work_dirs/yolo3/yolov3_d53_mstrain-608_273e_coco.py

_base_ = '../_base_/default_runtime.py'
# model settings
model = dict(
    type='YOLOV3',
    backbone=dict(
        type='Darknet',
        depth=53,
        out_indices=(3, 4, 5),
        init_cfg=dict(type='Pretrained', checkpoint='open-mmlab://darknet53')),
    neck=dict(
        type='YOLOV3Neck',
        num_scales=3,
        in_channels=[1024, 512, 256],
        out_channels=[512, 256, 128]),
    bbox_head=dict(
        type='YOLOV3Head',
        num_classes=14,
        in_channels=[512, 256, 128],
        out_channels=[1024, 512, 256],
        anchor_generator=dict(
            type='YOLOAnchorGenerator',
            base_sizes=[[(116, 90), (156, 198), (373, 326)],
                        [(30, 61), (62, 45), (59, 119)],
                        [(10, 13), (16, 30), (33, 23)]],
            strides=[32, 16, 8]),
        bbox_coder=dict(type='YOLOBBoxCoder'),
        featmap_strides=[32, 16, 8],
        loss_cls=dict(
            type='CrossEntropyLoss',
            use_sigmoid=True,
            loss_weight=1.0,
            reduction='sum'),
        loss_conf=dict(
            type='CrossEntropyLoss',
            use_sigmoid=True,
            loss_weight=1.0,
            reduction='sum'),
        loss_xy=dict(
            type='CrossEntropyLoss',
            use_sigmoid=True,
            loss_weight=2.0,
            reduction='sum'),
        loss_wh=dict(type='MSELoss', loss_weight=2.0, reduction='sum')),
    # training and testing settings
    train_cfg=dict(
        assigner=dict(
            type='GridAssigner',
            pos_iou_thr=0.5,
            neg_iou_thr=0.5,
            min_pos_iou=0)),
    test_cfg=dict(
        nms_pre=1000,
        min_bbox_size=0,
        score_thr=0.05,
        conf_thr=0.005,
        nms=dict(type='nms', iou_threshold=0.45),
        max_per_img=100))
# dataset settings
data_root = './'
work_dir = './result/yolov3'
load_from = 'result/yolov3/latest.pth'
resume_from = 'result/yolov3/latest.pth'
img_norm_cfg = dict(mean=[0, 0, 0], std=[255., 255., 255.], to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile', to_float32=True),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='Expand',
        mean=img_norm_cfg['mean'],
        to_rgb=img_norm_cfg['to_rgb'],
        ratio_range=(1, 2)),
    dict(
        type='MinIoURandomCrop',
        min_ious=(0.4, 0.5, 0.6, 0.7, 0.8, 0.9),
        min_crop_size=0.3),
    dict(type='Resize', img_scale=[(320, 320), (608, 608)], keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='PhotoMetricDistortion'),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(608, 608),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]
classes = ('person bev', 'car bev', 'van bev', 'bus bev', 'truck bev','aeroplane','train' , 'bird', 'boat', 'car', 'person', 'bus', 'truck','camouflage man')

data = dict(
    samples_per_gpu=8,
    workers_per_gpu=4,
    train=dict(

        classes=classes,
        ann_file='./final_train_dataset/label/train_final_with_js.json',
        img_prefix='./final_train_dataset/images',
        pipeline=train_pipeline),
    val=dict(

        classes=classes,
        ann_file='./final_train_dataset/label/val_final_with_js.json',
        img_prefix='./final_train_dataset/images',

        pipeline=test_pipeline),
    test=dict(

        classes=classes,
        ann_file='./final_train_dataset/label/val_final_with_js.json',
        img_prefix='./final_train_dataset/images',

        pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0005)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=2000,  # same as burn-in in darknet
    warmup_ratio=0.1,
    step=[218, 246])
# runtime settings
# checkpoint resumed from 273
runner = dict(type='EpochBasedRunner', max_epochs=300)
evaluation = dict(interval=10, metric=['bbox'])

log_config = dict(interval=100)
checkpoint_config = dict(interval=10)

seed = 0
gpu_ids = range(1)