File size: 5,201 Bytes
2a68c9d 5bc02c3 2a68c9d 5bc02c3 2a68c9d |
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 |
_base_ = [
"mmdet::_base_/default_runtime.py",
"mmdet::_base_/schedules/schedule_1x.py",
"mmdet::_base_/datasets/coco_detection.py",
"mmdet::rtmdet/rtmdet_tta.py",
]
model = dict(
type="RTMDet",
data_preprocessor=dict(
type="DetDataPreprocessor",
mean=[103.53, 116.28, 123.675],
std=[57.375, 57.12, 58.395],
bgr_to_rgb=False,
batch_augments=None,
),
backbone=dict(
type="CSPNeXt",
arch="P5",
expand_ratio=0.5,
deepen_factor=0.67,
widen_factor=0.75,
channel_attention=True,
norm_cfg=dict(type="SyncBN"),
act_cfg=dict(type="SiLU", inplace=True),
),
neck=dict(
type="CSPNeXtPAFPN",
in_channels=[192, 384, 768],
out_channels=192,
num_csp_blocks=2,
expand_ratio=0.5,
norm_cfg=dict(type="SyncBN"),
act_cfg=dict(type="SiLU", inplace=True),
),
bbox_head=dict(
type="RTMDetSepBNHead",
num_classes=80,
in_channels=192,
stacked_convs=2,
feat_channels=192,
anchor_generator=dict(type="MlvlPointGenerator", offset=0, strides=[8, 16, 32]),
bbox_coder=dict(type="DistancePointBBoxCoder"),
loss_cls=dict(
type="QualityFocalLoss", use_sigmoid=True, beta=2.0, loss_weight=1.0
),
loss_bbox=dict(type="GIoULoss", loss_weight=2.0),
with_objectness=False,
exp_on_reg=True,
share_conv=True,
pred_kernel_size=1,
norm_cfg=dict(type="SyncBN"),
act_cfg=dict(type="SiLU", inplace=True),
),
train_cfg=dict(
assigner=dict(type="DynamicSoftLabelAssigner", topk=13),
allowed_border=-1,
pos_weight=-1,
debug=False,
),
test_cfg=dict(
nms_pre=30000,
min_bbox_size=0,
score_thr=0.001,
nms=dict(type="nms", iou_threshold=0.65),
max_per_img=300,
),
)
train_pipeline = [
dict(type="LoadImageFromFile", backend_args={{_base_.backend_args}}),
dict(type="LoadAnnotations", with_bbox=True),
dict(type="CachedMosaic", img_scale=(640, 640), pad_val=114.0),
dict(
type="RandomResize", scale=(1280, 1280), ratio_range=(0.1, 2.0), keep_ratio=True
),
dict(type="RandomCrop", crop_size=(640, 640)),
dict(type="YOLOXHSVRandomAug"),
dict(type="RandomFlip", prob=0.5),
dict(type="Pad", size=(640, 640), pad_val=dict(img=(114, 114, 114))),
dict(
type="CachedMixUp",
img_scale=(640, 640),
ratio_range=(1.0, 1.0),
max_cached_images=20,
pad_val=(114, 114, 114),
),
dict(type="mmdet.PackDetInputs"),
]
train_pipeline_stage2 = [
dict(type="LoadImageFromFile", backend_args={{_base_.backend_args}}),
dict(type="LoadAnnotations", with_bbox=True),
dict(
type="RandomResize", scale=(640, 640), ratio_range=(0.1, 2.0), keep_ratio=True
),
dict(type="RandomCrop", crop_size=(640, 640)),
dict(type="YOLOXHSVRandomAug"),
dict(type="RandomFlip", prob=0.5),
dict(type="Pad", size=(640, 640), pad_val=dict(img=(114, 114, 114))),
dict(type="mmdet.PackDetInputs"),
]
test_pipeline = [
dict(type="LoadImageFromFile", backend_args={{_base_.backend_args}}),
dict(type="Resize", scale=(640, 640), keep_ratio=True),
dict(type="Pad", size=(640, 640), pad_val=dict(img=(114, 114, 114))),
dict(
type="mmdet.PackDetInputs",
meta_keys=("img_id", "img_path", "ori_shape", "img_shape", "scale_factor"),
),
]
train_dataloader = dict(
batch_size=32,
num_workers=10,
batch_sampler=None,
pin_memory=True,
dataset=dict(pipeline=train_pipeline),
)
val_dataloader = dict(
batch_size=5, num_workers=10, dataset=dict(pipeline=test_pipeline)
)
test_dataloader = val_dataloader
max_epochs = 300
stage2_num_epochs = 20
base_lr = 0.004
interval = 10
train_cfg = dict(
max_epochs=max_epochs,
val_interval=interval,
dynamic_intervals=[(max_epochs - stage2_num_epochs, 1)],
)
val_evaluator = dict(proposal_nums=(100, 1, 10))
test_evaluator = val_evaluator
# optimizer
optim_wrapper = dict(
_delete_=True,
type="OptimWrapper",
optimizer=dict(type="AdamW", lr=base_lr, weight_decay=0.05),
paramwise_cfg=dict(norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True),
)
# learning rate
param_scheduler = [
dict(type="LinearLR", start_factor=1.0e-5, by_epoch=False, begin=0, end=1000),
dict(
# use cosine lr from 150 to 300 epoch
type="CosineAnnealingLR",
eta_min=base_lr * 0.05,
begin=max_epochs // 2,
end=max_epochs,
T_max=max_epochs // 2,
by_epoch=True,
convert_to_iter_based=True,
),
]
# hooks
default_hooks = dict(
checkpoint=dict(
interval=interval, max_keep_ckpts=3 # only keep latest 3 checkpoints
)
)
custom_hooks = [
dict(
type="EMAHook",
ema_type="ExpMomentumEMA",
momentum=0.0002,
update_buffers=True,
priority=49,
),
dict(
type="PipelineSwitchHook",
switch_epoch=max_epochs - stage2_num_epochs,
switch_pipeline=train_pipeline_stage2,
),
]
|