我有 labelmap.prototxt ,我想将其转换为集合,因为我想将其与Intel Neural Compute Stick SDK一起使用。
输入
home / labelmap.prototxt
self
输出:
item {
name: "none_of_the_above"
label: 0
display_name: "background"
}
item {
name: "1"
label: 1
display_name: "person"
}
item {
name: "2"
label: 2
display_name: "bicycle"
}
item {
name: "3"
label: 3
display_name: "car"
}
我尝试如下:
set(["background","person","bicycle","car"])
答案 0 :(得分:1)
在caffe ssd中,获取有关原型缓冲区的信息,即持久性消息LabelMap,以便您可以从prototxt中读取对象数据。很好 签出代码:
from caffe.proto import caffe_pb2
from google.protobuf import text_format as tf
f = open('labelmap.prototxt', 'r')
lm = caffe_pb2.LabelMap()
lm = tf.Parse(f.read(), lm)
display_names = [x.display_name for x in lm.item]