Skip to content

Instantly share code, notes, and snippets.

View wenfahu's full-sized avatar
🎯
Focusing

Bran Stewart wenfahu

🎯
Focusing
  • Intel
  • Beijing
View GitHub Profile
@wenfahu
wenfahu / inception_bn_triplet_train_val.prototxt
Last active December 21, 2016 08:38
inception triplet face
name: "inception_bn"
layer{
name: 'data'
type: 'Python'
top: 'data'
top: 'label'
python_param {
module: 'data_layer'
layer: 'DataLayer'
}
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

道可道

本服务是一个针对于专业知识领域问答社区, 旨在为相关知识领域创造一个良性,优质,纯粹的交流环境。我们通过严谨合理的机制,为来自各个专业领域的人士提供一个纯粹,高水平的交流平台,让每一位提问者和解惑者从中获得干净,纯粹,优质的体验。

“传道解惑”,不仅仅限于课堂,这里不是课堂的延伸, 这里是求知者的沙龙。我们让每一位来到本站的用户,平等,自由的分享知识。“道可道,非常道”, 我们备好了沙发,咖啡和下午茶,你来定义知识的交流,思维的碰撞。

问答规则

我们为高水平的问题找到高水准的答案,我们拒绝平庸和重复,因而我们为提问与回答环节制定以下规则:

  • 提问
  • 不问重复的问题。 在你提问的过程中,我们针对你问题中的关键词搜索本站已有的问题库,并且对问题本身做智能的语义分析,从问题库中获得同你的提问尽可能相匹配的已有的问题。如果你觉得这些解答仍然不能解决你现在遇到的问题,你便可以继续描述自己的问题状况。
@wenfahu
wenfahu / face_train_test.prototxt
Last active November 26, 2016 05:21
Caffe face center loss train prototxt
name: "Face-ResNet"
layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
name: "Face-ResNet"
layer {
name: "data"
type: "ImageData"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
## inception triplet loss face clasffication
name: "inception_bn_triplet"
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
## inception face clasffication
name: "inception_bn"
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}