我仿照DOTA的配置文件写了一个MyDataset类，并只把
CLASSES = ('plane', 'baseball-diamond', 'bridge', 'ground-track-field', 'small-vehicle', 'large-vehicle', 'ship', 'tennis-court', 'basketball-court', 'storage-tank', 'soccer-ball-field', 'roundabout', 'harbor', 'swimming-pool', 'helicopter')
改为了：
CLASSES = 'ship'
以下为运行后自动生成的代码
data_root = '/content/drive/MyDrive/HRSC2016/'
img_norm_cfg = dict(
mean=[70.954, 81.526, 78.456], std=[58.371, 57.745, 50.858], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RResize', img_scale=(512, 512)),
dict(type='RRandomFlip', flip_ratio=0.5),
dict(
type='Normalize',
mean=[70.954, 81.526, 78.456],
std=[58.371, 57.745, 50.858],
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=(512, 512),
flip=False,
transforms=[
dict(type='RResize'),
dict(
type='Normalize',
mean=[70.954, 81.526, 78.456],
std=[58.371, 57.745, 50.858],
to_rgb=True),
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='MyDataset',
ann_file='/content/drive/MyDrive/HRSC2016/Train/labelTxt/',
img_prefix='/content/drive/MyDrive/HRSC2016/Train/AllImages/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RResize', img_scale=(512, 512)),
dict(type='RRandomFlip', flip_ratio=0.5),
dict(
type='Normalize',
mean=[70.954, 81.526, 78.456],
std=[58.371, 57.745, 50.858],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]),
val=dict(
type='MyDataset',
ann_file='/content/drive/MyDrive/HRSC2016/Test/labelTxt/',
img_prefix='/content/drive/MyDrive/HRSC2016/Test/AllImages/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(512, 512),
flip=False,
transforms=[
dict(type='RResize'),
dict(
type='Normalize',
mean=[70.954, 81.526, 78.456],
std=[58.371, 57.745, 50.858],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
]),
test=dict(
type='MyDataset',
ann_file='/content/drive/MyDrive/HRSC2016/Test/Annotations/',
img_prefix='/content/drive/MyDrive/HRSC2016/Test/AllImages/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(512, 512),
flip=False,
transforms=[
dict(type='RResize'),
dict(
type='Normalize',
mean=[70.954, 81.526, 78.456],
std=[58.371, 57.745, 50.858],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
]))
evaluation = dict(interval=12, 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=12)
checkpoint_config = dict(interval=12)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
model = dict(
type='R3Det',
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='RRetinaHead',
num_classes=15,
in_channels=256,
stacked_convs=4,
feat_channels=256,
anchor_generator=dict(
type='RAnchorGenerator',
octave_base_scale=4,
scales_per_octave=3,
ratios=[1.0, 0.5, 2.0],
strides=[8, 16, 32, 64, 128]),
bbox_coder=dict(
type='DeltaXYWHAOBBoxCoder',
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),
loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)),
frm_cfgs=[dict(in_channels=256, featmap_strides=[8, 16, 32, 64, 128])],
num_refine_stages=1,
refine_heads=[
dict(
type='RRetinaRefineHead',
num_classes=15,
in_channels=256,
stacked_convs=4,
feat_channels=256,
assign_by_circumhbbox=None,
anchor_generator=dict(
type='PseudoAnchorGenerator', strides=[8, 16, 32, 64, 128]),
bbox_coder=dict(
type='DeltaXYWHAOBBoxCoder',
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),
loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0))
],
train_cfg=dict(
s0=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1,
iou_calculator=dict(type='RBboxOverlaps2D_v1')),
allowed_border=-1,
pos_weight=-1,
debug=False),
sr=[
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.5,
min_pos_iou=0,
ignore_iof_thr=-1,
iou_calculator=dict(type='RBboxOverlaps2D_v1')),
allowed_border=-1,
pos_weight=-1,
debug=False)
],
stage_loss_weights=[1.0]),
test_cfg=dict(
nms_pre=2000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(iou_thr=0.1),
max_per_img=2000))
work_dir = './work_dirs/r3det_r50_fpn_1x_dota_v1'
gpu_ids = range(0, 1)```
以下为报错：
2022-03-19 09:44:59,167 - mmdet - INFO - initialize ResNet with init_cfg {'type': 'Pretrained', 'checkpoint': 'torchvision://resnet50'}
2022-03-19 09:44:59,168 - mmcv - INFO - load model from: torchvision://resnet50
2022-03-19 09:44:59,168 - mmcv - INFO - load checkpoint from torchvision path: torchvision://resnet50
2022-03-19 09:44:59,410 - mmcv - WARNING - The model and loaded state dict do not match exactly
unexpected key in source state_dict: fc.weight, fc.bias
2022-03-19 09:44:59,444 - mmdet - INFO - initialize FPN with init_cfg {'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'}
Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 52, in build_from_cfg
return obj_cls(**args)
File "/content/drive/MyDrive/Colab/r3det-pytorch-main/r3det/datasets/mydataset1.py", line 47, in init
super(MyDataset, self).init(ann_file, pipeline, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/mmdet/datasets/custom.py", line 95, in init
self.data_infos = self.load_annotations(local_path)
File "/content/drive/MyDrive/Colab/r3det-pytorch-main/r3det/datasets/mydataset1.py", line 102, in load_annotations
label = cls_map[cls_name]
KeyError: 'ship'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "./tools/train.py", line 193, in
main()
File "./tools/train.py", line 169, in main
datasets = [build_dataset(cfg.data.train)]
File "/usr/local/lib/python3.7/dist-packages/mmdet/datasets/builder.py", line 81, in build_dataset
dataset = build_from_cfg(cfg, DATASETS, default_args)
File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 55, in build_from_cfg
raise type(e)(f'{obj_cls.name}: {e}')
KeyError: "MyDataset: 'ship'"
目前推测是单类训练导致的问题，因为CSDN上也有人反映：
想知道大佬有没有解决这个问题的思路呢？
32 Nov 25, 2022
139 Jan 1, 2023
62 Dec 24, 2022
52 Nov 30, 2022
7 Sep 26, 2022
13 Nov 4, 2022
2 Feb 15, 2022
3 Mar 11, 2022
6.3k Dec 30, 2022
40 Sep 14, 2022
57 Nov 17, 2022
16 Jan 16, 2022
1.3k Nov 17, 2022
49 Nov 23, 2022
50 Dec 3, 2022
185 Dec 26, 2022
336 Nov 25, 2022
43 Nov 19, 2022
444 Dec 30, 2022