| ttest |
| #http://www.cnblogs.com/hhh5460/p/4304628.html | |
| import math | |
| import random | |
| import string | |
| random.seed(0) | |
| # 生成区间[a, b)内的随机数 | |
| def rand(a, b): |
本步骤能实现用Intel核芯显卡来进行显示， 用NVIDIA GPU进行计算。
安装开发所需要的一些基本包
sudo apt-get install build-essential # basic requirement
sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libboost-all-dev libhdf5-serial-dev libgflags-dev libgoogle-glog-dev liblmdb-dev protobuf-compiler #required by caffe
Our goal is to run python -c "import caffe" without crashing. For anyone who doesn't spend most of their time with build systems, getting to this point can be extremely difficult on OS X. Instead of providing a list of steps to follow, I'll try to epxlain why each step happens.
This page has OS X specific install instructions.
I assume:
| """ | |
| Multiclass SVMs (Crammer-Singer formulation). | |
| A pure Python re-implementation of: | |
| Large-scale Multiclass Support Vector Machine Training via Euclidean Projection onto the Simplex. | |
| Mathieu Blondel, Akinori Fujino, and Naonori Ueda. | |
| ICPR 2014. | |
| http://www.mblondel.org/publications/mblondel-icpr2014.pdf | |
| """ |
| # VGG 16-layer network convolutional finetuning | |
| # Network modified to have smaller receptive field (128 pixels) | |
| # nand smaller stride (8 pixels) when run in convolutional mode. | |
| # | |
| # In this model we also change max pooling size in the first 4 layers | |
| # from 2 to 3 while retaining stride = 2 | |
| # which makes it easier to exactly align responses at different layers. | |
| # | |
| # For alignment to work, we set (we choose 32x so as to be able to evaluate | |
| # the model for all different subsampling sizes): |
| name: "deeplabv2_resnet101_test" | |
| layer { | |
| name: "data" | |
| type: "ImageSegData" | |
| top: "data" | |
| top: "label" | |
| top: "data_dim" | |
| include { | |
| phase: TEST |
| name: "deeplabv2_resnet101_deploy" | |
| layers { | |
| name: "data" | |
| type: MEMORY_DATA | |
| top: "data" | |
| top: "label" | |
| top: "data_dim" | |
| memory_data_param { |
| name: "deeplabv2_resnet101_train" | |
| layer { | |
| name: "data" | |
| type: "ImageSegData" | |
| top: "data" | |
| top: "label" | |
| #top: "data_dim" | |
| include { | |
| phase: TRAIN |
| # VGG 16-layer network convolutional finetuning | |
| # Network modified to have smaller receptive field (128 pixels) | |
| # nand smaller stride (8 pixels) when run in convolutional mode. | |
| # | |
| # In this model we also change max pooling size in the first 4 layers | |
| # from 2 to 3 while retaining stride = 2 | |
| # which makes it easier to exactly align responses at different layers. | |
| # | |
| # For alignment to work, we set (we choose 32x so as to be able to evaluate | |
| # the model for all different subsampling sizes): |