How to change the length of CLASSES in RepeatDataset?

[wonbul2022]

I am trying to transform COCO dataset to VOC and running in on mmdetection.

I meet this error:

AssertionError: The num_classes (80) in SSDHead of MMDataParallel does not matches the length of CLASSES 20) in RepeatDataset

How to fix it?

[ZwwWayne]

You can set it through config by set the metainfo=dict(CLASSES=()))

[wonbul2022]

Here is the config, where should I add it?
Thank you.

base = 'ssd300_voc.py'
input_size = 512
model = dict(
neck=dict(
out_channels=(512, 1024, 512, 256, 256, 256, 256),
level_strides=(2, 2, 2, 2, 1),
level_paddings=(1, 1, 1, 1, 1),
last_kernel_size=4),
bbox_head=dict(
in_channels=(512, 1024, 512, 256, 256, 256, 256),
anchor_generator=dict(
type='SSDAnchorGenerator',
scale_major=False,
input_size=input_size,
basesize_ratio_range=(0.1, 0.9),
strides=[8, 16, 32, 64, 128, 256, 512],
ratios=[[2], [2, 3], [2, 3], [2, 3], [2, 3], [2], [2]])))
#dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Expand',
mean=img_norm_cfg['mean'],
to_rgb=img_norm_cfg['to_rgb'],
ratio_range=(1, 4)),
dict(
type='MinIoURandomCrop',
min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
min_crop_size=0.3),
dict(type='Resize', img_scale=(512, 512), keep_ratio=False),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='PhotoMetricDistortion',
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
dict(type='Normalize', **img_norm_cfg),
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='Resize', keep_ratio=False),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=8,
workers_per_gpu=3,
train=dict(
delete=True,
type='RepeatDataset',
times=5,
dataset=dict(
type=dataset_type,
ann_file=data_root + 'VOC2007/ImageSets/Main/train.txt', #'annotations/instances_train2017.json',
img_prefix=data_root + 'VOC2007/', #data_root + 'train2017/',
pipeline=train_pipeline)),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))

optimizer = dict(type='SGD', lr=2e-3, momentum=0.9, weight_decay=5e-4)
optimizer_config = dict(delete=True)
custom_hooks = [
dict(type='NumClassCheckHook'),
dict(type='CheckInvalidLossHook', interval=50, priority='VERY_LOW')
]

auto_scale_lr = dict(base_batch_size=64)