博文

如何在caffe中添加新类型的layer

热度 1 2014-12-11 16:47

参考： https://github.com/BVLC/caffe/issues/684 Add a class declaration for your layer to the appropriate one of common_layers.hpp,data_layers.hpp, loss_layers.hpp, neuron_layers.hpp, or vision_layers.hpp. Include an inline implementation of type and the *Blobs() methods to specify ...

个人分类: Caffe|14837 次阅读|1 个评论 热度 1

DIY Deep Learning for Vision- a Hands-On Tutorial with Caffe

2014-11-17 22:58

Examples: Logistic Regression (in Python): http://nbviewer.ipython.org/github/BVLC/caffe/blob/dev/examples/hdf5_classification.ipynb Learn LeNet on MNIST: http://caffe.berkeleyvision.org/gathered/examples/mnist.html Fine-tuning CaffeNet for Style Recognition ...

个人分类: Caffe|11352 次阅读|没有评论

Caffe 实例测试一： MNIST

热度 1 2014-11-13 19:19

参考： http://caffe.berkeleyvision.org/gathered/examples/mnist.html 原笔记在印象笔记中，复制过来格式就乱了，原笔记地址： http://app.yinxiang.com/l/AARGaZ2rlLdEn7ikhvPcGA7hd7_EnB2OlIo/ caffe安装目录：home/user/caffe-master cd caffe-master download MNIST dataset 注意：新版caff ...

个人分类: Caffe|27629 次阅读|1 个评论 热度 1

Ubuntu+CUDA6.5+Caffe安装配置汇总

热度 3 2014-11-7 17:23

感谢欧新宇的分享，此配置贴大部分参考他的博客。 http://ouxinyu.github.io/Blogs/20140723001.html 此贴历经坎坷，一入DL深似海啊，配个caffe玩玩足足折腾了我半个多月，就在我想放弃之时，峰回路转，成功了，其中心酸只有自己知道啊。起初安装ubuntu因为引导问题折腾了一三天左右 ...

个人分类: Caffe|39616 次阅读|4 个评论 热度 3

Coursera: Neural Networks for ML- Lecture 14

2014-8-19 06:51

DBN(信息量较大) 2006_Hinton_A fast learning algorithm for deep belief nets 2006_Science_Reducing the Dimensionality of data with neural networks 2009_The difficulty of training deep architectures and the effect of unsupervised pre-training ICML2010_Rectified Linear Units Improve Restricte ...

个人分类: Coursera: Neural Networks|3880 次阅读|没有评论

本页有 5 篇博文因作者的隐私设置或未通过审核而隐藏