFlip',
flip_ratio=[0.25, 0.25, 0.25],
direction=['horizontal', 'vertical', 'diagonal'],
version='oc'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=False),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(608, 608),
flip=False,
transforms=[
dict(type='RResize'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=False),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=2,
train=dict(
type='SARDataset',
ann_file='/data/seekyou/ssdd/train/labelTxt/',
img_prefix='/data/seekyou/ssdd/train/images/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RResize', img_scale=(608, 608)),
dict(
type='RRandomFlip',
flip_ratio=[0.25, 0.25, 0.25],
direction=['horizontal', 'vertical', 'diagonal'],
version='oc'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=False),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
],
filter_empty_gt=False,
version='oc'),
val=dict(
type='SARDataset',
ann_file='/data/seekyou/ssdd/test/inshore/labelTxt/',
img_prefix='/data/seekyou/ssdd/test/inshore/images/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(608, 608),
flip=False,
transforms=[
dict(type='RResize'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=False),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
],
version='oc'),
test=dict(
type='SARDataset',
ann_file='/data/seekyou/ssdd/test/all/labelTxt/',
img_prefix='/data/seekyou/ssdd/test/all/images/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(608, 608),
flip=False,
transforms=[
dict(type='RResize'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=False),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
],
version='oc'))
evaluation = dict(interval=1, metric='mAP', save_best='auto')
optimizer = dict(
type='AdamW',
lr=0.0001,
weight_decay=1e-05,
betas=(0.9, 0.999),
paramwise_cfg=dict(
custom_keys=dict(
backbone=dict(lr_mult=0.1),
sampling_offsets=dict(lr_mult=0.1),
reference_points=dict(lr_mult=0.1))))
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.3333333333333333,
step=[120])
runner = dict(type='EpochBasedRunner', max_epochs=150)
checkpoint_config = dict(interval=6)
log_config = dict(interval=20, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
angle_version = 'oc'
model = dict(
type='RotatedDeformableDETR',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='ChannelMapper',
in_channels=[512, 1024, 2048],
kernel_size=1,
out_channels=256,
act_cfg=None,
norm_cfg=dict(type='GN', num_groups=32),
num_outs=4),
bbox_head=dict(
type='RotatedDeformableDETRHead',
num_query=250,
num_classes=1,
in_channels=2048,
sync_cls_avg_factor=True,
as_two_stage=True,
transformer=dict(
type='RotatedDeformableDetrTransformer',
two_stage_num_proposals=250,
encoder=dict(
type='DetrTransformerEncoder',
num_layers=6,
transformerlayers=dict(
type='BaseTransformerLayer',
attn_cfgs=dict(
type='MultiScaleDeformableAttention', embed_dims=256),
feedforward_channels=1024,
ffn_dropout=0.1,
operation_order=('self_attn', 'norm', 'ffn', 'norm'))),
decoder=dict(
type='RotatedDeformableDetrTransformerDecoder',
num_layers=6,
return_intermediate=True,
transformerlayers=dict(
type='DetrTransformerDecoderLayer',
attn_cfgs=[
dict(
type='MultiheadAttention',
embed_dims=256,
num_heads=8,
dropout=0.1),
dict(
type='MultiScaleDeformableAttention',
embed_dims=256)
],
feedforward_channels=1024,
ffn_dropout=0.1,
operation_order=('self_attn', 'norm', 'cross_attn', 'norm',
'ffn', 'norm')))),
positional_encoding=dict(
type='SinePositionalEncoding',
num_feats=128,
normalize=True,
offset=-0.5),
bbox_coder=dict(
type='DeltaXYWHAOBBoxCoder',
angle_range='oc',
norm_factor=None,
edge_swap=True,
proj_xy=True,
target_means=(0.0, 0.0, 0.0, 0.0, 0.0),
target_stds=(0.1, 0.1, 0.2, 0.2, 0.1)),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=2.0),
loss_bbox=dict(type='L1Loss', loss_weight=2.0),
reg_decoded_bbox=True,
loss_iou=dict(type='RotatedIoULoss', loss_weight=5.0),
with_box_refine=True),
train_cfg=dict(
assigner=dict(
type='Rotated_HungarianAssigner',
cls_cost=dict(type='FocalLossCost', weight=2.0),
reg_cost=dict(type='RBBoxL1Cost', weight=2.0, box_format='xywha'),
iou_cost=dict(type='RotatedIoUCost', iou_mode='iou', weight=5.0))),
test_cfg=dict())
find_unused_parameters = True
work_dir = 'work_dirs/new_refine/'
auto_resume = False
gpu_ids = range(0, 1)