Hugging Face's logo

adonaivera
/
YOLO-World

Model card Files Community
YOLO-World
File size: 2,255 Bytes 
e9b779d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
 
_base_ = './yolov8_s_syncbn_fast_8xb16-500e_coco.py'

# ========================modified parameters======================
deepen_factor = 0.67
widen_factor = 0.75
last_stage_out_channels = 768

affine_scale = 0.9
mixup_prob = 0.1

# =======================Unmodified in most cases==================
img_scale = _base_.img_scale
pre_transform = _base_.pre_transform
last_transform = _base_.last_transform

model = dict(
    backbone=dict(
        last_stage_out_channels=last_stage_out_channels,
        deepen_factor=deepen_factor,
        widen_factor=widen_factor),
    neck=dict(
        deepen_factor=deepen_factor,
        widen_factor=widen_factor,
        in_channels=[256, 512, last_stage_out_channels],
        out_channels=[256, 512, last_stage_out_channels]),
    bbox_head=dict(
        head_module=dict(
            widen_factor=widen_factor,
            in_channels=[256, 512, last_stage_out_channels])))

mosaic_affine_transform = [
    dict(
        type='Mosaic',
        img_scale=img_scale,
        pad_val=114.0,
        pre_transform=pre_transform),
    dict(
        type='YOLOv5RandomAffine',
        max_rotate_degree=0.0,
        max_shear_degree=0.0,
        max_aspect_ratio=100,
        scaling_ratio_range=(1 - affine_scale, 1 + affine_scale),
        # img_scale is (width, height)
        border=(-img_scale[0] // 2, -img_scale[1] // 2),
        border_val=(114, 114, 114))
]

# enable mixup
train_pipeline = [
    *pre_transform, *mosaic_affine_transform,
    dict(
        type='YOLOv5MixUp',
        prob=mixup_prob,
        pre_transform=[*pre_transform, *mosaic_affine_transform]),
    *last_transform
]

train_pipeline_stage2 = [
    *pre_transform,
    dict(type='YOLOv5KeepRatioResize', scale=img_scale),
    dict(
        type='LetterResize',
        scale=img_scale,
        allow_scale_up=True,
        pad_val=dict(img=114.0)),
    dict(
        type='YOLOv5RandomAffine',
        max_rotate_degree=0.0,
        max_shear_degree=0.0,
        scaling_ratio_range=(1 - affine_scale, 1 + affine_scale),
        max_aspect_ratio=100,
        border_val=(114, 114, 114)), *last_transform
]

train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
_base_.custom_hooks[1].switch_pipeline = train_pipeline_stage2