File size: 11,038 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 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 |
_base_ = ['./default_runtime.py', './det_p5_tta.py']
# ========================Frequently modified parameters======================
# -----data related-----
data_root = 'data/coco/' # Root path of data
# Path of train annotation file
train_ann_file = 'annotations/instances_train2017.json'
train_data_prefix = 'train2017/' # Prefix of train image path
# Path of val annotation file
val_ann_file = 'annotations/instances_val2017.json'
val_data_prefix = 'val2017/' # Prefix of val image path
num_classes = 80 # Number of classes for classification
# Batch size of a single GPU during training
train_batch_size_per_gpu = 16
# Worker to pre-fetch data for each single GPU during training
train_num_workers = 8
# persistent_workers must be False if num_workers is 0
persistent_workers = True
# -----train val related-----
# Base learning rate for optim_wrapper. Corresponding to 8xb16=64 bs
base_lr = 0.01
max_epochs = 500 # Maximum training epochs
# Disable mosaic augmentation for final 10 epochs (stage 2)
close_mosaic_epochs = 10
model_test_cfg = dict(
# The config of multi-label for multi-class prediction.
multi_label=True,
# The number of boxes before NMS
nms_pre=30000,
score_thr=0.001, # Threshold to filter out boxes.
nms=dict(type='nms', iou_threshold=0.7), # NMS type and threshold
max_per_img=300) # Max number of detections of each image
# ========================Possible modified parameters========================
# -----data related-----
img_scale = (640, 640) # width, height
# Dataset type, this will be used to define the dataset
dataset_type = 'YOLOv5CocoDataset'
# Batch size of a single GPU during validation
val_batch_size_per_gpu = 1
# Worker to pre-fetch data for each single GPU during validation
val_num_workers = 2
# Config of batch shapes. Only on val.
# We tested YOLOv8-m will get 0.02 higher than not using it.
batch_shapes_cfg = None
# You can turn on `batch_shapes_cfg` by uncommenting the following lines.
# batch_shapes_cfg = dict(
# type='BatchShapePolicy',
# batch_size=val_batch_size_per_gpu,
# img_size=img_scale[0],
# # The image scale of padding should be divided by pad_size_divisor
# size_divisor=32,
# # Additional paddings for pixel scale
# extra_pad_ratio=0.5)
# -----model related-----
# The scaling factor that controls the depth of the network structure
deepen_factor = 0.33
# The scaling factor that controls the width of the network structure
widen_factor = 0.5
# Strides of multi-scale prior box
strides = [8, 16, 32]
# The output channel of the last stage
last_stage_out_channels = 1024
num_det_layers = 3 # The number of model output scales
norm_cfg = dict(type='BN', momentum=0.03, eps=0.001) # Normalization config
# -----train val related-----
affine_scale = 0.5 # YOLOv5RandomAffine scaling ratio
# YOLOv5RandomAffine aspect ratio of width and height thres to filter bboxes
max_aspect_ratio = 100
tal_topk = 10 # Number of bbox selected in each level
tal_alpha = 0.5 # A Hyper-parameter related to alignment_metrics
tal_beta = 6.0 # A Hyper-parameter related to alignment_metrics
# TODO: Automatically scale loss_weight based on number of detection layers
loss_cls_weight = 0.5
loss_bbox_weight = 7.5
# Since the dfloss is implemented differently in the official
# and mmdet, we're going to divide loss_weight by 4.
loss_dfl_weight = 1.5 / 4
lr_factor = 0.01 # Learning rate scaling factor
weight_decay = 0.0005
# Save model checkpoint and validation intervals in stage 1
save_epoch_intervals = 10
# validation intervals in stage 2
val_interval_stage2 = 1
# The maximum checkpoints to keep.
max_keep_ckpts = 2
# Single-scale training is recommended to
# be turned on, which can speed up training.
env_cfg = dict(cudnn_benchmark=True)
# ===============================Unmodified in most cases====================
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=norm_cfg,
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=norm_cfg,
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=norm_cfg,
act_cfg=dict(type='SiLU', inplace=True),
featmap_strides=strides),
prior_generator=dict(
type='mmdet.MlvlPointGenerator', offset=0.5, strides=strides),
bbox_coder=dict(type='DistancePointBBoxCoder'),
# scaled based on number of detection layers
loss_cls=dict(
type='mmdet.CrossEntropyLoss',
use_sigmoid=True,
reduction='none',
loss_weight=loss_cls_weight),
loss_bbox=dict(
type='IoULoss',
iou_mode='ciou',
bbox_format='xyxy',
reduction='sum',
loss_weight=loss_bbox_weight,
return_iou=False),
loss_dfl=dict(
type='mmdet.DistributionFocalLoss',
reduction='mean',
loss_weight=loss_dfl_weight)),
train_cfg=dict(
assigner=dict(
type='BatchTaskAlignedAssigner',
num_classes=num_classes,
use_ciou=True,
topk=tal_topk,
alpha=tal_alpha,
beta=tal_beta,
eps=1e-9)),
test_cfg=model_test_cfg)
albu_train_transforms = [
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', backend_args=_base_.backend_args),
dict(type='LoadAnnotations', with_bbox=True)
]
last_transform = [
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_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=(1 - affine_scale, 1 + affine_scale),
max_aspect_ratio=max_aspect_ratio,
# 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=(1 - affine_scale, 1 + affine_scale),
max_aspect_ratio=max_aspect_ratio,
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=train_ann_file,
data_prefix=dict(img=train_data_prefix),
filter_cfg=dict(filter_empty_gt=False, min_size=32),
pipeline=train_pipeline))
test_pipeline = [
dict(type='LoadImageFromFile', backend_args=_base_.backend_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'))
]
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=val_data_prefix),
ann_file=val_ann_file,
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=weight_decay,
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=max_keep_ckpts))
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 - close_mosaic_epochs,
switch_pipeline=train_pipeline_stage2)
]
val_evaluator = dict(
type='mmdet.CocoMetric',
proposal_nums=(100, 1, 10),
ann_file=data_root + val_ann_file,
metric='bbox')
test_evaluator = val_evaluator
train_cfg = dict(
type='EpochBasedTrainLoop',
max_epochs=max_epochs,
val_interval=save_epoch_intervals,
dynamic_intervals=[((max_epochs - close_mosaic_epochs),
val_interval_stage2)])
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop') |