tevit_swin-l_mstrain.py

_base_ = './tevit_r50.py'

pretrained = 'https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_large_patch4_window7_224_22kto1k-5f0996db.pth'  # noqa

num_proposals = 300
model = dict(
    backbone=dict(
        _delete_=True,
        type='SwinTransformer',
        embed_dims=192,
        depths=[2, 2, 18, 2],
        num_heads=[6, 12, 24, 48],
        window_size=7,
        mlp_ratio=4,
        qkv_bias=True,
        qk_scale=None,
        drop_rate=0.,
        attn_drop_rate=0.,
        drop_path_rate=0.2,
        patch_norm=True,
        out_indices=(0, 1, 2, 3),
        with_cp=True,
        init_cfg=dict(type='Pretrained', checkpoint=pretrained)),
    neck=dict(in_channels=[192, 384, 768, 1536]),
    rpn_head=dict(
        type='EmbeddingRPNHead',
        num_proposals=num_proposals,
        proposal_feature_channel=256))

optimizer = dict(
    paramwise_cfg=dict(
        custom_keys={
            'absolute_pos_embed': dict(decay_mult=0.),
            'relative_position_bias_table': dict(decay_mult=0.),
            'norm': dict(decay_mult=0.)
        }))

img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
min_values = (320, 352, 384, 416, 448, 480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='LoadAnnotations',
        with_bbox=True,
        with_mask=True,
        with_id=True,
        bitmask=True),
    dict(
        type='Resize',
        img_scale=[(1333, value) for value in min_values],
        multiscale_mode='value',
        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', 'gt_masks', 'gt_ids']),
]

test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='Resize', img_scale=(1333, 480), keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.0),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img']),
]

data = dict(train=dict(pipeline=train_pipeline), test=dict(pipeline=test_pipeline))