retinanet_pvt_s_fpn_1x_coco_640.py

_base_ = [
    '_base_/models/retinanet_r50_fpn.py',
    '_base_/default_runtime.py',
    '_base_/schedules/schedule_1x.py',
]
model = dict(
    # pretrained='pretrained/pvt_small.pth',
    pretrained='https://github.com/whai362/PVT/releases/download/v2/pvt_small.pth',
    backbone=dict(
        type='pvt_small',
        style='pytorch'),
    neck=dict(
        type='FPN',
        in_channels=[64, 128, 320, 512],
        out_channels=256,
        start_level=1,
        add_extra_convs='on_input',
        num_outs=5))
# optimizer
optimizer = dict(_delete_=True, type='AdamW', lr=0.0001, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# dataset
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
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'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='Resize', img_scale=(1066, 640), keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    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='MultiScaleFlipAug',
        img_scale=(1066, 640),
        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']),
        ])
]
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_train2017.json',
        img_prefix=data_root + 'train2017/',
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json',
        img_prefix=data_root + 'val2017/',
        pipeline=test_pipeline),
    test=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json',
        img_prefix=data_root + 'val2017/',
        pipeline=test_pipeline))
evaluation = dict(interval=1, metric='bbox')