FSRCNN网络资源学习（Fast Region-based Convolutional Network）

FSRCNN（Fast Region-based Convolutional Network）

参考:
https://arxiv.org/pdf/1608.00367v1.pdf Accelerating the Super-Resolution Convolutional Neural Networks (ECCV 2016)

1. FSRCNN放在 Caffe/examples/下

2. 运行generate_train.m和generate_test.m

生成hdf5文件：

generate_train.m

clear; close all;%% settingsfolder = 'Train/General-100';%savepath = 'train.h5';%size_input = 11;% There are 4 pixels padding. Paper presents 7size_label = 19;% (11-4) *3 - (3-1)scale = 3;stride = 4;%% initializationdata = zeros(size_input, size_input, 1, 1);label = zeros(size_label, size_label, 1, 1);padding = abs(size_input - size_label)/2;count = 0;%% generate datafilepaths = dir(fullfile(folder,'*.bmp'));for i = 1 : length(filepaths)    image = imread(fullfile(folder, filepaths(i).name));    image = rgb2ycbcr(image);    image = im2double(image(:, :, 1));    im_label = modcrop(image, scale);    im_input = imresize(im_label, 1/scale, 'bicubic');    [hei,wid] = size(im_input);    for x = 1 : stride : hei - size_input + 1        for y = 1 : stride : wid - size_input + 1            locx = scale * (x + floor((size_input - 1)/2)) - floor((size_label + scale)/2 - 1);            locy = scale * (y + floor((size_input - 1)/2)) - floor((size_label + scale)/2 - 1);            subim_input = im_input(x : size_input + x - 1, y : size_input + y - 1);            subim_label = im_label(locx : size_label + locx - 1, locy : size_label + locy - 1);            count = count + 1;            data(:, :, 1, count) = subim_input;            label(:, :, 1, count) = subim_label;        end    endendorder = randperm(count);data = data(:, :, 1, order);label = label(:, :, 1, order); %% writing to HDF5chunksz = 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);endh5disp(savepath);

3.
运行./build/tools/caffe train –solver examples/FSRCNN/FSRCNN_solver.prototxt
问题：

I1208 11:11:17.523556  2658 layer_factory.hpp:77] Creating layer dataI1208 11:11:17.524196  2658 net.cpp:100] Creating Layer dataI1208 11:11:17.524271  2658 net.cpp:408] data -> dataI1208 11:11:17.524309  2658 net.cpp:408] data -> labelI1208 11:11:17.524338  2658 hdf5_data_layer.cpp:79] Loading list of HDF5 filenames from: examples/FSRCNN/train.txtI1208 11:11:17.524843  2658 hdf5_data_layer.cpp:93] Number of HDF5 files: 1HDF5-DIAG: Error detected in HDF5 (1.8.15-patch1) thread 140052527355712:  #000: ../../../src/H5F.c line 604 in H5Fopen(): unable to open file    major: File accessibilty    minor: Unable to open file  #001: ../../../src/H5Fint.c line 990 in H5F_open(): unable to open file: time = Thu Dec  8 11:11:17 2016, name = 'examples/FSRCNN/train.h5', tent_flags = 0    major: File accessibilty    minor: Unable to open file  #002: ../../../src/H5FD.c line 993 in H5FD_open(): open failed    major: Virtual File Layer    minor: Unable to initialize object  #003: ../../../src/H5FDsec2.c line 343 in H5FD_sec2_open(): unable to open file: name = 'examples/FSRCNN/train.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0    major: File accessibilty    minor: Unable to open fileF1208 11:11:17.579452  2658 hdf5_data_layer.cpp:31] Failed opening HDF5 file: examples/FSRCNN/train.h5*** Check failure stack trace: ***    @     0x7f60848805cd  google::LogMessage::Fail()    @     0x7f6084882433  google::LogMessage::SendToLog()    @     0x7f608488015b  google::LogMessage::Flush()    @     0x7f6084882e1e  google::LogMessageFatal::~LogMessageFatal()    @     0x7f6084cac2e3  caffe::HDF5DataLayer<>::LoadHDF5FileData()    @     0x7f6084ca7b27  caffe::HDF5DataLayer<>::LayerSetUp()    @     0x7f6084db90af  caffe::Net<>::Init()    @     0x7f6084dba931  caffe::Net<>::Net()    @     0x7f6084d978ea  caffe::Solver<>::InitTrainNet()    @     0x7f6084d98c67  caffe::Solver<>::Init()    @     0x7f6084d9900a  caffe::Solver<>::Solver()    @     0x7f6084c18fd3  caffe::Creator_SGDSolver<>()    @           0x40a569  train()    @           0x407060  main    @     0x7f60837f0ac0  __libc_start_main    @           0x407889  _start    @              (nil)  (unknown)Aborted (core dumped)

解决：
添加：
train.h5 test.h5 （Matlab2016a生成）

训练中：

~/caffe$ ./build/tools/caffe train --solver examples/FSRCNN/FSRCNN_solver.prototxtI1208 19:20:04.535562  3428 caffe.cpp:210] Use CPU.I1208 19:20:04.536381  3428 solver.cpp:48] Initializing solver from parameters: test_iter: 231test_interval: 5000base_lr: 0.001display: 100max_iter: 10000000lr_policy: "fixed"momentum: 0.9weight_decay: 0snapshot: 100000snapshot_prefix: "examples/FSRCNN/N-56-12-4"solver_mode: CPUnet: "examples/FSRCNN/FSRCNN_net.prototxt"train_state {  level: 0  stage: ""}I1208 19:20:04.536700  3428 solver.cpp:91] Creating training net from net file: examples/FSRCNN/FSRCNN_net.prototxtI1208 19:20:04.537152  3428 net.cpp:322] The NetState phase (0) differed from the phase (1) specified by a rule in layer dataI1208 19:20:04.537380  3428 net.cpp:58] Initializing net from parameters: name: "SR_test"state {  phase: TRAIN  level: 0  stage: ""}layer {  name: "data"  type: "HDF5Data"  top: "data"  top: "label"  include {    phase: TRAIN  }  hdf5_data_param {    source: "examples/FSRCNN/train.txt"    batch_size: 128  }}layer {  name: "conv1"  type: "Convolution"  bottom: "data"  top: "conv1"  param {    lr_mult: 1  }  param {    lr_mult: 0.1  }  convolution_param {    num_output: 56    pad: 0    kernel_size: 5    stride: 1    weight_filler {      type: "gaussian"      std: 0.0378    }    bias_filler {      type: "constant"      value: 0    }  }}layer {  name: "relu1"  type: "PReLU"  bottom: "conv1"  top: "conv1"  prelu_param {    channel_shared: true  }}layer {  name: "conv2"  type: "Convolution"  bottom: "conv1"  top: "conv2"  param {    lr_mult: 1  }  param {    lr_mult: 0.1  }  convolution_param {    num_output: 12    pad: 0    kernel_size: 1    group: 1    stride: 1    weight_filler {      type: "gaussian"      std: 0.3536    }    bias_filler {      type: "constant"      value: 0    }  }}layer {  name: "relu2"  type: "PReLU"  bottom: "conv2"  top: "conv2"  prelu_param {    channel_shared: true  }}layer {  name: "conv22"  type: "Convolution"  bottom: "conv2"  top: "conv22"  param {    lr_mult: 1  }  param {    lr_mult: 0.1  }  convolution_param {    num_output: 12    pad: 1    kernel_size: 3    group: 1    stride: 1    weight_filler {      type: "gaussian"      std: 0.1179    }    bias_filler {      type: "constant"      value: 0    }  }}layer {  name: "relu22"  type: "PReLU"  bottom: "conv22"  top: "conv22"  prelu_param {    channel_shared: true  }}layer {  name: "conv23"  type: "Convolution"  bottom: "conv22"  top: "conv23"  param {    lr_mult: 1  }  param {    lr_mult: 0.1  }  convolution_param {    num_output: 12    pad: 1    kernel_size: 3    group: 1    stride: 1    weight_filler {      type: "gaussian"      std: 0.1179    }    bias_filler {      type: "constant"      value: 0    }  }}layer {  name: "relu23"  type: "PReLU"  bottom: "conv23"  top: "conv23"  prelu_param {    channel_shared: true  }}layer {  name: "conv24"  type: "Convolution"  bottom: "conv23"  top: "conv24"  param {    lr_mult: 1  }  param {    lr_mult: 0.1  }  convolution_param {    num_output: 12    pad: 1    kernel_size: 3    group: 1    stride: 1    weight_filler {      type: "gaussian"      std: 0.1179    }    bias_filler {      type: "constant"      value: 0    }  }}layer {  name: "relu24"  type: "PReLU"  bottom: "conv24"  top: "conv24"  prelu_param {    channel_shared: true  }}layer {  name: "conv25"  type: "Convolution"  bottom: "conv24"  top: "conv25"  param {    lr_mult: 1  }  param {    lr_mult: 0.1  }  convolution_param {    num_output: 12    pad: 1    kernel_size: 3    group: 1    stride: 1    weight_filler {      type: "gaussian"      std: 0.1179    }    bias_filler {      type: "constant"      value: 0    }  }}layer {  name: "relu25"  type: "PReLU"  bottom: "conv25"  top: "conv25"  prelu_param {    channel_shared: true  }}layer {  name: "conv26"  type: "Convolution"  bottom: "conv25"  top: "conv26"  param {    lr_mult: 1  }  param {    lr_mult: 0.1  }  convolution_param {    num_output: 56    pad: 0    kernel_size: 1    group: 1    stride: 1    weight_filler {      type: "gaussian"      std: 0.189    }    bias_filler {      type: "constant"      value: 0    }  }}layer {  name: "relu26"  type: "PReLU"  bottom: "conv26"  top: "conv26"  prelu_param {    channel_shared: true  }}layer {  name: "conv3"  type: "Deconvolution"  bottom: "conv26"  top: "conv3"  param {    lr_mult: 0.1  }  param {    lr_mult: 0.1  }  convolution_param {    num_output: 1    pad: 4    kernel_size: 9    stride: 3    weight_filler {      type: "gaussian"      std: 0.001    }    bias_filler {      type: "constant"      value: 0    }  }}layer {  name: "loss"  type: "EuclideanLoss"  bottom: "conv3"  bottom: "label"  top: "loss"}I1208 19:20:04.539083  3428 layer_factory.hpp:77] Creating layer dataI1208 19:20:04.539145  3428 net.cpp:100] Creating Layer dataI1208 19:20:04.539166  3428 net.cpp:408] data -> dataI1208 19:20:04.539196  3428 net.cpp:408] data -> labelI1208 19:20:04.539242  3428 hdf5_data_layer.cpp:79] Loading list of HDF5 filenames from: examples/FSRCNN/train.txtI1208 19:20:04.539290  3428 hdf5_data_layer.cpp:93] Number of HDF5 files: 1I1208 19:20:04.540756  3428 hdf5.cpp:32] Datatype class: H5T_FLOATI1208 19:20:04.676849  3428 net.cpp:150] Setting up dataI1208 19:20:04.676926  3428 net.cpp:157] Top shape: 128 1 11 11 (15488)I1208 19:20:04.676942  3428 net.cpp:157] Top shape: 128 1 19 19 (46208)I1208 19:20:04.676959  3428 net.cpp:165] Memory required for data: 246784I1208 19:20:04.676972  3428 layer_factory.hpp:77] Creating layer conv1I1208 19:20:04.677001  3428 net.cpp:100] Creating Layer conv1I1208 19:20:04.677034  3428 net.cpp:434] conv1 <- dataI1208 19:20:04.677062  3428 net.cpp:408] conv1 -> conv1I1208 19:20:04.677525  3428 net.cpp:150] Setting up conv1I1208 19:20:04.677563  3428 net.cpp:157] Top shape: 128 56 7 7 (351232)I1208 19:20:04.677573  3428 net.cpp:165] Memory required for data: 1651712I1208 19:20:04.677599  3428 layer_factory.hpp:77] Creating layer relu1I1208 19:20:04.677630  3428 net.cpp:100] Creating Layer relu1I1208 19:20:04.677644  3428 net.cpp:434] relu1 <- conv1I1208 19:20:04.677654  3428 net.cpp:395] relu1 -> conv1 (in-place)I1208 19:20:04.677721  3428 net.cpp:150] Setting up relu1I1208 19:20:04.677753  3428 net.cpp:157] Top shape: 128 56 7 7 (351232)I1208 19:20:04.677762  3428 net.cpp:165] Memory required for data: 3056640I1208 19:20:04.677786  3428 layer_factory.hpp:77] Creating layer conv2I1208 19:20:04.677816  3428 net.cpp:100] Creating Layer conv2I1208 19:20:04.677826  3428 net.cpp:434] conv2 <- conv1I1208 19:20:04.677839  3428 net.cpp:408] conv2 -> conv2I1208 19:20:04.677873  3428 net.cpp:150] Setting up conv2I1208 19:20:04.677903  3428 net.cpp:157] Top shape: 128 12 7 7 (75264)I1208 19:20:04.677914  3428 net.cpp:165] Memory required for data: 3357696I1208 19:20:04.677932  3428 layer_factory.hpp:77] Creating layer relu2I1208 19:20:04.677942  3428 net.cpp:100] Creating Layer relu2I1208 19:20:04.677953  3428 net.cpp:434] relu2 <- conv2I1208 19:20:04.677961  3428 net.cpp:395] relu2 -> conv2 (in-place)I1208 19:20:04.677976  3428 net.cpp:150] Setting up relu2I1208 19:20:04.678004  3428 net.cpp:157] Top shape: 128 12 7 7 (75264)I1208 19:20:04.678015  3428 net.cpp:165] Memory required for data: 3658752I1208 19:20:04.678025  3428 layer_factory.hpp:77] Creating layer conv22I1208 19:20:04.678041  3428 net.cpp:100] Creating Layer conv22I1208 19:20:04.678050  3428 net.cpp:434] conv22 <- conv2I1208 19:20:04.678061  3428 net.cpp:408] conv22 -> conv22I1208 19:20:04.678098  3428 net.cpp:150] Setting up conv22I1208 19:20:04.678128  3428 net.cpp:157] Top shape: 128 12 7 7 (75264)I1208 19:20:04.678139  3428 net.cpp:165] Memory required for data: 3959808I1208 19:20:04.678153  3428 layer_factory.hpp:77] Creating layer relu22I1208 19:20:04.678163  3428 net.cpp:100] Creating Layer relu22I1208 19:20:04.678171  3428 net.cpp:434] relu22 <- conv22I1208 19:20:04.678184  3428 net.cpp:395] relu22 -> conv22 (in-place)I1208 19:20:04.678198  3428 net.cpp:150] Setting up relu22I1208 19:20:04.678400  3428 net.cpp:157] Top shape: 128 12 7 7 (75264)

data_aug.m

clear; %% To do data augmentationfolder = 'Train/General-100';savepath = 'Train/General-100-aug/';filepaths = dir(fullfile(folder,'*.bmp'));for i = 1 : length(filepaths)    filename = filepaths(i).name;    [add, im_name, type] = fileparts(filepaths(i).name);    image = imread(fullfile(folder, filename));    for angle = 0: 90 :270        im_rot = rot90(image, angle);        imwrite(im_rot, [savepath im_name, '_rot' num2str(angle) '.bmp']);        for scale = 0.6 : 0.1 :0.9            im_down = imresize(im_rot, scale, 'bicubic');            imwrite(im_down, [savepath im_name, '_rot' num2str(angle) '_s' num2str(scale*10) '.bmp']);        end    endend

下载代码：
http://download.csdn.net/detail/forest_world/9705982

参考资料：
http://blog.csdn.net/zuolunqiang/article/details/52411673 super-resolution技术日记——FSRCNN