ValueError: need at least one array to stack

[PanYang]

当我更换了自己定义的一个数据集时，出现了上述bug，以下是我的参数，
2022-03-02 22:06:41,743 - mmdet - INFO - Distributed training: False
2022-03-02 22:06:41,744 - mmdet - INFO - MMDetection Version: 1.0.0+unknown
2022-03-02 22:06:41,744 - mmdet - INFO - Config:

model settings

model = dict(
type='SOLO',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
in_channels=4,
num_stages=4,
out_indices=(0, 1, 2, 3), # C2, C3, C4, C5
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=0,
num_outs=5),
bbox_head=dict(
type='SOLOHead',
num_classes=2,
in_channels=256,
stacked_convs=7,
seg_feat_channels=256,
strides=[8, 8, 16, 32, 32],
scale_ranges=((1, 96), (48, 192), (96, 384), (192, 768), (384, 2048)),
sigma=0.2,
num_grids=[40, 36, 24, 16, 12],
cate_down_pos=0,
with_deform=False,
loss_ins=dict(
type='DiceLoss',
use_sigmoid=True,
loss_weight=3.0),
loss_cate=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
))

training and testing settings

train_cfg = dict()
test_cfg = dict(
nms_pre=500,
score_thr=0.1,
mask_thr=0.5,
update_thr=0.05,
kernel='gaussian', # gaussian/linear
sigma=2.0,
max_per_img=100)

dataset settings

dataset_type = 'CocoDataset'
classes = ('cropland_parcel',)
data_root = '/home/py21/data_py/San_joaquin_2014_NAIP/'
img_norm_cfg = dict(
mean=[125.9752,125.6327,101.7500,138.4956], std=[45.8814,38.8707,38.4250,43.5888],to_rgb=False)
train_pipeline = [
dict(type='LoadRSImage',to_float32=True),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(512, 512), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadRSImage', to_float32=True),
dict(
type='MultiScaleFlipAug',
img_scale=(512, 512),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
imgs_per_gpu=8,
workers_per_gpu=0,
train=dict(
type=dataset_type,
ann_file=data_root + 'San_joaquin_2014_NAIP_train.json',
img_prefix=data_root + 'train_coco/',
pipeline = train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'San_joaquin_2014_NAIP_valid.json',
img_prefix=data_root + 'valid_coco/',
pipeline=test_pipeline),
test=dict(
type = dataset_type,
ann_file=data_root + 'San_joaquin_2014_NAIP_valid.json',
img_prefix=data_root + 'valid_coco/',
pipeline = test_pipeline),
)

optimizer

optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

evaluation = dict(interval=1,save_best='segm_mAP',

metric=['bbox', 'segm'])

learning policy

lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.001,
step=[32, 44])
checkpoint_config = dict(interval=1)

yapf:disable

log_config = dict(
interval=50,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])

yapf:enable

runtime settings

total_epochs = 50
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './parcel_NAIP/solo_release_r50_fpn_50epoch'
load_from = None
resume_from = None
workflow = [('train', 1)]
filter_empty_gt = True
2022-03-02 22:06:42,553 - mmdet - INFO - load model from: torchvision://resnet50
2022-03-02 22:06:43,129 - mmdet - WARNING - The model and loaded state dict do not match exactly

size mismatch for conv1.weight: copying a param with shape torch.Size([64, 3, 7, 7]) from checkpoint, the shape in current model is torch.Size([64, 4, 7, 7]).
unexpected key in source state_dict: fc.weight, fc.bias

2022-03-02 22:06:50,715 - mmdet - INFO - Start running, host: py21@gpu3, work_dir: /home/py21/SOLO-master/parcel_NAIP/solo_release_r50_fpn_50epoch
2022-03-02 22:06:50,715 - mmdet - INFO - workflow: [('train', 1)], max: 50 epochs
2022-03-02 22:11:43,107 - mmdet - INFO - Epoch [1][50/307] lr: 0.00099, eta: 1 day, 0:51:08, time: 5.848, data_time: 1.795, memory: 8342, loss_ins: 2.9401, loss_cate: 0.5971, loss: 3.5373
2022-03-02 22:16:05,093 - mmdet - INFO - Epoch [1][100/307] lr: 0.00199, eta: 23:29:00, time: 5.240, data_time: 1.742, memory: 8347, loss_ins: 2.9399, loss_cate: 0.4326, loss: 3.3725

File "/home/py21/SOLO-master/mmdet/datasets/custom.py", line 131, in getitem
data = self.prepare_train_img(idx)
File "/home/py21/SOLO-master/mmdet/datasets/custom.py", line 144, in prepare_train_img
return self.pipeline(results)
File "/home/py21/SOLO-master/mmdet/datasets/pipelines/compose.py", line 24, in call
data = t(data)
File "/home/py21/SOLO-master/mmdet/datasets/pipelines/transforms.py", line 176, in call
self._resize_masks(results)
File "/home/py21/SOLO-master/mmdet/datasets/pipelines/transforms.py", line 159, in _resize_masks
results[key] = np.stack(masks)
File "<array_function internals>", line 6, in stack
File "/home/py21/anaconda3/envs/solo/lib/python3.7/site-packages/numpy/core/shape_base.py", line 423, in stack
raise ValueError('need at least one array to stack')
ValueError: need at least one array to stack

请问是什么具体问题呢？