File size: 3,148 Bytes
e8f2571 |
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 |
_base_ = [
'../_base_/models/retinanet_r50_fpn.py',
'../_base_/schedules/schedule_1x.py',
'../_base_/datasets/coco_detection.py', '../_base_/default_runtime.py'
]
image_size = (896, 896)
batch_augments = [dict(type='BatchFixedSizePad', size=image_size)]
norm_cfg = dict(type='BN', requires_grad=True)
checkpoint = 'https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b3_3rdparty_8xb32-aa_in1k_20220119-5b4887a0.pth' # noqa
model = dict(
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=32,
batch_augments=batch_augments),
backbone=dict(
_delete_=True,
type='EfficientNet',
arch='b3',
drop_path_rate=0.2,
out_indices=(3, 4, 5),
frozen_stages=0,
norm_cfg=dict(
type='SyncBN', requires_grad=True, eps=1e-3, momentum=0.01),
norm_eval=False,
init_cfg=dict(
type='Pretrained', prefix='backbone', checkpoint=checkpoint)),
neck=dict(
in_channels=[48, 136, 384],
start_level=0,
out_channels=256,
relu_before_extra_convs=True,
no_norm_on_lateral=True,
norm_cfg=norm_cfg),
bbox_head=dict(type='RetinaSepBNHead', num_ins=5, norm_cfg=norm_cfg),
# training and testing settings
train_cfg=dict(assigner=dict(neg_iou_thr=0.5)))
# dataset settings
train_pipeline = [
dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='RandomResize',
scale=image_size,
ratio_range=(0.8, 1.2),
keep_ratio=True),
dict(type='RandomCrop', crop_size=image_size),
dict(type='RandomFlip', prob=0.5),
dict(type='PackDetInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
dict(type='Resize', scale=image_size, keep_ratio=True),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader = dict(
batch_size=4, num_workers=4, dataset=dict(pipeline=train_pipeline))
val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
test_dataloader = val_dataloader
# optimizer
optim_wrapper = dict(
optimizer=dict(lr=0.04),
paramwise_cfg=dict(norm_decay_mult=0, bypass_duplicate=True))
# learning policy
max_epochs = 12
param_scheduler = [
dict(type='LinearLR', start_factor=0.1, by_epoch=False, begin=0, end=1000),
dict(
type='MultiStepLR',
begin=0,
end=max_epochs,
by_epoch=True,
milestones=[8, 11],
gamma=0.1)
]
train_cfg = dict(max_epochs=max_epochs)
# cudnn_benchmark=True can accelerate fix-size training
env_cfg = dict(cudnn_benchmark=True)
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (8 GPUs) x (4 samples per GPU)
auto_scale_lr = dict(base_batch_size=32)
|