Adaptive-DeconvNetToolbox

所属分类:图形图像处理
开发工具:matlab
文件大小:13994KB
下载次数:106
上传日期:2013-04-10 14:23:16
上 传 者Zmztt
说明:  自适应卷积网络工具箱,深度学习入门者可以研究看看。
(The Adaptive the convolution Network Toolbox, depth learning beginners can look at the problem.)

文件列表:
DeconvNetToolbox (0, 2011-07-23)
DeconvNetToolbox\Documentation (0, 2011-07-23)
DeconvNetToolbox\Documentation\split_compile_features_8m_source.html (15267, 2011-07-23)
DeconvNetToolbox\Documentation\_s_p_m_2_conv_descriptors_2compilemex_8m_source.html (8979, 2011-07-23)
DeconvNetToolbox\Documentation\move_all2_g_p_u_8m.html (7254, 2011-07-23)
DeconvNetToolbox\Documentation\varying__crosses_8m_source.html (10206, 2011-07-23)
DeconvNetToolbox\Documentation\dir_5d31cc570c40ab523f35cc1c98664ec1_dep.md5 (32, 2011-07-23)
DeconvNetToolbox\Documentation\minimize_8m_source.html (28774, 2011-07-23)
DeconvNetToolbox\Documentation\dataset.html (14122, 2011-07-23)
DeconvNetToolbox\Documentation\max__pool_2make_8m_source.html (12786, 2011-07-23)
DeconvNetToolbox\Documentation\recon__down__now_8m_source.html (9682, 2011-07-23)
DeconvNetToolbox\Documentation\update__conmats_8m_source.html (23430, 2011-07-23)
DeconvNetToolbox\Documentation\globals_vars_0x6e.html (8239, 2011-07-23)
DeconvNetToolbox\Documentation\test__conv__max_8m_source.html (22355, 2011-07-23)
DeconvNetToolbox\Documentation\max__pool_2make_8m.html (7553, 2011-07-23)
DeconvNetToolbox\Documentation\estimate__runtime_8m.html (9715, 2011-07-23)
DeconvNetToolbox\Documentation\split_compare_batch_recons_8m.html (7757, 2011-07-23)
DeconvNetToolbox\Documentation\dir_c85fc0aabd21f574f680dc18e8854f0c_dep.map (275, 2011-07-23)
DeconvNetToolbox\Documentation\dir_bbb5322ddd6e4f2397307a4f141de05e_dep.md5 (32, 2011-07-23)
DeconvNetToolbox\Documentation\compile__filters_8m_source.html (20159, 2011-07-23)
DeconvNetToolbox\Documentation\cu_rev_avg_pool_8cpp.html (33360, 2011-07-23)
DeconvNetToolbox\Documentation\conmat__singles__randdoub_8m.html (9832, 2011-07-23)
DeconvNetToolbox\Documentation\region__zca_8m_source.html (22645, 2011-07-23)
DeconvNetToolbox\Documentation\tab_s.png (189, 2011-07-23)
DeconvNetToolbox\Documentation\cu_conv8__2_8cpp_ab0e64e66cdf8c17e62ce30d85d2f217e_icgraph.map (299, 2011-07-23)
DeconvNetToolbox\Documentation\cu_conv8__2_8cpp_a3a45e5326578e0ebe4fd8d0895b70455_cgraph.png (1491, 2011-07-23)
DeconvNetToolbox\Documentation\convs_2reloadmodule_8m_source.html (7029, 2011-07-23)
DeconvNetToolbox\Documentation\dir_825b33bab452b260d09c7fc459e1c8be_dep.png (863, 2011-07-23)
DeconvNetToolbox\Documentation\padarray_8cpp_source.html (25887, 2011-07-23)
DeconvNetToolbox\Documentation\compare__two__vars_8m.html (9423, 2011-07-23)
DeconvNetToolbox\Documentation\clean__results__dir_8m_source.html (17868, 2011-07-23)
DeconvNetToolbox\Documentation\dir_cfeb6b21b079343fbbed48f4a39ccd70_dep.png (713, 2011-07-23)
DeconvNetToolbox\Documentation\keypress_8m_source.html (10087, 2011-07-23)
DeconvNetToolbox\Documentation\conmat__singles_8m_source.html (9339, 2011-07-23)
DeconvNetToolbox\Documentation\split_hist_pyr_8m.html (9859, 2011-07-23)
DeconvNetToolbox\Documentation\avg__pool_2moduleinit_8m.html (7353, 2011-07-23)
DeconvNetToolbox\Documentation\sift__linear_8m.html (7927, 2011-07-23)
DeconvNetToolbox\Documentation\infer__all_8m_source.html (61443, 2011-07-23)
DeconvNetToolbox\Documentation\avg__pool_2testcu_max_pool_8m.html (7427, 2011-07-23)
DeconvNetToolbox\Documentation\clean__results__dir_8m.html (9280, 2011-07-23)
... ...

Instructions: Follow these instructions to setup the toolbox: - Download and unzip this toolbox in the location of choice. - To setup this toolbox, simply open matlab, cd to this directory, and type "setupDeconvNetToolbox" (without the quotes) in the command window. This sets up your path to include the required directories (you may want to add these paths into your startup.m file as well however) and opens complete documentation for this toolbox. - Next you need to compile the pooling functinos in the PoolingToolbox folder using the included compilemex.m function there. You may need to change the paths for you system however. These compiled version are MUCH faster then any MATLAB version and only require openMP libraries for compilation. Some functions won't actually work unless these are compiled. - You may also want to compile the IPPConvToolbox files if you have IPP libraries installed on your system as they are much faster than the MATLAB versions. There is a compilemex script in the IPPConvsToolbox folder to compile all the necessary functions but you will likely need to set the paths within it correctly. - Also, there are GPUmat capable files included in the zip. You must copy the "mdz" directory in the included zip's /modules/ directory to your GPUmat/modules directory. You must type "make install" in each of those module directories from within MATLAB to ensure the necessary files are installed in GPUmat's top directory correctly. - After everything is installed properly (or you just want to use the default CPU implementation) then you can just type "gui" at the command line to configure the settings of the deconvolutional network as you wish. However, you MUST set the paths at the top of the gui.m file to reflect your desired setup. Alternatively, you can modify parameters within /Defaults/set_defaults_here.m which allows you to manually set the model struct that the gui would create. - Run any of the main scripts listed below (it is recommended to RUN THEM FROM THIS DIRECTORY as the results will be added to ./Results/ by default). The main scripts to run (from the main directory) are: gui.m - open the gui to set parameters for the following scripts. trainAll.m - trains a Deconvoltuional Network using specified parameters. reconAll.m - reconstructs input images using a previously trained Deconvolutional Network. top_down_select.m - loads previously trained top layer (and all layers below) and visualizes the top layer's filters in pixel space. License: Permission is granted for anyone to copy, use, modify, or distribute this program and accompanying programs and documents for any purpose, provided this copyright notice is retained and prominently displayed, along with a note saying that the original programs are available from our web page. The programs and documents are distributed without any warranty, express or implied. As the programs were written for research purposes only, they have not been tested to the degree that would be advisable in any important application. All use of these programs is entirely at the user's own risk.

近期下载者

相关文件


收藏者