File size: 3,653 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 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 |
_base_ = [
'../_base_/default_runtime.py', '../_base_/datasets/coco_detection.py'
]
# model settings
model = dict(
type='CornerNet',
backbone=dict(
type='HourglassNet',
downsample_times=5,
num_stacks=2,
stage_channels=[256, 256, 384, 384, 384, 512],
stage_blocks=[2, 2, 2, 2, 2, 4],
norm_cfg=dict(type='BN', requires_grad=True)),
neck=None,
bbox_head=dict(
type='CentripetalHead',
num_classes=80,
in_channels=256,
num_feat_levels=2,
corner_emb_channels=0,
loss_heatmap=dict(
type='GaussianFocalLoss', alpha=2.0, gamma=4.0, loss_weight=1),
loss_offset=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1),
loss_guiding_shift=dict(
type='SmoothL1Loss', beta=1.0, loss_weight=0.05),
loss_centripetal_shift=dict(
type='SmoothL1Loss', beta=1.0, loss_weight=1)),
# training and testing settings
train_cfg=None,
test_cfg=dict(
corner_topk=100,
local_maximum_kernel=3,
distance_threshold=0.5,
score_thr=0.05,
max_per_img=100,
nms=dict(type='soft_nms', iou_threshold=0.5, method='gaussian')))
# data settings
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', to_float32=True),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PhotoMetricDistortion',
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
dict(
type='RandomCenterCropPad',
crop_size=(511, 511),
ratios=(0.6, 0.7, 0.8, 0.9, 1.0, 1.1, 1.2, 1.3),
test_mode=False,
test_pad_mode=None,
**img_norm_cfg),
dict(type='Resize', img_scale=(511, 511), keep_ratio=False),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile', to_float32=True),
dict(
type='MultiScaleFlipAug',
scale_factor=1.0,
flip=True,
transforms=[
dict(type='Resize'),
dict(
type='RandomCenterCropPad',
crop_size=None,
ratios=None,
border=None,
test_mode=True,
test_pad_mode=['logical_or', 127],
**img_norm_cfg),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(
type='Collect',
keys=['img'],
meta_keys=('filename', 'ori_shape', 'img_shape', 'pad_shape',
'scale_factor', 'flip', 'img_norm_cfg', 'border')),
])
]
data = dict(
samples_per_gpu=6,
workers_per_gpu=3,
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(type='Adam', lr=0.0005)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[190])
runner = dict(type='EpochBasedRunner', max_epochs=210)
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (16 GPUs) x (6 samples per GPU)
auto_scale_lr = dict(base_batch_size=96)
|