datasets
Opened this issue · 2 comments
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'train/labelTxt/',
img_prefix=data_root + 'train/images/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'test/inshore/labelTxt/',
img_prefix=data_root + 'test/inshore/images/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'test/offshore/labelTxt/',
img_prefix=data_root + 'test/offshore/images/',
pipeline=test_pipeline))
Please introduce the base of inshore and offshore.
sorry, I am not sure what the problem is given the limited information. Could you please describe the problem in detail?
1.> 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='RResize', img_scale=(640, 640)),
dict(type='RRandomFlip', flip_ratio=0.5),
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'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(640, 640),
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=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
]
data = dict(
samples_per_gpu=4,
workers_per_gpu=4,
train=dict(
type='DOTADataset',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RResize', img_scale=(640, 640)),
dict(type='RRandomFlip', flip_ratio=0.5),
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'])
]),
val=dict(
type='DOTADataset',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(640, 640),
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=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='DOTADataset',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(640, 640),
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=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
]))
evaluation = dict(interval=5, metric='mAP')
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))
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.3333333333333333,
step=[8, 11])
runner = dict(type='EpochBasedRunner', max_epochs=150)
checkpoint_config = dict(interval=5)
log_config = dict(interval=100, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
opencv_num_threads = 0
mp_start_method = 'fork'
angle_version = 'le135'
model = dict(
type='RotatedRetinaNet',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
zero_init_residual=False,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs='on_input',
num_outs=5),
bbox_head=dict(
type='RDCFLHead',
num_classes=1,
in_channels=256,
stacked_convs=4,
feat_channels=256,
assign_by_circumhbbox=None,
dcn_assign=True,
dilation_rate=3,
anchor_generator=dict(
type='RotatedAnchorGenerator',
octave_base_scale=4,
scales_per_octave=1,
ratios=[1.0],
strides=[8, 16, 32, 64, 128]),
bbox_coder=dict(
type='DeltaXYWHAOBBoxCoder',
angle_range='le135',
norm_factor=1,
edge_swap=False,
proj_xy=True,
target_means=(0.0, 0.0, 0.0, 0.0, 0.0),
target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
reg_decoded_bbox=True,
loss_bbox=dict(type='RotatedIoULoss', loss_weight=1.0)),
train_cfg=dict(
assigner=dict(
type='C2FAssigner',
ignore_iof_thr=-1,
gpu_assign_thr=1024,
iou_calculator=dict(type='RBboxMetrics2D'),
assign_metric='gjsd',
topk=16,
topq=12,
constraint='dgmm',
gauss_thr=0.6),
allowed_border=-1,
pos_weight=-1,
debug=False),
test_cfg=dict(
nms_pre=2000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(iou_thr=0.4),
max_per_img=2000))
2.mmrotate/models/dense_heads/init.py
####### from .oriented_reppoints_head import OrientedRepPointsHead
[ERROR]
Traceback (most recent call last):
File "./tools/train.py", line 193, in
main()
File "./tools/train.py", line 182, in main
train_detector(
File "/root/mmrotate-dcfl/mmrotate/apis/train.py", line 141, in train_detector
runner.run(data_loaders, cfg.workflow)
File "/usr/local/lib/python3.8/dist-packages/mmcv/runner/epoch_based_runner.py", line 127, in run
epoch_runner(data_loaders[i], **kwargs)
File "/usr/local/lib/python3.8/dist-packages/mmcv/runner/epoch_based_runner.py", line 50, in train
self.run_iter(data_batch, train_mode=True, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/mmcv/runner/epoch_based_runner.py", line 29, in run_iter
outputs = self.model.train_step(data_batch, self.optimizer,
File "/usr/local/lib/python3.8/dist-packages/mmcv/parallel/distributed.py", line 59, in train_step
output = self.module.train_step(*inputs[0], **kwargs[0])
File "/root/mmrotate-dcfl/mmdet/models/detectors/base.py", line 248, in train_step
losses = self(**data)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/mmcv/runner/fp16_utils.py", line 110, in new_func
return old_func(*args, **kwargs)
File "/root/mmrotate-dcfl/mmdet/models/detectors/base.py", line 172, in forward
return self.forward_train(img, img_metas, **kwargs)
File "/root/mmrotate-dcfl/mmrotate/models/detectors/single_stage.py", line 81, in forward_train
losses = self.bbox_head.forward_train(x, img_metas, gt_bboxes,
File "/root/mmrotate-dcfl/mmdet/models/dense_heads/base_dense_head.py", line 335, in forward_train
losses = self.loss(*loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
File "/usr/local/lib/python3.8/dist-packages/mmcv/runner/fp16_utils.py", line 198, in new_func
return old_func(*args, **kwargs)
File "/root/mmrotate-dcfl/mmrotate/models/dense_heads/r_dcfl_head.py", line 301, in loss
cls_reg_targets = self.get_targets(
File "/root/mmrotate-dcfl/mmrotate/models/dense_heads/r_dcfl_head.py", line 579, in get_targets
results = multi_apply(
File "/root/mmrotate-dcfl/mmdet/core/utils/misc.py", line 30, in multi_apply
return tuple(map(list, zip(*map_results)))
File "/root/mmrotate-dcfl/mmrotate/models/dense_heads/r_dcfl_head.py", line 452, in _get_targets_single
labels = unmap(
File "/root/mmrotate-dcfl/mmdet/core/utils/misc.py", line 38, in unmap
ret[inds.type(torch.bool)] = data
RuntimeError: shape mismatch: value tensor of shape [8105] cannot be broadcast to indexing result of shape [5970]
Killing subprocess 12229