double-vane

Results 5 issues of double-vane

Hi, when I trained the sphereface-27 with my dataset, I always run into a problem:loss=87.33, and my prototxt as shown below: layer { name: "fc6-" type: "MarginInnerProduct" bottom: "fc5" bottom:...

![0018031_1_4_0](https://user-images.githubusercontent.com/20334378/190096349-0dec50eb-30ad-4719-98ba-23330a203f63.jpg) 识别结果就是 ![1663142462778](https://user-images.githubusercontent.com/20334378/190096518-5da54dfc-ac17-4999-845d-81bf5709007f.png) 请问这样的结果应该从哪里去下手分析

你好,vgg16的tensorflow网络代码在哪里?你的deploy.prototxt里网络层的名称是随便取的吗?

Hi, Does the version of opencv have an impact on this?(uniform_data_layer.cpp)