File size: 4,605 Bytes
6c9ac8f |
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 |
_base_ = [
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
pretrained = 'https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window12_384_22k.pth' # noqa
model = dict(
type='ATSS',
data_preprocessor=dict(
type='DetDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_size_divisor=128),
backbone=dict(
type='SwinTransformer',
pretrain_img_size=384,
embed_dims=192,
depths=[2, 2, 18, 2],
num_heads=[6, 12, 24, 48],
window_size=12,
mlp_ratio=4,
qkv_bias=True,
qk_scale=None,
drop_rate=0.,
attn_drop_rate=0.,
drop_path_rate=0.2,
patch_norm=True,
out_indices=(1, 2, 3),
# Please only add indices that would be used
# in FPN, otherwise some parameter will not be used
with_cp=False,
convert_weights=True,
init_cfg=dict(type='Pretrained', checkpoint=pretrained)),
neck=[
dict(
type='FPN',
in_channels=[384, 768, 1536],
out_channels=256,
start_level=0,
add_extra_convs='on_output',
num_outs=5),
dict(
type='DyHead',
in_channels=256,
out_channels=256,
num_blocks=6,
# disable zero_init_offset to follow official implementation
zero_init_offset=False)
],
bbox_head=dict(
type='ATSSHead',
num_classes=80,
in_channels=256,
pred_kernel_size=1, # follow DyHead official implementation
stacked_convs=0,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
ratios=[1.0],
octave_base_scale=8,
scales_per_octave=1,
strides=[8, 16, 32, 64, 128],
center_offset=0.5), # follow DyHead official implementation
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[0.1, 0.1, 0.2, 0.2]),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
loss_centerness=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)),
# training and testing settings
train_cfg=dict(
assigner=dict(type='ATSSAssigner', topk=9),
allowed_border=-1,
pos_weight=-1,
debug=False),
test_cfg=dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.6),
max_per_img=100))
# dataset settings
train_pipeline = [
dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='RandomResize',
scale=[(2000, 480), (2000, 1200)],
keep_ratio=True,
backend='pillow'),
dict(type='RandomFlip', prob=0.5),
dict(type='PackDetInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
dict(type='Resize', scale=(2000, 1200), keep_ratio=True, backend='pillow'),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader = dict(
dataset=dict(
_delete_=True,
type='RepeatDataset',
times=2,
dataset=dict(
type={{_base_.dataset_type}},
data_root={{_base_.data_root}},
ann_file='annotations/instances_train2017.json',
data_prefix=dict(img='train2017/'),
filter_cfg=dict(filter_empty_gt=True, min_size=32),
pipeline=train_pipeline,
backend_args={{_base_.backend_args}})))
val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
test_dataloader = val_dataloader
# optimizer
optim_wrapper = dict(
_delete_=True,
type='OptimWrapper',
optimizer=dict(
type='AdamW', lr=0.00005, betas=(0.9, 0.999), weight_decay=0.05),
paramwise_cfg=dict(
custom_keys={
'absolute_pos_embed': dict(decay_mult=0.),
'relative_position_bias_table': dict(decay_mult=0.),
'norm': dict(decay_mult=0.)
}),
clip_grad=None)
|