mmdetection/result/20240406_214846/vis_data/config.py

auto_scale_lr = dict(base_batch_size=32)
backend_args = None
data_root = '../../../media/tricolops/T7/Dataset/coco_format_bd/'
dataset_type = 'CocoDataset'
default_hooks = dict(
    checkpoint=dict(interval=10, type='CheckpointHook'),
    logger=dict(interval=50, type='LoggerHook'),
    param_scheduler=dict(type='ParamSchedulerHook'),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    timer=dict(type='IterTimerHook'),
    visualization=dict(type='DetVisualizationHook'))
default_scope = 'mmdet'
env_cfg = dict(
    cudnn_benchmark=False,
    dist_cfg=dict(backend='nccl'),
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
launcher = 'none'
load_from = 'work_dirs/deformable-detr_r50_16xb2-50e_coco/epoch_240.pth'
log_level = 'INFO'
log_processor = dict(by_epoch=True, type='LogProcessor', window_size=50)
max_epochs = 50
metainfo = dict(
    classes=('barcode', ), palette=[
        (
            220,
            20,
            60,
        ),
    ])
model = dict(
    as_two_stage=False,
    backbone=dict(
        depth=50,
        frozen_stages=1,
        init_cfg=dict(checkpoint='torchvision://resnet50', type='Pretrained'),
        norm_cfg=dict(requires_grad=False, type='BN'),
        norm_eval=True,
        num_stages=4,
        out_indices=(
            1,
            2,
            3,
        ),
        style='pytorch',
        type='ResNet'),
    bbox_head=dict(
        loss_bbox=dict(loss_weight=5.0, type='L1Loss'),
        loss_cls=dict(
            alpha=0.25,
            gamma=2.0,
            loss_weight=2.0,
            type='FocalLoss',
            use_sigmoid=True),
        loss_iou=dict(loss_weight=2.0, type='GIoULoss'),
        num_classes=1,
        sync_cls_avg_factor=True,
        type='DeformableDETRHead'),
    data_preprocessor=dict(
        bgr_to_rgb=True,
        mean=[
            123.675,
            116.28,
            103.53,
        ],
        pad_size_divisor=1,
        std=[
            58.395,
            57.12,
            57.375,
        ],
        type='DetDataPreprocessor'),
    decoder=dict(
        layer_cfg=dict(
            cross_attn_cfg=dict(batch_first=True, embed_dims=256),
            ffn_cfg=dict(
                embed_dims=256, feedforward_channels=1024, ffn_drop=0.1),
            self_attn_cfg=dict(
                batch_first=True, dropout=0.1, embed_dims=256, num_heads=8)),
        num_layers=6,
        post_norm_cfg=None,
        return_intermediate=True),
    encoder=dict(
        layer_cfg=dict(
            ffn_cfg=dict(
                embed_dims=256, feedforward_channels=1024, ffn_drop=0.1),
            self_attn_cfg=dict(batch_first=True, embed_dims=256)),
        num_layers=6),
    neck=dict(
        act_cfg=None,
        in_channels=[
            512,
            1024,
            2048,
        ],
        kernel_size=1,
        norm_cfg=dict(num_groups=32, type='GN'),
        num_outs=4,
        out_channels=256,
        type='ChannelMapper'),
    num_feature_levels=4,
    num_queries=300,
    positional_encoding=dict(normalize=True, num_feats=128, offset=-0.5),
    test_cfg=dict(max_per_img=100),
    train_cfg=dict(
        assigner=dict(
            match_costs=[
                dict(type='FocalLossCost', weight=2.0),
                dict(box_format='xywh', type='BBoxL1Cost', weight=5.0),
                dict(iou_mode='giou', type='IoUCost', weight=2.0),
            ],
            type='HungarianAssigner')),
    type='DeformableDETR',
    with_box_refine=False)
optim_wrapper = dict(
    clip_grad=dict(max_norm=0.1, norm_type=2),
    optimizer=dict(lr=0.0002, type='AdamW', weight_decay=0.0001),
    paramwise_cfg=dict(
        custom_keys=dict(
            backbone=dict(lr_mult=0.1),
            reference_points=dict(lr_mult=0.1),
            sampling_offsets=dict(lr_mult=0.1))),
    type='OptimWrapper')
param_scheduler = [
    dict(
        begin=0,
        by_epoch=True,
        end=50,
        gamma=0.1,
        milestones=[
            40,
        ],
        type='MultiStepLR'),
]
resume = False
test_cfg = dict(type='TestLoop')
test_dataloader = dict(
    batch_size=1,
    dataset=dict(
        ann_file='Val/Val.json',
        backend_args=None,
        data_prefix=dict(img='Val/'),
        data_root='../../../media/tricolops/T7/Dataset/coco_format_bd/',
        metainfo=dict(classes=('barcode', ), palette=[
            (
                220,
                20,
                60,
            ),
        ]),
        pipeline=[
            dict(backend_args=None, type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(
                640,
                640,
            ), type='Resize'),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(
                meta_keys=(
                    'img_id',
                    'img_path',
                    'ori_shape',
                    'img_shape',
                    'scale_factor',
                ),
                type='PackDetInputs'),
        ],
        test_mode=True,
        type='CocoDataset'),
    drop_last=False,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
test_evaluator = dict(
    ann_file='../../../media/tricolops/T7/Dataset/coco_format_bd/Val/Val.json',
    backend_args=None,
    format_only=False,
    metric='bbox',
    type='CocoMetric')
test_pipeline = [
    dict(backend_args=None, type='LoadImageFromFile'),
    dict(keep_ratio=True, scale=(
        640,
        640,
    ), type='Resize'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        meta_keys=(
            'img_id',
            'img_path',
            'ori_shape',
            'img_shape',
            'scale_factor',
        ),
        type='PackDetInputs'),
]
train_cfg = dict(max_epochs=250, type='EpochBasedTrainLoop', val_interval=10)
train_dataloader = dict(
    batch_sampler=dict(type='AspectRatioBatchSampler'),
    batch_size=4,
    dataset=dict(
        ann_file='Train/Train.json',
        backend_args=None,
        data_prefix=dict(img='Train/'),
        data_root='../../../media/tricolops/T7/Dataset/coco_format_bd/',
        filter_cfg=dict(filter_empty_gt=False, min_size=32),
        metainfo=dict(classes=('barcode', ), palette=[
            (
                220,
                20,
                60,
            ),
        ]),
        pipeline=[
            dict(backend_args=None, type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(prob=0.5, type='RandomFlip'),
            dict(
                keep_ratio=True,
                ratio_range=(
                    0.5,
                    2.0,
                ),
                scale=(
                    640,
                    640,
                ),
                type='RandomResize'),
            dict(crop_size=(
                640,
                640,
            ), type='RandomCrop'),
            dict(type='PackDetInputs'),
        ],
        type='CocoDataset'),
    num_workers=2,
    persistent_workers=True,
    sampler=dict(shuffle=True, type='DefaultSampler'))
train_pipeline = [
    dict(backend_args=None, type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(prob=0.5, type='RandomFlip'),
    dict(
        keep_ratio=True,
        ratio_range=(
            0.5,
            2.0,
        ),
        scale=(
            640,
            640,
        ),
        type='RandomResize'),
    dict(crop_size=(
        640,
        640,
    ), type='RandomCrop'),
    dict(type='PackDetInputs'),
]
val_cfg = dict(type='ValLoop')
val_dataloader = dict(
    batch_size=1,
    dataset=dict(
        ann_file='Val/Val.json',
        backend_args=None,
        data_prefix=dict(img='Val/'),
        data_root='../../../media/tricolops/T7/Dataset/coco_format_bd/',
        metainfo=dict(classes=('barcode', ), palette=[
            (
                220,
                20,
                60,
            ),
        ]),
        pipeline=[
            dict(backend_args=None, type='LoadImageFromFile'),
            dict(keep_ratio=True, scale=(
                640,
                640,
            ), type='Resize'),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(
                meta_keys=(
                    'img_id',
                    'img_path',
                    'ori_shape',
                    'img_shape',
                    'scale_factor',
                ),
                type='PackDetInputs'),
        ],
        test_mode=True,
        type='CocoDataset'),
    drop_last=False,
    num_workers=2,
    persistent_workers=True,
    sampler=dict(shuffle=False, type='DefaultSampler'))
val_evaluator = dict(
    ann_file='../../../media/tricolops/T7/Dataset/coco_format_bd/Val/Val.json',
    backend_args=None,
    format_only=False,
    metric='bbox',
    type='CocoMetric')
vis_backends = [
    dict(type='LocalVisBackend'),
]
visualizer = dict(
    name='visualizer',
    type='DetLocalVisualizer',
    vis_backends=[
        dict(type='LocalVisBackend'),
    ])
work_dir = 'result'