Spaces:
Sleeping
Sleeping
File size: 3,113 Bytes
186701e |
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 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
_base_ = './rtmdet_l_syncbn_fast_8xb32-300e_coco.py'
checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-s_imagenet_600e.pth' # noqa
# ========================modified parameters======================
deepen_factor = 0.33
widen_factor = 0.5
img_scale = _base_.img_scale
# ratio range for random resize
random_resize_ratio_range = (0.5, 2.0)
# Number of cached images in mosaic
mosaic_max_cached_images = 40
# Number of cached images in mixup
mixup_max_cached_images = 20
# =======================Unmodified in most cases==================
model = dict(
backbone=dict(
deepen_factor=deepen_factor,
widen_factor=widen_factor,
# Since the checkpoint includes CUDA:0 data,
# it must be forced to set map_location.
# Once checkpoint is fixed, it can be removed.
init_cfg=dict(
type='Pretrained',
prefix='backbone.',
checkpoint=checkpoint,
map_location='cpu')),
neck=dict(
deepen_factor=deepen_factor,
widen_factor=widen_factor,
),
bbox_head=dict(head_module=dict(widen_factor=widen_factor)))
train_pipeline = [
dict(type='LoadImageFromFile', backend_args=_base_.backend_args),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='Mosaic',
img_scale=img_scale,
use_cached=True,
max_cached_images=mosaic_max_cached_images,
pad_val=114.0),
dict(
type='mmdet.RandomResize',
# img_scale is (width, height)
scale=(img_scale[0] * 2, img_scale[1] * 2),
ratio_range=random_resize_ratio_range, # note
resize_type='mmdet.Resize',
keep_ratio=True),
dict(type='mmdet.RandomCrop', crop_size=img_scale),
dict(type='mmdet.YOLOXHSVRandomAug'),
dict(type='mmdet.RandomFlip', prob=0.5),
dict(type='mmdet.Pad', size=img_scale, pad_val=dict(img=(114, 114, 114))),
dict(
type='YOLOv5MixUp',
use_cached=True,
max_cached_images=mixup_max_cached_images),
dict(type='mmdet.PackDetInputs')
]
train_pipeline_stage2 = [
dict(type='LoadImageFromFile', backend_args=_base_.backend_args),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='mmdet.RandomResize',
scale=img_scale,
ratio_range=random_resize_ratio_range, # note
resize_type='mmdet.Resize',
keep_ratio=True),
dict(type='mmdet.RandomCrop', crop_size=img_scale),
dict(type='mmdet.YOLOXHSVRandomAug'),
dict(type='mmdet.RandomFlip', prob=0.5),
dict(type='mmdet.Pad', size=img_scale, pad_val=dict(img=(114, 114, 114))),
dict(type='mmdet.PackDetInputs')
]
train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
custom_hooks = [
dict(
type='EMAHook',
ema_type='ExpMomentumEMA',
momentum=0.0002,
update_buffers=True,
strict_load=False,
priority=49),
dict(
type='mmdet.PipelineSwitchHook',
switch_epoch=_base_.max_epochs - _base_.num_epochs_stage2,
switch_pipeline=train_pipeline_stage2)
]
|