File size: 1,460 Bytes
f549064
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
_base_ = './rtmdet_s_8xb32-300e_coco.py'

checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-tiny_imagenet_600e.pth'  # noqa

model = dict(
    backbone=dict(
        deepen_factor=0.167,
        widen_factor=0.375,
        init_cfg=dict(
            type='Pretrained', prefix='backbone.', checkpoint=checkpoint)),
    neck=dict(in_channels=[96, 192, 384], out_channels=96, num_csp_blocks=1),
    bbox_head=dict(in_channels=96, feat_channels=96, exp_on_reg=False))

train_pipeline = [
    dict(
        type='LoadImageFromFile',
        file_client_args={{_base_.file_client_args}}),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='CachedMosaic',
        img_scale=(640, 640),
        pad_val=114.0,
        max_cached_images=20,
        random_pop=False),
    dict(
        type='RandomResize',
        scale=(1280, 1280),
        ratio_range=(0.5, 2.0),
        keep_ratio=True),
    dict(type='RandomCrop', crop_size=(640, 640)),
    dict(type='YOLOXHSVRandomAug'),
    dict(type='RandomFlip', prob=0.5),
    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
    dict(
        type='CachedMixUp',
        img_scale=(640, 640),
        ratio_range=(1.0, 1.0),
        max_cached_images=10,
        random_pop=False,
        pad_val=(114, 114, 114),
        prob=0.5),
    dict(type='PackDetInputs')
]

train_dataloader = dict(dataset=dict(pipeline=train_pipeline))