Spaces:
Sleeping
Sleeping
File size: 2,381 Bytes
b291f6a |
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 78 |
_base_ = './yolov5_m_mask-refine-v61_syncbn_fast_8xb16-300e_coco.py'
# This config use refining bbox and `YOLOv5CopyPaste`.
# Refining bbox means refining bbox by mask while loading annotations and
# transforming after `YOLOv5RandomAffine`
# ========================modified parameters======================
deepen_factor = 1.0
widen_factor = 1.0
mixup_prob = 0.1
copypaste_prob = 0.1
# =======================Unmodified in most cases==================
img_scale = _base_.img_scale
model = dict(
backbone=dict(
deepen_factor=deepen_factor,
widen_factor=widen_factor,
),
neck=dict(
deepen_factor=deepen_factor,
widen_factor=widen_factor,
),
bbox_head=dict(head_module=dict(widen_factor=widen_factor)))
pre_transform = _base_.pre_transform
albu_train_transforms = _base_.albu_train_transforms
mosaic_affine_pipeline = [
dict(
type='Mosaic',
img_scale=img_scale,
pad_val=114.0,
pre_transform=pre_transform),
dict(type='YOLOv5CopyPaste', prob=copypaste_prob),
dict(
type='YOLOv5RandomAffine',
max_rotate_degree=0.0,
max_shear_degree=0.0,
scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale),
# img_scale is (width, height)
border=(-img_scale[0] // 2, -img_scale[1] // 2),
border_val=(114, 114, 114),
min_area_ratio=_base_.min_area_ratio,
use_mask_refine=_base_.use_mask2refine),
dict(type='RemoveDataElement', keys=['gt_masks'])
]
# enable mixup and copypaste
train_pipeline = [
*pre_transform, *mosaic_affine_pipeline,
dict(
type='YOLOv5MixUp',
prob=mixup_prob,
pre_transform=[*pre_transform, *mosaic_affine_pipeline]),
dict(
type='mmdet.Albu',
transforms=albu_train_transforms,
bbox_params=dict(
type='BboxParams',
format='pascal_voc',
label_fields=['gt_bboxes_labels', 'gt_ignore_flags']),
keymap={
'img': 'image',
'gt_bboxes': 'bboxes'
}),
dict(type='YOLOv5HSVRandomAug'),
dict(type='mmdet.RandomFlip', prob=0.5),
dict(
type='mmdet.PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip',
'flip_direction'))
]
train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
|