使用GPU在caffe上进行CNN训练
1.配置caffe環境
[請參考此篇博客：http://blog.csdn.net/ws_20100/article/details/48850449]
本篇介紹如何在caffe環境下，實現"圖像對圖像"的卷積神經網絡的訓練。
2.文件結構
在配置好的caffe文件夾中，進入examples目錄，創建CNN文件夾，并進入文件夾
$ cd caffe-master/examples/
$ mkdir CNN
$ cd CNN/
在CNN文件夾下面創建子文件夾
$ mkdir model snapshot TestPhotos TestLabels TrainPhotos TrainLabels
其中，
model用于以后存儲卷積核矩陣和偏置向量；
snapshot用于存儲訓練中備份的caffe模型，每一段時間存儲一次，防止斷電等一些情況；
TrainPhotos、TrainLabels分別存儲訓練集輸入和監督樣本；
TestPhotos、TestLabels分別存儲測試集輸入和監督樣本，不直接參與到訓練中。
然后，將訓練所用的輸入樣本和監督樣本分別放入到TrainPhotos和TrainLabels中去。注意，樣本文件名無所謂，但是排列次序必須一一對應。同樣，將測試所用的輸入樣本和監督樣本分別放入到TestPhotos和TestLabels中去。
3.產生訓練和測試數據
1.)產生路徑文件
在CNN文件夾下面(以下均是在此文件夾下)創建兩個路徑文件。
$ vim train.txt
輸入內容：
examples/CNN/train.h5
:wq保存文檔。
$ vim test.txt
輸入內容：
examples/CNN/test.h5
:wq保存文檔。
2.)產生訓練數據
$ vim generate_train.m
輸入內容：(把輸入圖像切成11*11的像素塊，監督圖像為3*3的像素塊(由網絡結構和卷積核大小決定)，步長為1個像素)
clear;close all;%% settings folder_input = 'TrainPhotos'; folder_label = 'TrainLabels'; savepath = 'train.h5'; size_input = 11; size_label = 3; % size_input - 12 stride = 1;%% initialization data = zeros(size_input, size_input, 1, 1); label = zeros(size_label, size_label, 1, 1); padding = abs(size_input - size_label) / 2; count = 0;%% read data filepaths_input = dir(fullfile(folder_input,'*.jpg')); filepaths_label = dir(fullfile(folder_label,'*.jpg'));if (length(filepaths_input)==length(filepaths_label))length = length(filepaths_input); elseerror('The Number of Input is NOT equal to the Number of Label.'); end%% generate data for i = 1 : lengthim_input = imread(fullfile(folder_input,filepaths_input(i).name));im_input = rgb2ycbcr(im_input);im_input = im2double(im_input(:, :, 1));im_label = imread(fullfile(folder_label,filepaths_label(i).name));im_label = im2double(im_label(:, :, 1));if size(im_input) == size(im_label)[hei,wid] = size(im_input);elseerror('The size of input and label are not equal.');endfor x = 1 : stride : hei-size_input+1for y = 1 :stride : wid-size_input+1subim_input = im_input(x : x+size_input-1, y : y+size_input-1);subim_label = im_label(x+padding : x+padding+size_label-1, y+padding : y+padding+size_label-1);count = count + 1;data(:, :, 1, count) = subim_input;label(:, :, 1, count) = subim_label;endendend%% randomized the data and label order = randperm(count); data = data(:, :, 1, order); label = label(:, :, 1, order); %% writing to HDF5 chunksz = 128; created_flag = false; totalct = 0;for batchno = 1:floor(count/chunksz)last_read=(batchno-1)*chunksz;batchdata = data(:,:,1,last_read+1:last_read+chunksz); batchlabs = label(:,:,1,last_read+1:last_read+chunksz);startloc = struct('dat',[1,1,1,totalct+1], 'lab', [1,1,1,totalct+1]);curr_dat_sz = store2hdf5(savepath, batchdata, batchlabs, ~created_flag, startloc, chunksz); created_flag = true;totalct = curr_dat_sz(end); end h5disp(savepath);
終端下輸入：
$ matlab -nodesktop -nosplash -logfile generate_train.log -r generate_train
產生訓練數據train.h5。
3.)產生測試數據
$ vim generate_test.m
generate_test.m只需要將generate_test.m文件開頭改為：
clear;close all;%% settings folder_input = 'TestPhotos'; folder_label = 'TestLabels'; savepath = 'test.h5'; size_input = 11; size_label = 3; stride = 30;
將最后一段改成：
%% writing to HDF5 chunksz = 2; created_flag = false; totalct = 0;for batchno = 1:floor(count/chunksz)last_read=(batchno-1)*chunksz;batchdata = data(:,:,1,last_read+1:last_read+chunksz); batchlabs = label(:,:,1,last_read+1:last_read+chunksz);startloc = struct('dat',[1,1,1,totalct+1], 'lab', [1,1,1,totalct+1]);curr_dat_sz = store2hdf5(savepath, batchdata, batchlabs, ~created_flag, startloc, chunksz); created_flag = true;totalct = curr_dat_sz(end); end h5disp(savepath);
終端下輸入：
$ matlab -nodesktop -nosplash -logfile generate_test.log -r generate_test
產生測試數據test.h5。僅僅用于判斷訓練到達什么地步。
4.建立訓練文件
1.)建立solver文件
$ vim CNN_solver.prototxt
此為運行的配置文件，輸入以下內容：
# The train/test net protocol buffer definition net: "examples/CNN/CNN_net.prototxt" test_iter: 556 # Carry out testing every 500 training iterations. test_interval: 500 # The base learning rate, momentum and the weight decay of the network. base_lr: 0.0001 momentum: 0.9 weight_decay: 0 # The learning rate policy lr_policy: "fixed" # Display every 100 iterations display: 100 # The maximum number of iterations max_iter: 15000000 # snapshot intermediate results snapshot: 500 snapshot_prefix: "examples/CNN/snapshot/CNN" # solver mode: CPU or GPU solver_mode: GPU
:wq保存退出。
2.)建立net文件
$ vim CNN_net.prototxt
此為網絡結構配置文件，可以配置網絡層數，節點數，卷積核等參數。輸入以下內容：
name: "CNN" layer {name: "data"type: "HDF5Data"top: "data"top: "label"hdf5_data_param {source: "examples/CNN/train.txt"batch_size: 128}include: { phase: TRAIN } } layer {name: "data"type: "HDF5Data"top: "data"top: "label"hdf5_data_param {source: "examples/CNN/test.txt"batch_size: 2}include: { phase: TEST } }layer {name: "conv1"type: "Convolution"bottom: "data"top: "conv1"param {lr_mult: 1}param {lr_mult: 0.1}convolution_param {num_output: 128kernel_size: 5stride: 1pad: 0weight_filler {type: "gaussian"std: 0.001}bias_filler {type: "constant"value: 0}} }layer {name: "relu1"type: "ReLU"bottom: "conv1"top: "conv1" }layer {name: "conv2"type: "Convolution"bottom: "conv1"top: "conv2"param {lr_mult: 1}param {lr_mult: 0.1}convolution_param {num_output: 64kernel_size: 3stride: 1pad: 0weight_filler {type: "gaussian"std: 0.001}bias_filler {type: "constant"value: 0}} }layer {name: "relu2"type: "ReLU"bottom: "conv2"top: "conv2" }layer {name: "conv3"type: "Convolution"bottom: "conv2"top: "conv3"param {lr_mult: 0.1}param {lr_mult: 0.1}convolution_param {num_output: 1kernel_size: 3stride: 1pad: 0weight_filler {type: "gaussian"std: 0.001}bias_filler {type: "constant"value: 0}} }layer {name: "loss"type: "EuclideanLoss"bottom: "conv3"bottom: "label"top: "loss" }
:wq保存退出。
5.CNN訓練
$ vim train.sh
輸入以下shell：
#!/bin/bash
cd ../../
./build/tools/caffe train --solver examples/CNN/CNN_solver.prototxt 2>&1 | tee examples/CNN/CNN.log
增加運行權限：
$ chmod +x train.sh
運行腳本文件：
$ ./train.sh
時間可能會運行幾天，也可以提前退出(Ctrl+C)，因為在snapshot中有中間備份存儲。
6.保存濾波器
1.)創建mat文件
$ cp CNN_net.prototxt CNN_mat.prototxt
將CNN_mat.prototxt文件開頭兩個layer段改為：
name: "CNN" input: "data" input_dim: 1 input_dim: 1 input_dim: 11 input_dim: 11input: "label" input_dim: 1 input_dim: 1 input_dim: 3 input_dim: 3
:wq保存即可。
2.)創建M文件
$ vim saveFilters.m
輸入以下內容：(第7行可以更改需要轉換的caffemodel文件名)
caffe.reset_all(); clear; close all; %% settings %folder = 'examples/CNN/'; folder = './'; model = [folder 'CNN_mat.prototxt']; weights = [folder 'snapshot/CNN_iter_550000.caffemodel']; savepath = [folder 'model/x.mat']; layers = 3;%% load model using mat_caffe net = caffe.Net(model,weights,'test');%% reshap parameters weights_conv = cell(layers,1);for idx = 1 : layersconv_filters = net.layers(['conv' num2str(idx)]).params(1).get_data();[~,fsize,channel,fnum] = size(conv_filters);if channel == 1weights = double(ones(fsize^2, fnum));elseweights = double(ones(channel, fsize^2, fnum));endfor i = 1 : channelfor j = 1 : fnumtemp = conv_filters(:,:,i,j);if channel == 1weights(:,j) = temp(:);elseweights(i,:,j) = temp(:);endendendweights_conv{idx} = weights; end%% save parameters weights_conv1 = weights_conv{1}; weights_conv2 = weights_conv{2}; weights_conv3 = weights_conv{3}; biases_conv1 = double(net.layers('conv1').params(2).get_data()); biases_conv2 = double(net.layers('conv2').params(2).get_data()); biases_conv3 = double(net.layers('conv3').params(2).get_data());save(savepath,'weights_conv1','biases_conv1','weights_conv2','biases_conv2','weights_conv3','biases_conv3');
:wq保存。
3.)運行M文件
$ matlab -nodesktop -nosplash -logfile saveFilters.log -r saveFilters
此時，在model中會生成x.mat文件。
7.CNN重構
已經知道了x.mat文件中，有三層卷積層的卷積核矩陣weights_conv*和偏置向量biases_conv*。
編寫一個demo_net.m文件，使用這些參數構建卷積網絡結構，對輸入圖像(矩陣)進行處理，即可得到結果。
不同應用有不同的源碼，這里省略該文件源碼。
本文可能敘述不全面，如有錯誤，歡迎指正！
Enjoy~~
轉載于:https://www.cnblogs.com/lixuebin/p/10814875.html
總結
以上是生活随笔為你收集整理的使用GPU在caffe上进行CNN训练的全部內容，希望文章能夠幫你解決所遇到的問題。
- 上一篇： ReactJS学习笔记八：动画
- 下一篇： solaris 源代码