Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
honghuCode committed Jun 12, 2018
1 parent 73bd703 commit b5f1f5a
Showing 1 changed file with 6 additions and 6 deletions.
12 changes: 6 additions & 6 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
## update 5.17
### update 5.17
### 采用insightface作者训练的mobileFaceNet
### https://github.com/deepinsight/insightface/issues/214
#### training dataset: ms1m
Expand All @@ -10,10 +10,10 @@


##### ====================================
1.VS2015下 选择X64 Release模式,运行即可。opencv、ncnn依赖都已经自动配置。
2.直接解压lfw-112X112.zip文件,可计算lfw数据集中同一张脸和不同脸的得分。
##### 1.VS2015下 选择X64 Release模式,运行即可。opencv、ncnn依赖都已经自动配置。
##### 2.直接解压lfw-112X112.zip文件,可计算lfw数据集中同一张脸和不同脸的得分。

##### TODO ############
1.将mxnet的模型转换为caffe模型 。
2.将BN层和卷积层合并(提高速度)参考: https://github.com/chuanqi305/MobileNet-SSD/blob/master/merge_bn.py
3.将caffe模型转换为ncnn模型。
##### 1.将mxnet的模型转换为caffe模型 。
##### 2.将BN层和卷积层合并(提高速度)参考: https://github.com/chuanqi305/MobileNet-SSD/blob/master/merge_bn.py
##### 3.将caffe模型转换为ncnn模型。

0 comments on commit b5f1f5a

Please sign in to comment.