inference/centernet_config.py

dataset_type = 'CocoDataset'
data_root = '/home/safouane/Downloads/benchmark_aircraft/data/' # dataset root
backend_args = None

max_epochs = 500 

metainfo = {
    'classes': ('airplane', ),
    'palette': [
        (0, 128, 255),
    ]
}
num_classes = 1        

train_pipeline = [
    dict(type='LoadImageFromFile', backend_args=None),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='RandomChoiceResize',
        scales=[
            ( 1333, 640, ),
            ( 1333, 672, ),
            ( 1333, 704, ),
            ( 1333, 736, ),
            ( 1333, 768, ),
            ( 1333, 800, ),
        ],
        keep_ratio=True),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PackDetInputs'),
]
test_pipeline = [
    dict(type='LoadImageFromFile', backend_args=None),
    dict(type='Resize', scale=(
        1333,
        800,
    ), keep_ratio=True),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='PackDetInputs',
        meta_keys=(
            'img_id',
            'img_path',
            'ori_shape',
            'img_shape',
            'scale_factor',
        )),
]
train_dataloader = dict(
    batch_size=32,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    batch_sampler=dict(type='AspectRatioBatchSampler'),
    dataset=dict(
        type='CocoDataset',
        metainfo=metainfo,
        data_root=data_root,
        ann_file='train/__coco.json',
        data_prefix=dict(img='train/'),
        filter_cfg=dict(filter_empty_gt=True, min_size=32),
        pipeline=[
            dict(type='LoadImageFromFile', backend_args=None),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(
                type='RandomChoiceResize',
                scales=[
                    ( 1333, 640, ),
                    ( 1333, 672, ),
                    ( 1333, 704, ),
                    ( 1333, 736, ),
                    ( 1333, 768, ),
                    ( 1333, 800, ),
                ],
                keep_ratio=True),
            dict(type='RandomFlip', prob=0.5),
            dict(type='PackDetInputs'),
        ],
        backend_args=None))
val_dataloader = dict(
    batch_size=32,
    num_workers=2,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type='CocoDataset',
        metainfo=metainfo,
        data_root=data_root,
        ann_file='val/__coco.json',
        data_prefix=dict(img='val/'),
        test_mode=True,
        pipeline=[
            dict(type='LoadImageFromFile', backend_args=None),
            dict(type='Resize', scale=(
                1333,
                800,
            ), keep_ratio=True),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(
                type='PackDetInputs',
                meta_keys=(
                    'img_id',
                    'img_path',
                    'ori_shape',
                    'img_shape',
                    'scale_factor',
                )),
        ],
        backend_args=None))
test_dataloader = dict(
    batch_size=32,
    num_workers=2,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type='CocoDataset',
        metainfo=metainfo,
        data_root=data_root,
        ann_file='test/__coco.json',
        data_prefix=dict(img='test/'),
        test_mode=True,
        pipeline=[
            dict(type='LoadImageFromFile', backend_args=None),
            dict(type='Resize', scale=(
                1333,
                800,
            ), keep_ratio=True),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(
                type='PackDetInputs',
                meta_keys=(
                    'img_id',
                    'img_path',
                    'ori_shape',
                    'img_shape',
                    'scale_factor',
                )),
        ],
        backend_args=None))
val_evaluator = dict(
    type='CocoMetric',
    ann_file=data_root + 'val/__coco.json',
    metric='bbox',
    format_only=False,
    backend_args=None)
test_evaluator = dict(
    type='CocoMetric',
    ann_file=data_root + 'test/__coco.json',
    metric='bbox',
    format_only=False,
    backend_args=None)

train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=max_epochs, val_interval=10)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
param_scheduler = [
    dict(
        type='LinearLR',
        start_factor=0.00025,
        by_epoch=False,
        begin=0,
        end=4000),
    dict(
        type='MultiStepLR',
        begin=0,
        end=12,
        by_epoch=True,
        milestones=[
            8,
            11,
        ],
        gamma=0.1),
]
optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=dict(type='SGD', lr=0.015, momentum=0.9, weight_decay=0.0001),
    paramwise_cfg=dict(norm_decay_mult=0.0))
auto_scale_lr = dict(enable=False, base_batch_size=32)
default_scope = 'mmdet'
default_hooks = dict(
    timer=dict(type='IterTimerHook'),
    logger=dict(type='LoggerHook', interval=5),
    param_scheduler=dict(type='ParamSchedulerHook'),
    checkpoint=dict(
        type='CheckpointHook',
        interval=5,
        max_keep_ckpts=2,  # only keep latest 2 checkpoints
        save_best='auto'
    ),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    visualization=dict(type='DetVisualizationHook'))
env_cfg = dict(
    cudnn_benchmark=False,
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    dist_cfg=dict(backend='nccl'))
vis_backends = [
    dict(type='LocalVisBackend'),
]
visualizer = dict(
    type='DetLocalVisualizer',
    vis_backends=[
        dict(type='LocalVisBackend'),
        dict(type='TensorboardVisBackend'),
    ],
    name='visualizer')

log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
log_level = 'INFO'
load_from = None
resume = False
model = dict(
    type='CenterNet',
    data_preprocessor=dict(
        type='DetDataPreprocessor',
        mean=[
            103.53,
            116.28,
            123.675,
        ],
        std=[
            1.0,
            1.0,
            1.0,
        ],
        bgr_to_rgb=False,
        pad_size_divisor=32),
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(
            0,
            1,
            2,
            3,
        ),
        frozen_stages=1,
        norm_cfg=dict(type='BN', requires_grad=False),
        norm_eval=True,
        style='caffe',
        init_cfg=dict(
            type='Pretrained',
            checkpoint='open-mmlab://detectron2/resnet50_caffe')),
    neck=dict(
        type='FPN',
        in_channels=[
            256,
            512,
            1024,
            2048,
        ],
        out_channels=256,
        start_level=1,
        add_extra_convs='on_output',
        num_outs=5,
        init_cfg=dict(type='Caffe2Xavier', layer='Conv2d'),
        relu_before_extra_convs=True),
    bbox_head=dict(
        type='CenterNetUpdateHead',
        num_classes=num_classes,
        in_channels=256,
        stacked_convs=4,
        feat_channels=256,
        strides=[
            8,
            16,
            32,
            64,
            128,
        ],
        hm_min_radius=4,
        hm_min_overlap=0.8,
        more_pos_thresh=0.2,
        more_pos_topk=9,
        soft_weight_on_reg=False,
        loss_cls=dict(
            type='GaussianFocalLoss',
            pos_weight=0.25,
            neg_weight=0.75,
            loss_weight=1.0),
        loss_bbox=dict(type='GIoULoss', loss_weight=2.0)),
    train_cfg=None,
    test_cfg=dict(
        nms_pre=1000,
        min_bbox_size=0,
        score_thr=0.05,
        nms=dict(type='nms', iou_threshold=0.6),
        max_per_img=100))