Python——from collections import namedtuple
在读SSD源码中看到 namedtuple这个子类,这可以理解为元祖的升级版。细节看官方文档。
collections.namedtuple(typename, field_names, *, verbose=False, rename=False, module=None)¶
- typename: 代表新建的一个元组的名字。
- field_names: 是元组的内容,是一个类似list的[‘x’,‘y’]
例如:
SSDParams = namedtuple('SSDParameters', ['img_shape',
'num_classes',
'no_annotation_label',
'feat_layers',
'feat_shapes',
'anchor_size_bounds',
'anchor_sizes',
'anchor_ratios',
'anchor_steps',
'anchor_offset',
'normalizations',
'prior_scaling'
])
default_params = SSDParams(
img_shape=(300, 300),
num_classes=21,
no_annotation_label=21,
feat_layers=['block4', 'block7', 'block8', 'block9', 'block10', 'block11'],
feat_shapes=[(38, 38), (19, 19), (10, 10), (5, 5), (3, 3), (1, 1)],
anchor_size_bounds=[0.15, 0.90],
anchor_sizes=[(21., 45.),
(45., 99.),
(99., 153.),
(153., 207.),
(207., 261.),
(261., 315.)],
anchor_ratios=[[2, .5],
[2, .5, 3, 1./3],
[2, .5, 3, 1./3],
[2, .5, 3, 1./3],
[2, .5],
[2, .5]],
anchor_steps=[8, 16, 32, 64, 100, 300],
anchor_offset=0.5,
normalizations=[20, -1, -1, -1, -1, -1],
prior_scaling=[0.1, 0.1, 0.2, 0.2]
)
ssd_params = default_params._replace(num_classes=FLAGS.num_classes)