OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io/
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
110 lines
3.6 KiB
110 lines
3.6 KiB
_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)
|
|
|