自定义博客皮肤VIP专享

*博客头图:

格式为PNG、JPG,宽度*高度大于1920*100像素,不超过2MB,主视觉建议放在右侧,请参照线上博客头图

请上传大于1920*100像素的图片!

博客底图:

图片格式为PNG、JPG,不超过1MB,可上下左右平铺至整个背景

栏目图:

图片格式为PNG、JPG,图片宽度*高度为300*38像素,不超过0.5MB

主标题颜色:

RGB颜色,例如:#AFAFAF

Hover:

RGB颜色,例如:#AFAFAF

副标题颜色:

RGB颜色,例如:#AFAFAF

自定义博客皮肤

-+
  • 博客(4)
  • 收藏
  • 关注

原创 The NaN values

The NaN values are used to identify undefined or non-representable values for floating-point elements, such as the square root of negative numbers or the result of 0/020.5.2 Infinity and NaN

2016-07-30 10:00:57 582

转载 caffe loss NaN

by Yangqing on 14 May 2014For a sanity check, try running with a learning rate 0 to see if any nan errors pop up (they shouldn’t, since no learning takes place). If data is not initialized well, it mig

2016-07-22 22:17:40 1084

原创 matlab 读取图片的格式

dlib::shape_predictor , dlib::full_object_detection 是dlib里面的两个两个类,最近在做一个人脸的项目的时候需要用到它们,也是第一次使用Dlib,感觉这是一个比较新的一个开源机器学习库。本人也是刚开始学习,后续会更新先上一段源码,shape_predictor:class shape_predictor { /*!

2016-07-17 18:19:27 5967

原创 What is zero-shot learning?

Zero-shot learning is being able to solve a task despite not having received any training examples of that task. For a concrete example, imagine recognizing a category of object in photos without ever

2016-07-13 14:38:38 2465

空空如也

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人

提示
确定要删除当前文章?
取消 删除