SRCNN
所属分类：人工智能/神经网络/深度学习
开发工具：C/C++
文件大小：5KB
下载次数：5
上传日期：2018-11-02 11:45:57
上 传 者：
夏雪风雷
说明： 超分辨率开山之作，SRCNN的源代码，大神汤晓鸥参与研究的，对做超分辨率领域的朋友很有帮助
(Super resolution pioneering, SRCNN source code)
文件列表:
SRCNN\generate_test.m (1771, 2015-07-08)
SRCNN\generate_train.m (1769, 2015-07-08)
SRCNN\modcrop.m (279, 2015-03-17)
SRCNN\saveFilters.m (1318, 2015-07-01)
SRCNN\SRCNN_mat.prototxt (1478, 2015-07-01)
SRCNN\SRCNN_net.prototxt (1705, 2015-07-01)
SRCNN\SRCNN_solver.prototxt (566, 2015-07-01)
SRCNN\store2hdf5.m (2897, 2015-06-05)
SRCNN\test.txt (23, 2015-07-01)
SRCNN\train.txt (24, 2015-07-01)
SRCNN (0, 2018-11-02)
***********************************************************************************************************
Training code for "Learning a Deep Convolutional Network for Image Super-Resolution" (ECCV 2014)
and "Image Super-Resolution Using Deep Convolutional Networks" (TPAMI 2015)
by Chao Dong (ndc.forward@gmail.com)
***********************************************************************************************************
Usage:
1. Place the "SRCNN" folder into "($Caffe_Dir)/examples/"
2. Open MATLAB and direct to ($Caffe_Dir)/example/SRCNN, run
"generate_train.m" and "generate_test.m" to generate training and test data.
3. To train our SRCNN, run
./build/tools/caffe train --solver examples/SRCNN/SRCNN_solver.prototxt
4. After training, you can extract parameters from the caffe model and save them in the format that can be used in our test package (SRCNN_v1). To do this, you need to install mat-caffe first, then open MATLAB and direct to ($Caffe_Dir) and run "saveFilters.m". The "($Caffe_Dir)/examples/SRCNN/x3.mat" will be there for you.
近期下载者：
相关文件：
收藏者：