File size: 2,499 Bytes
3bbb319 |
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 |
_base_ = [
'../_base_/models/mask_rcnn_r50_fpn.py',
'../_base_/datasets/coco_instance.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
norm_cfg = dict(type='BN', requires_grad=True)
model = dict(
backbone=dict(norm_cfg=norm_cfg, norm_eval=False),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
norm_cfg=norm_cfg,
num_outs=5),
roi_head=dict(
bbox_head=dict(norm_cfg=norm_cfg), mask_head=dict(norm_cfg=norm_cfg)))
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(
type='Resize',
img_scale=(640, 640),
ratio_range=(0.8, 1.2),
keep_ratio=True),
dict(type='RandomCrop', crop_size=(640, 640)),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size=(640, 640)),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(640, 640),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=64),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=8,
workers_per_gpu=4,
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# learning policy
optimizer = dict(
type='SGD',
lr=0.08,
momentum=0.9,
weight_decay=0.0001,
paramwise_cfg=dict(norm_decay_mult=0, bypass_duplicate=True))
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=1000,
warmup_ratio=0.1,
step=[30, 40])
# runtime settings
runner = dict(max_epochs=50)
evaluation = dict(interval=2)
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (8 GPUs) x (8 samples per GPU)
auto_scale_lr = dict(base_batch_size=64)
|