可视化CNN
来源:互联网 发布:中兴网络机顶盒怎么用 编辑:程序博客网 时间:2024/06/05 20:04
reference:
https://github.com/yosinski/deep-visualization-toolbox
caffe配置使用OpenBLAS
http://wxyblog.com/2015/08/27/ubuntu-caffe-openblas/
knowleage:
BLAS:(Basic Linear Algebra Subprograms)
http://yufeigan.github.io/2014/12/14/Caffe%E5%AD%A6%E4%B9%A0%E7%AC%94%E8%AE%B04-caffe%E5%AE%89%E8%A3%85%E9%9C%80%E8%A6%81%E6%B3%A8%E6%84%8F%E7%9A%84libraries/
一、install caffe.
reference:
http://caffe.berkeleyvision.org/install_apt.html
1. 安装依赖
sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler
sudo apt-get install --no-install-recommends libboost-all-dev
2.安装OPENBLAS
sudo apt-get install libopenblas-dev
#sudo apt-get install libatlas-base-dev #也可以安装ATLAS,但是不支持CPU多线程
#或者安装MKL (Intel MKL:Intel Math Kernel Library,英特尔数学核心函数库,收费)
3.安装ubuntu 14版本的依赖库
sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
sudo apt-get install python-opencv scipy python-skimage
4.download and compile caffe
git clone https://github.com/BVLC/caffe.git
cd caffe
git remote add yosinski https://github.com/yosinski/caffe.git
git fetch --all
git checkout --track -b deconv-deep-vis-toolbox yosinski/deconv-deep-vis-toolbox
< edit Makefile.config to suit your system if not already done in Step 0
BLAS := atlas 改为 BLAS := open
CPU_ONLY := 1>
make clean
make -j
make -j pycaffe
5. Download and configure Deep Visualization Toolbox code
$ git clone https://github.com/yosinski/deep-visualization-toolbox
$ cd deep-visualization-toolbox
$ cp models/caffenet-yos/settings_local.template-caffenet-yos.py settings_local.py
$ vi settings_local.py
/*设置caffevis_caffe_root 路径到caffe 安装路径*/
/* (downloads a 230MB model and 1.1GB of jpgs to show as visualization): */
$ cd models/caffenet-yos/
$ ./fetch.sh
$ cd ../..
或者
Rerun as "./fetch.sh all" to also fetch fc6 and fc7 unit visualizations (Warning: 4.5G more)
6.Run it!
$ ./run_toolbox.py
7. 验证caffe安装成功,训练mnist 数据集
# cd ~/caffe
# sudo sh data/mnist/get_mnist.sh
# sudo sh examples/mnist/create_mnist.sh
# sudo vi examples/mnist/lenet_solver.prototxt
将最后一行的solver_mode:GPU改为solver_mode:CPU
# sudo sh examples/mnist/train_lenet.sh
三、问题:
1、sudo apt-get install libprotobuf-dev
Reading package lists... Error!
E: Unable to parse package file /var/lib/apt/lists/cn.archive.ubuntu.com_ubuntu_dists_trusty_multiverse_i18n_Translation-en%5fUS (1)
E: The package lists or status file could not be parsed or opened.
解决方案:
sudo rm -r /var/lib/apt/lists/*
sudo apt-get update
四、模型研究:
1. model:
deep-visualization-toolbox-master\models\caffenet-yos\caffenet-yos-deploy.prototxt
input 227 X 227 X 3 out: 1 3 227 227 (154587)
conv1 kernel(11 X 11 X 3) channel 96 out: 1 96 55 55 (290400)
pool1 (3 X 3) 96 out: 1 96 27 27 (69984)
conv2 kernel (5 X 5 X 96) channel 256 out: 1 96 27 27 (69984)
pool2 (3 X 3) out: 1 256 13 13 (43264)
conv3 kernel (3 X 3 X 256) channel 384 out: 1 384 13 13 (64896)
conv4 kernel (3 X 3 X 384) channel 384 out: 1 384 13 13 (64896)
conv5 kernel (3 X 3 X 384) channel 256 out: 1 256 13 13 (43264)
pool5 (3 X 3) out: 1 256 6 6 (9216)
fc6 output 4096 out: 1 4096 (4096)
fc7 output 4096 out: 1 4096 (4096)
fc8 output 1000 out: 1 1000 (1000)
2.输入操作
o: next layer
u: previous layer
s: color
e: load next file
w: load previous file
z: cycle zooming
c: toggle between camera and file
https://github.com/yosinski/deep-visualization-toolbox
caffe配置使用OpenBLAS
http://wxyblog.com/2015/08/27/ubuntu-caffe-openblas/
knowleage:
BLAS:(Basic Linear Algebra Subprograms)
http://yufeigan.github.io/2014/12/14/Caffe%E5%AD%A6%E4%B9%A0%E7%AC%94%E8%AE%B04-caffe%E5%AE%89%E8%A3%85%E9%9C%80%E8%A6%81%E6%B3%A8%E6%84%8F%E7%9A%84libraries/
一、install caffe.
reference:
http://caffe.berkeleyvision.org/install_apt.html
1. 安装依赖
sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler
sudo apt-get install --no-install-recommends libboost-all-dev
2.安装OPENBLAS
sudo apt-get install libopenblas-dev
#sudo apt-get install libatlas-base-dev #也可以安装ATLAS,但是不支持CPU多线程
#或者安装MKL (Intel MKL:Intel Math Kernel Library,英特尔数学核心函数库,收费)
3.安装ubuntu 14版本的依赖库
sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
sudo apt-get install python-opencv scipy python-skimage
4.download and compile caffe
git clone https://github.com/BVLC/caffe.git
cd caffe
git remote add yosinski https://github.com/yosinski/caffe.git
git fetch --all
git checkout --track -b deconv-deep-vis-toolbox yosinski/deconv-deep-vis-toolbox
< edit Makefile.config to suit your system if not already done in Step 0
BLAS := atlas 改为 BLAS := open
CPU_ONLY := 1>
make clean
make -j
make -j pycaffe
5. Download and configure Deep Visualization Toolbox code
$ git clone https://github.com/yosinski/deep-visualization-toolbox
$ cd deep-visualization-toolbox
$ cp models/caffenet-yos/settings_local.template-caffenet-yos.py settings_local.py
$ vi settings_local.py
/*设置caffevis_caffe_root 路径到caffe 安装路径*/
/* (downloads a 230MB model and 1.1GB of jpgs to show as visualization): */
$ cd models/caffenet-yos/
$ ./fetch.sh
$ cd ../..
或者
Rerun as "./fetch.sh all" to also fetch fc6 and fc7 unit visualizations (Warning: 4.5G more)
6.Run it!
$ ./run_toolbox.py
7. 验证caffe安装成功,训练mnist 数据集
# cd ~/caffe
# sudo sh data/mnist/get_mnist.sh
# sudo sh examples/mnist/create_mnist.sh
# sudo vi examples/mnist/lenet_solver.prototxt
将最后一行的solver_mode:GPU改为solver_mode:CPU
# sudo sh examples/mnist/train_lenet.sh
三、问题:
1、sudo apt-get install libprotobuf-dev
Reading package lists... Error!
E: Unable to parse package file /var/lib/apt/lists/cn.archive.ubuntu.com_ubuntu_dists_trusty_multiverse_i18n_Translation-en%5fUS (1)
E: The package lists or status file could not be parsed or opened.
解决方案:
sudo rm -r /var/lib/apt/lists/*
sudo apt-get update
四、模型研究:
1. model:
deep-visualization-toolbox-master\models\caffenet-yos\caffenet-yos-deploy.prototxt
input 227 X 227 X 3 out: 1 3 227 227 (154587)
conv1 kernel(11 X 11 X 3) channel 96 out: 1 96 55 55 (290400)
pool1 (3 X 3) 96 out: 1 96 27 27 (69984)
conv2 kernel (5 X 5 X 96) channel 256 out: 1 96 27 27 (69984)
pool2 (3 X 3) out: 1 256 13 13 (43264)
conv3 kernel (3 X 3 X 256) channel 384 out: 1 384 13 13 (64896)
conv4 kernel (3 X 3 X 384) channel 384 out: 1 384 13 13 (64896)
conv5 kernel (3 X 3 X 384) channel 256 out: 1 256 13 13 (43264)
pool5 (3 X 3) out: 1 256 6 6 (9216)
fc6 output 4096 out: 1 4096 (4096)
fc7 output 4096 out: 1 4096 (4096)
fc8 output 1000 out: 1 1000 (1000)
2.输入操作
o: next layer
u: previous layer
s: color
e: load next file
w: load previous file
z: cycle zooming
c: toggle between camera and file
阅读全文
0 0
- CNN可视化
- 可视化CNN
- Caffe CNN特征可视化
- Caffe CNN特征可视化
- CNN 可视化结果分析
- 可视化CNN卷积神经网络
- Caffe CNN特征可视化
- Caffe CNN特征可视化
- CNN中feature map可视化
- Tensorflow cnn网络 vgg可视化
- cnn神经网络卷积层可视化
- CNN 学习系列之 perdict 以及可视化
- 可视化CNN卷积神经网络-- 之二
- 基于DeepStream的CNN的可视化理解
- Deep Visualization:可视化并理解CNN
- Deep Visualization:可视化并理解CNN
- caffe中如何可视化cnn各层的输出
- caffe中如何可视化cnn各层的输出
- dd
- CSS中的单位
- java设计模式之单例模式
- SpringBoot创建MVC网站
- 快速排序
- 可视化CNN
- Unity3d 物体速度快直接穿透墙体没有发生碰撞怎么办?
- CAS 交互流程
- hbase 和 hive 学习
- 计算机网络通讯
- HDU 4614 线段树(区间更新)+二分
- hdu 4635(tarjan)
- 每日MySQL之013:TIMESTAMP和DATETIME列的自动初始化与自动更新
- 秒速五厘米(为情怀而补的题)