Model_T_h1_m1/Training_Evaluation/Run_Training_Evaluation.m

% clear all
%
model='T_h1_m1';
nmb_of_hidden_layers=1;

fun_training_evaulation(model,nmb_of_hidden_layers)
%%
load('T_h1_m1_1_performance.mat')
%%
rtmax=max(pstvrt_model,[],'all')
rtmin=min(pstvrt_model,[],'all')
rtmed=median(pstvrt_model(:),'all')
rtmean=mean(pstvrt_model(:),'all')
%%
aa=squeeze(pstvrt_model(1,:,1));
bb=squeeze(pstvrt_model(1,:,2));
cc=[aa,bb];
idx=(cc==100);
nmb_of_100rt=sum(1*idx)-1
rt100=(sum(idx*1)-1)/length(cc)
%%
[rtmin,rtmean,rtmean,rtmax,nmb_of_100rt]
%%
% channels_names={'R','G','B','RGg1','RBg1','GBg1','RGg2','RBg2','GBg2','RB','RG','GB','eRGB','BW','X','Y','Z'};
% for module=1:nmb_of_modules
%     for subset=1:nmb_of_module_subsets
%         for color=1:nmb_of_colors
%             reportname1 = sprintf('../Evaluation_Data/Model_Performance/Trained_Model_%s_patch_%d_module_%d_subset_%d_ch_%s.mat',...
%                 model,patch, module, subset, char(channels_names(color)));
%             % training_performance=[true_label;predicted_label;predicted_distance];
%             save(reportname1, 'training_performance');
%         end
%     end
% end