inference/retinanet_config.py

dataset_type = 'CocoDataset'
data_root = '/home/safouane/Downloads/benchmark_aircraft/data/'
backend_args = None
max_epochs = 500
metainfo = {
    'classes': ('airplane', ),
    'palette': [
        (0, 128, 255),
    ]
}
num_classes = 1
model = dict(
    type='RetinaNet',
    data_preprocessor=dict(
        type='DetDataPreprocessor',
        mean=[
            123.675,
            116.28,
            103.53,
        ],
        std=[
            58.395,
            57.12,
            57.375,
        ],
        bgr_to_rgb=True,
        pad_size_divisor=64,
        batch_augments=[
            dict(type='BatchFixedSizePad', size=(
                640,
                640,
            )),
        ]),
    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=True),
        norm_eval=False,
        style='pytorch',
        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
    neck=dict(
        type='FPN',
        in_channels=[
            256,
            512,
            1024,
            2048,
        ],
        out_channels=256,
        start_level=1,
        add_extra_convs='on_input',
        num_outs=5,
        relu_before_extra_convs=True,
        no_norm_on_lateral=True,
        norm_cfg=dict(type='BN', requires_grad=True)),
    bbox_head=dict(
        type='RetinaSepBNHead',
        num_classes=1,
        in_channels=256,
        stacked_convs=4,
        feat_channels=256,
        anchor_generator=dict(
            type='AnchorGenerator',
            octave_base_scale=4,
            scales_per_octave=3,
            ratios=[
                0.5,
                1.0,
                2.0,
            ],
            strides=[
                8,
                16,
                32,
                64,
                128,
            ]),
        bbox_coder=dict(
            type='DeltaXYWHBBoxCoder',
            target_means=[
                0.0,
                0.0,
                0.0,
                0.0,
            ],
            target_stds=[
                1.0,
                1.0,
                1.0,
                1.0,
            ]),
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(type='L1Loss', loss_weight=1.0),
        num_ins=5,
        norm_cfg=dict(type='BN', requires_grad=True)),
    train_cfg=dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.5,
            neg_iou_thr=0.5,
            min_pos_iou=0,
            ignore_iof_thr=-1),
        sampler=dict(type='PseudoSampler'),
        allowed_border=-1,
        pos_weight=-1,
        debug=False),
    test_cfg=dict(
        nms_pre=1000,
        min_bbox_size=0,
        score_thr=0.05,
        nms=dict(type='nms', iou_threshold=0.5),
        max_per_img=100))
train_pipeline = [
    dict(type='LoadImageFromFile', backend_args=None),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='RandomResize',
        scale=(
            640,
            640,
        ),
        ratio_range=(
            0.8,
            1.2,
        ),
        keep_ratio=True),
    dict(type='RandomCrop', crop_size=(
        640,
        640,
    )),
    dict(type='RandomFlip', prob=0.5),
    dict(type='PackDetInputs'),
]
test_pipeline = [
    dict(type='LoadImageFromFile', backend_args=None),
    dict(type='Resize', scale=(
        640,
        640,
    ), 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=dict(classes=('airplane', ), palette=[
            (
                220,
                20,
                60,
            ),
        ]),
        data_root='/home/safouane/Downloads/benchmark_aircraft/data/',
        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='RandomResize',
                scale=(
                    640,
                    640,
                ),
                ratio_range=(
                    0.8,
                    1.2,
                ),
                keep_ratio=True),
            dict(type='RandomCrop', crop_size=(
                640,
                640,
            )),
            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=dict(classes=('airplane', ), palette=[
            (
                220,
                20,
                60,
            ),
        ]),
        data_root='/home/safouane/Downloads/benchmark_aircraft/data/',
        ann_file='val/__coco.json',
        data_prefix=dict(img='val/'),
        test_mode=True,
        pipeline=[
            dict(type='LoadImageFromFile', backend_args=None),
            dict(type='Resize', scale=(
                640,
                640,
            ), 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=1,
    num_workers=2,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type='CocoDataset',
        metainfo=dict(classes=('airplane', ), palette=[
            (
                220,
                20,
                60,
            ),
        ]),
        data_root='/home/safouane/Downloads/benchmark_aircraft/data/',
        ann_file='test/__coco.json',
        data_prefix=dict(img='test/'),
        test_mode=True,
        pipeline=[
            dict(type='LoadImageFromFile', backend_args=None),
            dict(type='Resize', scale=(
                640,
                640,
            ), 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='/home/safouane/Downloads/benchmark_aircraft/data/val/__coco.json',
    metric='bbox',
    format_only=False,
    backend_args=None)
test_evaluator = dict(
    type='CocoMetric',
    ann_file=
    '/home/safouane/Downloads/benchmark_aircraft/data/test/__coco.json',
    metric='bbox',
    format_only=False,
    backend_args=None)
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=500, val_interval=10)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
param_scheduler = [
    dict(type='LinearLR', start_factor=0.1, by_epoch=False, begin=0, end=1000),
    dict(
        type='MultiStepLR',
        begin=0,
        end=50,
        by_epoch=True,
        milestones=[
            30,
            40,
        ],
        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, bypass_duplicate=True))
auto_scale_lr = dict(enable=False, base_batch_size=64)
default_scope = 'mmdet'
default_hooks = dict(
    timer=dict(type='IterTimerHook'),
    logger=dict(type='LoggerHook', interval=50),
    param_scheduler=dict(type='ParamSchedulerHook'),
    checkpoint=dict(
        type='CheckpointHook', interval=20, max_keep_ckpts=2,
        save_best='auto'),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    visualization=dict(type='DetVisualizationHook'))
env_cfg = dict(
    cudnn_benchmark=True,
    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 = '/home/safouane/Downloads/benchmark_aircraft/mmlab_configs/retinanet_r50_fpn_crop640_50e_coco-9b953d76.pth'
resume = False
norm_cfg = dict(type='BN', requires_grad=True)
launcher = 'none'
work_dir = './work_dirs/retinanet_r50_fpn_crop640-50e_coco'