58 lines
1.9 KiB
Python
58 lines
1.9 KiB
Python
_base_ = 'ssd300_voc0712.py'
|
|
input_size = 512
|
|
model = dict(
|
|
neck=dict(
|
|
out_channels=(512, 1024, 512, 256, 256, 256, 256),
|
|
level_strides=(2, 2, 2, 2, 1),
|
|
level_paddings=(1, 1, 1, 1, 1),
|
|
last_kernel_size=4),
|
|
bbox_head=dict(
|
|
in_channels=(512, 1024, 512, 256, 256, 256, 256),
|
|
anchor_generator=dict(
|
|
input_size=input_size,
|
|
strides=[8, 16, 32, 64, 128, 256, 512],
|
|
basesize_ratio_range=(0.15, 0.9),
|
|
ratios=([2], [2, 3], [2, 3], [2, 3], [2, 3], [2], [2]))))
|
|
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
|
|
train_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(type='LoadAnnotations', with_bbox=True),
|
|
dict(
|
|
type='Expand',
|
|
mean=img_norm_cfg['mean'],
|
|
to_rgb=img_norm_cfg['to_rgb'],
|
|
ratio_range=(1, 4)),
|
|
dict(
|
|
type='MinIoURandomCrop',
|
|
min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
|
|
min_crop_size=0.3),
|
|
dict(type='Resize', img_scale=(512, 512), keep_ratio=False),
|
|
dict(type='RandomFlip', flip_ratio=0.5),
|
|
dict(
|
|
type='PhotoMetricDistortion',
|
|
brightness_delta=32,
|
|
contrast_range=(0.5, 1.5),
|
|
saturation_range=(0.5, 1.5),
|
|
hue_delta=18),
|
|
dict(type='Normalize', **img_norm_cfg),
|
|
dict(type='DefaultFormatBundle'),
|
|
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
|
|
]
|
|
test_pipeline = [
|
|
dict(type='LoadImageFromFile'),
|
|
dict(
|
|
type='MultiScaleFlipAug',
|
|
img_scale=(512, 512),
|
|
flip=False,
|
|
transforms=[
|
|
dict(type='Resize', keep_ratio=False),
|
|
dict(type='Normalize', **img_norm_cfg),
|
|
dict(type='ImageToTensor', keys=['img']),
|
|
dict(type='Collect', keys=['img']),
|
|
])
|
|
]
|
|
data = dict(
|
|
train=dict(dataset=dict(pipeline=train_pipeline)),
|
|
val=dict(pipeline=test_pipeline),
|
|
test=dict(pipeline=test_pipeline))
|