mmdetection 使用自定义数据集训练 将数据集转为COCO格式

1.mmdet的安装与配置

按照官网来就好

2. 将数据转为COCO格式

3. 编写config配置文件

我想使用centernet进行训练，编写如下config脚本
改动的内容有：num_class
此外还需要改动 mmdet/datasets/coco.py

# -*- coding: utf-8 -*-
"""
Created on Thu Nov 18 11:57:13 2021

@author: sxj96
"""

_base_ = [
    '../_base_/datasets/coco_detection.py',
    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]

model = dict(
    type='CenterNet',
    backbone=dict(
        type='ResNet',
        depth=18,
        norm_eval=False,
        norm_cfg=dict(type='BN'),
        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet18')),
    neck=dict(
        type='CTResNetNeck',
        in_channel=512,
        num_deconv_filters=(256, 128, 64),
        num_deconv_kernels=(4, 4, 4),
        use_dcn=True),
    bbox_head=dict(
        type='CenterNetHead',
        #num_classes=80,
        num_classes=1,
        in_channel=64,
        feat_channel=64,
        loss_center_heatmap=dict(type='GaussianFocalLoss', loss_weight=1.0),
        loss_wh=dict(type='L1Loss', loss_weight=0.1),
        loss_offset=dict(type='L1Loss', loss_weight=1.0)),
    train_cfg=None,
    test_cfg=dict(topk=100, local_maximum_kernel=3, max_per_img=100))

# We fixed the incorrect img_norm_cfg problem in the source code.
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', to_float32=True, color_type='color'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='PhotoMetricDistortion',
        brightness_delta=32,
        contrast_range=(0.5, 1.5),
        saturation_range=(0.5, 1.5),
        hue_delta=18),
    dict(
        type='RandomCenterCropPad',
        crop_size=(512, 512),
        ratios=(0.6, 0.7, 0.8, 0.9, 1.0, 1.1, 1.2, 1.3),
        mean=[0, 0, 0],
        std=[1, 1, 1],
        to_rgb=True,
        test_pad_mode=None),
    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='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile', to_float32=True),
    dict(
        type='MultiScaleFlipAug',
        scale_factor=1.0,
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(
                type='RandomCenterCropPad',
                ratios=None,
                border=None,
                mean=[0, 0, 0],
                std=[1, 1, 1],
                to_rgb=True,
                test_mode=True,
                test_pad_mode=['logical_or', 31],
                test_pad_add_pix=1),
            dict(type='RandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='DefaultFormatBundle'),
            dict(
                type='Collect',
                meta_keys=('filename', 'ori_shape', 'img_shape', 'pad_shape',
                           'scale_factor', 'flip', 'flip_direction',
                           'img_norm_cfg', 'border'),
                keys=['img'])
        ])
]

dataset_type = 'CocoDataset'
data_root = 'data/Deptrum/'


# Use RepeatDataset to speed up training
data = dict(
    samples_per_gpu=16,
    workers_per_gpu=4,
    #train=dict(
        #_delete_=True,
        #type='RepeatDataset',
        #times=5,
        #dataset=dict(
            #type=dataset_type,
            #ann_file=data_root + 'annotations/instances_train2017.json',
            #img_prefix=data_root + 'train2017/',
            #pipeline=train_pipeline)),
    train=dict(
            type=dataset_type,
            ann_file=data_root + 'annotations/instances_train2017.json',
            img_prefix=data_root + 'train2017/',
            pipeline=train_pipeline),
    #val=dict(pipeline=test_pipeline),
    val=dict(
        ann_file=data_root + 'annotations/instances_test2017.json',
        img_prefix=data_root + 'val2017/',
        pipeline=test_pipeline),
        
        #_delete_=True,
        #type='RepeatDataset',
        #times=5,
        #dataset=dict(
            #type=dataset_type,
            #ann_file=data_root + 'annotations/instances_test2017.json',
            #img_prefix=data_root + 'val2017/',
            #pipeline=test_pipeline)),

    test=dict(
            img_prefix=data_root + 'test2017/',
            ann_file=data_root + 'annotations/instances_test2017.json',
            pipeline=test_pipeline))
            
            
# optimizer
# Based on the default settings of modern detectors, the SGD effect is better
# than the Adam in the source code, so we use SGD default settings and
# if you use adam+lr5e-4, the map is 29.1.
optimizer_config = dict(
    _delete_=True, grad_clip=dict(max_norm=35, norm_type=2))

# learning policy
# Based on the default settings of modern detectors, we added warmup settings.
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=1000,
    warmup_ratio=1.0 / 1000,
    step=[18, 24])  # the real step is [18*5, 24*5]
runner = dict(max_epochs=28)  # the real epoch is 28*5=140

报了一个错：

AssertionError: The `num_classes` (1) in CenterNetHead of MMDataParallel doe

网上给出的解决方案：
① 重新编译 python setup.py install
② 如果继续报同样的错，则把源码也给改了
源码地址：
\anaconda3\envs\conda_env_name\lib\python3.7\site-packages\mmdet\core\evaluation\class_names.py

\anaconda3\envs\conda_env_name\lib\python3.7\site-packages\mmdet\datasets\coco.py

AssertionError: `CLASSES` in CocoDatasetshould be a tuple of str.Add comma if number of classes is 1 as CLASSES = (hand,)

报错原因，COCO。py里面的CLASSES需要写成元组形式。因为我的数据集中只有一个类别所以我之前写为了 CLASSES=（‘hand’）应该改为CLASSES=（‘hand’,）