yolox_tiny_8x8_300e_coco.py
1.6 KB
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
_base_ = './yolox_s_8x8_300e_coco.py'
# model settings
model = dict(
random_size_range=(10, 20),
backbone=dict(deepen_factor=0.33, widen_factor=0.375),
neck=dict(in_channels=[96, 192, 384], out_channels=96),
bbox_head=dict(in_channels=96, feat_channels=96))
img_scale = (640, 640) # height, width
train_pipeline = [
dict(type='Mosaic', img_scale=img_scale, pad_val=114.0),
dict(
type='RandomAffine',
scaling_ratio_range=(0.5, 1.5),
border=(-img_scale[0] // 2, -img_scale[1] // 2)),
dict(type='YOLOXHSVRandomAug'),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Resize', img_scale=img_scale, keep_ratio=True),
dict(
type='Pad',
pad_to_square=True,
pad_val=dict(img=(114.0, 114.0, 114.0))),
dict(type='FilterAnnotations', min_gt_bbox_wh=(1, 1), keep_empty=False),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(416, 416),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(
type='Pad',
pad_to_square=True,
pad_val=dict(img=(114.0, 114.0, 114.0))),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img'])
])
]
train_dataset = dict(pipeline=train_pipeline)
data = dict(
train=train_dataset,
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))