The original code version is too old, so I reproduced the code to the new mmrotate version. I loaded the weights you provided and it went fine, the result was an accuracy of 68 on the validation set and 54 on the test set.
I don't know where the problem is, the weight file is loaded smoothly, I have also checked the configuration file parameters, but I just don't know what went wrong.If there is a problem with my reproduction, the final result should be 0, and it should not be as high as 54
dataset_type = 'DOTADataset'
data_root = '/data/facias/DOTA/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
angle_version = 'le90'
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RResize', img_scale=(1024, 1024)),
dict(
type='RRandomFlip',
flip_ratio=[0.25, 0.25, 0.25],
direction=['horizontal', 'vertical', 'diagonal'],
version=angle_version),
dict(type='Normalize', **img_norm_cfg),
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=(1024, 1024),
flip=False,
transforms=[
dict(type='RResize', img_scale=(1024, 1024)),
dict(type='RRandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'train_split/labelTXt/',
img_prefix=data_root + 'train_split/images/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'val_split/labelTxt/',
img_prefix=data_root + 'val_split/images/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
test_mode=True, #若test数据集没有标注,则设为True
ann_file=data_root + 'test_split/images/',
img_prefix=data_root + 'test_split/images/',
pipeline=test_pipeline))
model = dict(
type='OrientedRCNN',
backbone=dict(
type='ViT_Win_RVSA_V3_WSZ7',
img_size=1024,
embed_dim=768,
depth=12,
num_heads=12,
mlp_ratio=4,
qkv_bias=True,
drop_rate=0.,
attn_drop_rate=0.,
drop_path_rate=0.15,
use_abs_pos_emb=True),
neck=dict(
type='FPN',
in_channels=[768, 768, 768, 768],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='OrientedRPNHead',
in_channels=256,
feat_channels=256,
version=angle_version,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='MidpointOffsetCoder',
angle_range=angle_version,
target_means=[0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
target_stds=[1.0, 1.0, 1.0, 1.0, 0.5, 0.5]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(
type='SmoothL1Loss', beta=0.1111111111111111, loss_weight=1.0)),
roi_head=dict(
type='OrientedStandardRoIHead',
bbox_roi_extractor=dict(
type='RotatedSingleRoIExtractor',
roi_layer=dict(
type='RoIAlignRotated',
out_size=7,
sample_num=2,
clockwise=True),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='RotatedShared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=15,
bbox_coder=dict(
type='DeltaXYWHAOBBoxCoder',
angle_range=angle_version,
norm_factor=None,
edge_swap=True,
proj_xy=True,
target_means=(.0, .0, .0, .0, .0),
target_stds=(0.1, 0.1, 0.2, 0.2, 0.1)),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, 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=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.8),
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,
iou_calculator=dict(type='RBboxOverlaps2D'),
ignore_iof_thr=-1),
sampler=dict(
type='RRandomSampler',
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=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.8),
min_bbox_size=0),
rcnn=dict(
nms_pre=2000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(iou_thr=0.1),
max_per_img=2000)))
# evaluation
evaluation = dict(interval=1, metric='mAP')
# optimizer
optimizer = dict(type='SGD', lr=0.0025, 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])
runner = dict(type='EpochBasedRunner', max_epochs=12)
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
# disable opencv multithreading to avoid system being overloaded
opencv_num_threads = 0
# set multi-process start method as `fork` to speed up the training
mp_start_method = 'fork'