mirror of https://github.com/open-mmlab/mmyolo.git
287 lines
8.2 KiB
Python
287 lines
8.2 KiB
Python
_base_ = '../_base_/default_runtime.py'
|
|
|
|
# dataset settings
|
|
data_root = 'data/coco/'
|
|
dataset_type = 'YOLOv5CocoDataset'
|
|
|
|
# parameters that often need to be modified
|
|
num_classes = 80
|
|
img_scale = (640, 640) # height, width
|
|
deepen_factor = 0.33
|
|
widen_factor = 0.5
|
|
max_epochs = 500
|
|
save_epoch_intervals = 10
|
|
train_batch_size_per_gpu = 16
|
|
train_num_workers = 8
|
|
val_batch_size_per_gpu = 1
|
|
val_num_workers = 2
|
|
|
|
# persistent_workers must be False if num_workers is 0.
|
|
persistent_workers = True
|
|
|
|
strides = [8, 16, 32]
|
|
num_det_layers = 3
|
|
|
|
last_stage_out_channels = 1024
|
|
|
|
# Base learning rate for optim_wrapper
|
|
base_lr = 0.01
|
|
lr_factor = 0.01
|
|
|
|
# single-scale training is recommended to
|
|
# be turned on, which can speed up training.
|
|
env_cfg = dict(cudnn_benchmark=True)
|
|
|
|
model = dict(
|
|
type='YOLODetector',
|
|
data_preprocessor=dict(
|
|
type='YOLOv5DetDataPreprocessor',
|
|
mean=[0., 0., 0.],
|
|
std=[255., 255., 255.],
|
|
bgr_to_rgb=True),
|
|
backbone=dict(
|
|
type='YOLOv8CSPDarknet',
|
|
arch='P5',
|
|
last_stage_out_channels=last_stage_out_channels,
|
|
deepen_factor=deepen_factor,
|
|
widen_factor=widen_factor,
|
|
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
|
|
act_cfg=dict(type='SiLU', inplace=True)),
|
|
neck=dict(
|
|
type='YOLOv8PAFPN',
|
|
deepen_factor=deepen_factor,
|
|
widen_factor=widen_factor,
|
|
in_channels=[256, 512, last_stage_out_channels],
|
|
out_channels=[256, 512, last_stage_out_channels],
|
|
num_csp_blocks=3,
|
|
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
|
|
act_cfg=dict(type='SiLU', inplace=True)),
|
|
bbox_head=dict(
|
|
type='YOLOv8Head',
|
|
head_module=dict(
|
|
type='YOLOv8HeadModule',
|
|
num_classes=num_classes,
|
|
in_channels=[256, 512, last_stage_out_channels],
|
|
widen_factor=widen_factor,
|
|
reg_max=16,
|
|
norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
|
|
act_cfg=dict(type='SiLU', inplace=True),
|
|
featmap_strides=[8, 16, 32]),
|
|
prior_generator=dict(
|
|
type='mmdet.MlvlPointGenerator', offset=0.5, strides=[8, 16, 32]),
|
|
bbox_coder=dict(type='DistancePointBBoxCoder'),
|
|
loss_cls=dict(
|
|
type='mmdet.CrossEntropyLoss',
|
|
use_sigmoid=True,
|
|
reduction='none',
|
|
loss_weight=0.5),
|
|
loss_bbox=dict(
|
|
type='IoULoss',
|
|
iou_mode='ciou',
|
|
bbox_format='xyxy',
|
|
reduction='sum',
|
|
loss_weight=7.5,
|
|
return_iou=False),
|
|
# Since the dfloss is implemented differently in the official
|
|
# and mmdet, we're going to divide loss_weight by 4.
|
|
loss_dfl=dict(
|
|
type='mmdet.DistributionFocalLoss',
|
|
reduction='mean',
|
|
loss_weight=1.5 / 4)),
|
|
train_cfg=dict(
|
|
assigner=dict(
|
|
type='BatchTaskAlignedAssigner',
|
|
num_classes=num_classes,
|
|
use_ciou=True,
|
|
topk=10,
|
|
alpha=0.5,
|
|
beta=6.0,
|
|
eps=1e-9)),
|
|
test_cfg=dict(
|
|
multi_label=True,
|
|
nms_pre=30000,
|
|
score_thr=0.001,
|
|
nms=dict(type='nms', iou_threshold=0.7),
|
|
max_per_img=300))
|
|
|
|
albu_train_transform = [
|
|
dict(type='Blur', p=0.01),
|
|
dict(type='MedianBlur', p=0.01),
|
|
dict(type='ToGray', p=0.01),
|
|
dict(type='CLAHE', p=0.01)
|
|
]
|
|
|
|
pre_transform = [
|
|
dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args),
|
|
dict(type='LoadAnnotations', with_bbox=True)
|
|
]
|
|
|
|
last_transform = [
|
|
dict(
|
|
type='mmdet.Albu',
|
|
transforms=albu_train_transform,
|
|
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_pipeline = [
|
|
*pre_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,
|
|
scaling_ratio_range=(0.5, 1.5),
|
|
max_aspect_ratio=100,
|
|
# img_scale is (width, height)
|
|
border=(-img_scale[0] // 2, -img_scale[1] // 2),
|
|
border_val=(114, 114, 114)),
|
|
*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=(0.5, 1.5),
|
|
max_aspect_ratio=100,
|
|
border_val=(114, 114, 114)), *last_transform
|
|
]
|
|
|
|
train_dataloader = dict(
|
|
batch_size=train_batch_size_per_gpu,
|
|
num_workers=train_num_workers,
|
|
persistent_workers=persistent_workers,
|
|
pin_memory=True,
|
|
sampler=dict(type='DefaultSampler', shuffle=True),
|
|
collate_fn=dict(type='yolov5_collate'),
|
|
dataset=dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
ann_file='annotations/instances_train2017.json',
|
|
data_prefix=dict(img='train2017/'),
|
|
filter_cfg=dict(filter_empty_gt=False, min_size=32),
|
|
pipeline=train_pipeline))
|
|
|
|
test_pipeline = [
|
|
dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args),
|
|
dict(type='YOLOv5KeepRatioResize', scale=img_scale),
|
|
dict(
|
|
type='LetterResize',
|
|
scale=img_scale,
|
|
allow_scale_up=False,
|
|
pad_val=dict(img=114)),
|
|
dict(type='LoadAnnotations', with_bbox=True, _scope_='mmdet'),
|
|
dict(
|
|
type='mmdet.PackDetInputs',
|
|
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
|
|
'scale_factor', 'pad_param'))
|
|
]
|
|
|
|
# only on Val
|
|
# you can turn on `batch_shapes_cfg`,
|
|
# we tested YOLOv8-m will get 0.02 higher than not using it.
|
|
batch_shapes_cfg = None
|
|
# batch_shapes_cfg = dict(
|
|
# type='BatchShapePolicy',
|
|
# batch_size=val_batch_size_per_gpu,
|
|
# img_size=img_scale[0],
|
|
# size_divisor=32,
|
|
# extra_pad_ratio=0.5)
|
|
|
|
val_dataloader = dict(
|
|
batch_size=val_batch_size_per_gpu,
|
|
num_workers=val_num_workers,
|
|
persistent_workers=persistent_workers,
|
|
pin_memory=True,
|
|
drop_last=False,
|
|
sampler=dict(type='DefaultSampler', shuffle=False),
|
|
dataset=dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
test_mode=True,
|
|
data_prefix=dict(img='val2017/'),
|
|
ann_file='annotations/instances_val2017.json',
|
|
pipeline=test_pipeline,
|
|
batch_shapes_cfg=batch_shapes_cfg))
|
|
|
|
test_dataloader = val_dataloader
|
|
|
|
param_scheduler = None
|
|
optim_wrapper = dict(
|
|
type='OptimWrapper',
|
|
clip_grad=dict(max_norm=10.0),
|
|
optimizer=dict(
|
|
type='SGD',
|
|
lr=base_lr,
|
|
momentum=0.937,
|
|
weight_decay=0.0005,
|
|
nesterov=True,
|
|
batch_size_per_gpu=train_batch_size_per_gpu),
|
|
constructor='YOLOv5OptimizerConstructor')
|
|
|
|
default_hooks = dict(
|
|
param_scheduler=dict(
|
|
type='YOLOv5ParamSchedulerHook',
|
|
scheduler_type='linear',
|
|
lr_factor=lr_factor,
|
|
max_epochs=max_epochs),
|
|
checkpoint=dict(
|
|
type='CheckpointHook',
|
|
interval=save_epoch_intervals,
|
|
save_best='auto',
|
|
max_keep_ckpts=2))
|
|
|
|
custom_hooks = [
|
|
dict(
|
|
type='EMAHook',
|
|
ema_type='ExpMomentumEMA',
|
|
momentum=0.0001,
|
|
update_buffers=True,
|
|
strict_load=False,
|
|
priority=49),
|
|
dict(
|
|
type='mmdet.PipelineSwitchHook',
|
|
switch_epoch=max_epochs - 10,
|
|
switch_pipeline=train_pipeline_stage2)
|
|
]
|
|
|
|
val_evaluator = dict(
|
|
type='mmdet.CocoMetric',
|
|
proposal_nums=(100, 1, 10),
|
|
ann_file=data_root + 'annotations/instances_val2017.json',
|
|
metric='bbox')
|
|
test_evaluator = val_evaluator
|
|
|
|
train_cfg = dict(
|
|
type='EpochBasedTrainLoop',
|
|
max_epochs=max_epochs,
|
|
val_interval=save_epoch_intervals,
|
|
dynamic_intervals=[(max_epochs - 10, 1)])
|
|
|
|
val_cfg = dict(type='ValLoop')
|
|
test_cfg = dict(type='TestLoop')
|