open source pkg v1

pkg/OpenFace/model_training/AU_training/experiments/UNBC/Prepare_HOG_AU_data.m

@@ -0,0 +1,117 @@
+function [data_train, labels_train, data_devel, labels_devel, raw_devel, PC, means_norm, stds_norm, devel_ids, devel_success] = ...
+    Prepare_HOG_AU_data(train_users, devel_users, au_train, rest_aus, UNBC_dir, features_dir)
+
+%%
+addpath(genpath('../data extraction/'));
+
+% First extracting the labels
+[ labels_train, valid_ids_train, filenames ] = extract_UNBC_labels(UNBC_dir, train_users, au_train);
+
+[ labels_other, ~, ~ ] = extract_UNBC_labels(UNBC_dir, train_users, rest_aus);
+labels_other = cat(1, labels_other{:});
+
+% Reading in the HOG data (of only relevant frames)
+[train_appearance_data, valid_ids_train_hog, vid_ids_train_string] = Read_HOG_files(train_users, features_dir);
+
+[train_geom_data] = Read_geom_files(train_users,  features_dir);
+
+% Subsample the data to make training quicker
+labels_train = cat(1, labels_train{:});
+valid_ids_train = logical(cat(1, valid_ids_train{:}));
+
+if(numel(train_users) > 0)
+    reduced_inds = false(size(labels_train,1),1);
+    reduced_inds(labels_train > 0) = true;
+
+    % make sure the same number of positive and negative samples is taken
+    pos_count = sum(labels_train > 0);
+    neg_count = sum(labels_train == 0);
+
+    num_other = floor(pos_count / (size(labels_other, 2)));
+
+    inds_all = 1:size(labels_train,1);
+
+    for i=1:size(labels_other, 2)+1
+   
+        if(i > size(labels_other, 2))
+            % fill the rest with a proportion of neutral
+            inds_other = inds_all(sum(labels_other,2)==0 & ~labels_train );   
+                num_other_i = min(numel(inds_other), pos_count - sum(labels_train(reduced_inds,:)==0));     
+        else
+                % take a proportion of each other AU
+            inds_other = inds_all(labels_other(:, i) & ~labels_train );      
+            num_other_i = min(numel(inds_other), num_other);        
+        end
+        inds_other_to_keep = inds_other(round(linspace(1, numel(inds_other), num_other_i)));
+        reduced_inds(inds_other_to_keep) = true;
+
+    end
+
+    % Remove invalid ids based on CLM failing or AU not being labelled
+    reduced_inds(~valid_ids_train) = false;
+    reduced_inds(~valid_ids_train_hog) = false;
+
+    labels_other = labels_other(reduced_inds, :);
+    labels_train = labels_train(reduced_inds,:);
+    train_appearance_data = train_appearance_data(reduced_inds,:);
+    train_geom_data = train_geom_data(reduced_inds,:);
+    vid_ids_train_string = vid_ids_train_string(reduced_inds,:);
+end
+%% Extract devel data
+
+% First extracting the labels
+[ labels_devel, valid_ids_devel, vid_ids_devel ] = extract_UNBC_labels(UNBC_dir, devel_users, au_train);
+
+% Reading in the HOG data (of only relevant frames)
+[devel_appearance_data, valid_ids_devel_hog, vid_ids_devel_string] = Read_HOG_files(devel_users, features_dir);
+devel_success = valid_ids_devel_hog;
+devel_ids = vid_ids_devel_string;
+
+[devel_geom_data] = Read_geom_files(devel_users, features_dir);
+
+labels_devel = cat(1, labels_devel{:});
+
+% Peforming zone specific masking
+if(au_train < 8 || au_train == 43 || au_train == 45) % upper face AUs ignore bottom face
+    % normalise the data
+    pca_file = '../../pca_generation/generic_face_upper.mat';
+    load(pca_file);
+elseif(au_train > 9) % lower face AUs ignore upper face and the sides
+    % normalise the data
+    pca_file = '../../pca_generation/generic_face_lower.mat';
+    load(pca_file);
+elseif(au_train == 9) % Central face model
+    % normalise the data
+    pca_file = '../../pca_generation/generic_face_rigid.mat';
+    load(pca_file);
+end
+
+% Grab all data for validation as want good params for all the data
+raw_devel = cat(2, devel_appearance_data, devel_geom_data);
+
+devel_appearance_data = bsxfun(@times, bsxfun(@plus, devel_appearance_data, -means_norm), 1./stds_norm);
+
+data_devel = devel_appearance_data * PC;
+
+data_devel = cat(2, data_devel, devel_geom_data);
+
+if(numel(train_users) > 0)
+    train_appearance_data = bsxfun(@times, bsxfun(@plus, train_appearance_data, -means_norm), 1./stds_norm);
+
+    data_train = train_appearance_data * PC;
+    data_train = cat(2, data_train, train_geom_data);
+else
+    data_train = [];
+end
+
+geom_size = max(size(train_geom_data, 2), size(devel_geom_data, 2));
+
+PC_n = zeros(size(PC)+geom_size);
+PC_n(1:size(PC,1), 1:size(PC,2)) = PC;
+PC_n(size(PC,1)+1:end, size(PC,2)+1:end) = eye(geom_size);
+PC = PC_n;
+
+means_norm = cat(2, means_norm, zeros(1, geom_size));
+stds_norm = cat(2, stds_norm, ones(1, geom_size));
+
+end

pkg/OpenFace/model_training/AU_training/experiments/UNBC/Prepare_HOG_AU_data_dynamic.m

@@ -0,0 +1,117 @@
+function [data_train, labels_train, data_devel, labels_devel, raw_devel, PC, means_norm, stds_norm, devel_ids, devel_success] = ...
+    Prepare_HOG_AU_data_dynamic(train_users, devel_users, au_train, rest_aus, UNBC_dir, features_dir)
+
+%%
+addpath(genpath('../data extraction/'));
+
+% First extracting the labels
+[ labels_train, valid_ids_train, filenames ] = extract_UNBC_labels(UNBC_dir, train_users, au_train);
+
+[ labels_other, ~, ~ ] = extract_UNBC_labels(UNBC_dir, train_users, rest_aus);
+labels_other = cat(1, labels_other{:});
+
+% Reading in the HOG data (of only relevant frames)
+[train_appearance_data, valid_ids_train_hog, vid_ids_train_string] = Read_HOG_files_dynamic(train_users, features_dir);
+
+[train_geom_data] = Read_geom_files_dynamic(train_users,  features_dir);
+
+% Subsample the data to make training quicker
+labels_train = cat(1, labels_train{:});
+valid_ids_train = logical(cat(1, valid_ids_train{:}));
+
+if(numel(train_users) > 0)
+    reduced_inds = false(size(labels_train,1),1);
+    reduced_inds(labels_train > 0) = true;
+
+    % make sure the same number of positive and negative samples is taken
+    pos_count = sum(labels_train > 0);
+    neg_count = sum(labels_train == 0);
+
+    num_other = floor(pos_count / (size(labels_other, 2)));
+
+    inds_all = 1:size(labels_train,1);
+
+    for i=1:size(labels_other, 2)+1
+   
+        if(i > size(labels_other, 2))
+            % fill the rest with a proportion of neutral
+            inds_other = inds_all(sum(labels_other,2)==0 & ~labels_train );   
+                num_other_i = min(numel(inds_other), pos_count - sum(labels_train(reduced_inds,:)==0));     
+        else
+                % take a proportion of each other AU
+            inds_other = inds_all(labels_other(:, i) & ~labels_train );      
+            num_other_i = min(numel(inds_other), num_other);        
+        end
+        inds_other_to_keep = inds_other(round(linspace(1, numel(inds_other), num_other_i)));
+        reduced_inds(inds_other_to_keep) = true;
+
+    end
+
+    % Remove invalid ids based on CLM failing or AU not being labelled
+    reduced_inds(~valid_ids_train) = false;
+    reduced_inds(~valid_ids_train_hog) = false;
+
+    labels_other = labels_other(reduced_inds, :);
+    labels_train = labels_train(reduced_inds,:);
+    train_appearance_data = train_appearance_data(reduced_inds,:);
+    train_geom_data = train_geom_data(reduced_inds,:);
+    vid_ids_train_string = vid_ids_train_string(reduced_inds,:);
+end
+%% Extract devel data
+
+% First extracting the labels
+[ labels_devel, valid_ids_devel, vid_ids_devel ] = extract_UNBC_labels(UNBC_dir, devel_users, au_train);
+
+% Reading in the HOG data (of only relevant frames)
+[devel_appearance_data, valid_ids_devel_hog, vid_ids_devel_string] = Read_HOG_files_dynamic(devel_users, features_dir);
+devel_success = valid_ids_devel_hog;
+devel_ids = vid_ids_devel_string;
+
+[devel_geom_data] = Read_geom_files_dynamic(devel_users, features_dir);
+
+labels_devel = cat(1, labels_devel{:});
+
+% Peforming zone specific masking
+if(au_train < 8 || au_train == 43 || au_train == 45) % upper face AUs ignore bottom face
+    % normalise the data
+    pca_file = '../../pca_generation/generic_face_upper.mat';
+    load(pca_file);
+elseif(au_train > 9) % lower face AUs ignore upper face and the sides
+    % normalise the data
+    pca_file = '../../pca_generation/generic_face_lower.mat';
+    load(pca_file);
+elseif(au_train == 9) % Central face model
+    % normalise the data
+    pca_file = '../../pca_generation/generic_face_rigid.mat';
+    load(pca_file);
+end
+
+% Grab all data for validation as want good params for all the data
+raw_devel = cat(2, devel_appearance_data, devel_geom_data);
+
+devel_appearance_data = bsxfun(@times, bsxfun(@plus, devel_appearance_data, -means_norm), 1./stds_norm);
+
+data_devel = devel_appearance_data * PC;
+
+data_devel = cat(2, data_devel, devel_geom_data);
+
+if(numel(train_users) > 0)
+    train_appearance_data = bsxfun(@times, bsxfun(@plus, train_appearance_data, -means_norm), 1./stds_norm);
+
+    data_train = train_appearance_data * PC;
+    data_train = cat(2, data_train, train_geom_data);
+else
+    data_train = [];
+end
+
+geom_size = max(size(train_geom_data, 2), size(devel_geom_data, 2));
+
+PC_n = zeros(size(PC)+geom_size);
+PC_n(1:size(PC,1), 1:size(PC,2)) = PC;
+PC_n(size(PC,1)+1:end, size(PC,2)+1:end) = eye(geom_size);
+PC = PC_n;
+
+means_norm = cat(2, means_norm, zeros(1, geom_size));
+stds_norm = cat(2, stds_norm, ones(1, geom_size));
+
+end

pkg/OpenFace/model_training/AU_training/experiments/UNBC/Read_HOG_files.m

@@ -0,0 +1,89 @@
+function [hog_data, valid_data, vid_id] = Read_HOG_files(users, hog_data_dir)
+
+    
+    hog_data = [];
+    vid_id = {};
+    valid_data = [];
+    
+    feats_filled = 0;
+
+    for i=1:numel(users)
+        
+        hog_files = dir([hog_data_dir, '/' users{i} '*.hog']);
+        
+        for f_num=1:numel(hog_files)
+            f = fopen([hog_data_dir,  '/', hog_files(f_num).name], 'r');
+
+            curr_data = [];
+            curr_ind = 0;
+
+            while(~feof(f))
+
+                if(curr_ind == 0)
+                    num_cols = fread(f, 1, 'int32');
+                    if(isempty(num_cols))
+                        break;
+                    end
+
+                    num_rows = fread(f, 1, 'int32');
+                    num_chan = fread(f, 1, 'int32');
+
+                    curr_ind = curr_ind + 1;            
+
+                    % preallocate some space
+                    if(curr_ind == 1)
+                        curr_data = zeros(5000, 1 + num_rows * num_cols * num_chan);
+                        num_feats =  1 + num_rows * num_cols * num_chan;
+                    end
+
+                    if(curr_ind > size(curr_data,1))
+                        curr_data = cat(1, curr_data, zeros(6000, 1 + num_rows * num_cols * num_chan));
+                    end
+                    feature_vec = fread(f, [1, 1 + num_rows * num_cols * num_chan], 'float32');
+                    curr_data(curr_ind, :) = feature_vec;
+                else
+
+                    % Reading in batches of 5000
+
+                    feature_vec = fread(f, [4 + num_rows * num_cols * num_chan, 5000], 'float32');
+                    feature_vec = feature_vec(4:end,:)';
+
+                    num_rows_read = size(feature_vec,1);
+
+                    curr_data(curr_ind+1:curr_ind+num_rows_read,:) = feature_vec;
+
+                    curr_ind = curr_ind + size(feature_vec,1);
+
+                end
+
+            end
+
+            fclose(f);
+
+            curr_data = curr_data(1:curr_ind,:);
+            vid_id_curr = cell(curr_ind,1);
+            vid_id_curr(:) = users(i);
+
+            vid_id = cat(1, vid_id, vid_id_curr);
+
+            % Assume same number of frames per video
+            if(i==1)
+                hog_data = zeros(curr_ind*numel(users), num_feats);
+            end
+
+            if(size(hog_data,1) < feats_filled+curr_ind)
+               hog_data = cat(1, hog_data, zeros(size(hog_data,1), num_feats));
+            end
+
+            hog_data(feats_filled+1:feats_filled+curr_ind,:) = curr_data;
+
+            feats_filled = feats_filled + curr_ind;
+        end
+    end
+    
+    if(numel(users) > 0)
+        valid_data = hog_data(1:feats_filled,1) > 0;
+        hog_data = hog_data(1:feats_filled,2:end);
+    end
+    
+end

pkg/OpenFace/model_training/AU_training/experiments/UNBC/Read_HOG_files_dynamic.m

@@ -0,0 +1,93 @@
+function [hog_data, valid_data, vid_id] = Read_HOG_files_dynamic(users, hog_data_dir)
+
+    
+    hog_data = [];
+    vid_id = {};
+    valid_data = [];
+    
+    for i=1:numel(users)
+        
+        hog_files = dir([hog_data_dir, '/' users{i} '*.hog']);
+        
+        hog_data_curr_p = [];
+        feats_filled = 0;
+        
+        for f_num=1:numel(hog_files)
+            f = fopen([hog_data_dir,  '/', hog_files(f_num).name], 'r');
+
+            curr_data = [];
+            curr_ind = 0;
+
+            while(~feof(f))
+
+                if(curr_ind == 0)
+                    num_cols = fread(f, 1, 'int32');
+                    if(isempty(num_cols))
+                        break;
+                    end
+
+                    num_rows = fread(f, 1, 'int32');
+                    num_chan = fread(f, 1, 'int32');
+
+                    curr_ind = curr_ind + 1;            
+
+                    % preallocate some space
+                    if(curr_ind == 1)
+                        curr_data = zeros(5000, 1 + num_rows * num_cols * num_chan);
+                        num_feats =  1 + num_rows * num_cols * num_chan;
+                    end
+
+                    if(curr_ind > size(curr_data,1))
+                        curr_data = cat(1, curr_data, zeros(6000, 1 + num_rows * num_cols * num_chan));
+                    end
+                    feature_vec = fread(f, [1, 1 + num_rows * num_cols * num_chan], 'float32');
+                    curr_data(curr_ind, :) = feature_vec;
+                else
+
+                    % Reading in batches of 5000
+
+                    feature_vec = fread(f, [4 + num_rows * num_cols * num_chan, 5000], 'float32');
+                    feature_vec = feature_vec(4:end,:)';
+
+                    num_rows_read = size(feature_vec,1);
+
+                    curr_data(curr_ind+1:curr_ind+num_rows_read,:) = feature_vec;
+
+                    curr_ind = curr_ind + size(feature_vec,1);
+
+                end
+
+            end
+
+            fclose(f);
+
+            curr_data = curr_data(1:curr_ind,:);
+            vid_id_curr = cell(curr_ind,1);
+            vid_id_curr(:) = users(i);
+
+            vid_id = cat(1, vid_id, vid_id_curr);
+
+            % Assume same number of frames per video
+            if(f_num==1)
+                hog_data_curr_p = zeros(curr_ind*numel(users), num_feats);
+            end
+
+            if(size(hog_data_curr_p,1) < feats_filled+curr_ind)
+               hog_data_curr_p = cat(1, hog_data_curr_p, zeros(size(hog_data_curr_p,1), num_feats));
+            end
+
+            hog_data_curr_p(feats_filled+1:feats_filled+curr_ind,:) = curr_data;
+
+            feats_filled = feats_filled + curr_ind;
+        end
+        
+        hog_data_curr_p(1:feats_filled,2:end) = bsxfun(@plus, hog_data_curr_p(1:feats_filled,2:end), -median(hog_data_curr_p(1:feats_filled,2:end)));        
+        hog_data = cat(1, hog_data, hog_data_curr_p(1:feats_filled,:));
+        
+    end
+    
+    if(numel(users) > 0)
+        valid_data = hog_data(:,1) > 0;
+        hog_data = hog_data(:,2:end);
+    end
+end

pkg/OpenFace/model_training/AU_training/experiments/UNBC/Read_geom_files.m

@@ -0,0 +1,46 @@
+function [geom_data, valid_ids] = Read_geom_files(users, model_param_data_dir)
+
+    geom_data = [];
+    valid_ids = [];
+    
+    load('../../pca_generation/pdm_68_aligned_wild.mat');
+    
+    for i=1:numel(users)
+        
+        geom_files = dir([model_param_data_dir, '/' users{i} '*.csv']);
+        
+        for g=1:numel(geom_files)
+            
+            m_file = [model_param_data_dir, '/', geom_files(g).name, '.mat'];
+
+            if(~exist(m_file, 'file'))
+                
+                if(~exist('shape_inds', 'var'))
+                    tab = readtable([model_param_data_dir, '/', geom_files(g).name]);
+                    column_names = tab.Properties.VariableNames; 
+                    valid_ind = cellfun(@(x) ~isempty(x) && x==1, strfind(column_names, 'success'));
+                    shape_inds = cellfun(@(x) ~isempty(x) && x==1, strfind(column_names, 'p_'));
+                end
+        
+                res = dlmread([model_param_data_dir, '/', geom_files(g).name], ',', 1, 0);
+
+                valid = res(:, valid_ind) > 0.7;        
+                res = res(:, shape_inds);
+
+                % Do not consider global parameters
+                res = res(:, 7:end);
+
+                save(m_file, 'res', 'valid');
+            else
+                load(m_file);
+            end
+            
+            actual_locs = res * V';
+            res = cat(2, actual_locs, res);
+
+            valid_ids = cat(1, valid_ids, valid);
+
+            geom_data = cat(1, geom_data, res);
+        end
+    end
+end

pkg/OpenFace/model_training/AU_training/experiments/UNBC/Read_geom_files_dynamic.m

@@ -0,0 +1,51 @@
+function [geom_data, valid_ids] = Read_geom_files_dynamic(users, model_param_data_dir)
+
+    geom_data = [];
+    valid_ids = [];
+    
+    load('../../pca_generation/pdm_68_aligned_wild.mat');
+    
+    for i=1:numel(users)
+        
+        geom_files = dir([model_param_data_dir, '/' users{i} '*.csv']);
+        
+        geom_data_curr_p = [];
+        
+        for g=1:numel(geom_files)
+            m_file = [model_param_data_dir, '/', geom_files(g).name, '.mat'];
+
+            if(~exist(m_file, 'file'))
+                
+                if(~exist('shape_inds', 'var'))
+                    tab = readtable([model_param_data_dir, '/', geom_files(g).name]);
+                    column_names = tab.Properties.VariableNames; 
+                    valid_ind = cellfun(@(x) ~isempty(x) && x==1, strfind(column_names, 'success'));
+                    shape_inds = cellfun(@(x) ~isempty(x) && x==1, strfind(column_names, 'p_'));
+                end
+        
+                res = dlmread([model_param_data_dir, '/', geom_files(g).name], ',', 1, 0);
+
+                valid = res(:, valid_ind) > 0.7;        
+                res = res(:, shape_inds);
+
+                % Do not consider global parameters
+                res = res(:, 7:end);
+
+                save(m_file, 'res', 'valid');
+            else
+                load(m_file);
+            end
+
+            actual_locs = res * V';
+            res = cat(2, actual_locs, res);
+
+            valid_ids = cat(1, valid_ids, valid);
+
+            geom_data_curr_p = cat(1, geom_data_curr_p, res);
+        end
+        geom_data_curr_p = bsxfun(@plus, geom_data_curr_p, -median(geom_data_curr_p));
+        
+        geom_data = cat(1, geom_data, geom_data_curr_p);
+        
+    end
+end

pkg/OpenFace/model_training/AU_training/experiments/UNBC/Script_HOG_SVM_train.m

@@ -0,0 +1,83 @@
+function Script_HOG_SVM_train()
+
+% Change to your downloaded location
+addpath('C:\liblinear\matlab')
+addpath('../training_code/');
+addpath('../utilities/');
+addpath('../../data extraction/');
+
+%% load shared definitions and AU data
+shared_defs;
+
+% Set up the hyperparameters to be validated
+hyperparams.c = 10.^(-9:0.5:1);
+hyperparams.e = 10.^(-3);
+
+hyperparams.validate_params = {'c', 'e'};
+
+% Set the training function
+svm_train = @svm_train_linear;
+    
+% Set the test function (the first output will be used for validation)
+svm_test = @svm_test_linear;
+
+all_recs = cat(2, train_recs, devel_recs);
+
+%%
+for a=1:numel(aus)
+    
+    au = aus(a);
+            
+    rest_aus = setdiff(all_aus, au);        
+    
+    [users_train, users_valid] = get_balanced_fold(UNBC_dir, all_recs, au, 1/3, 1);
+    
+    % load the training and testing data for the current fold    
+    [train_samples, train_labels, valid_samples, valid_labels, ~, PC, means, scaling] = Prepare_HOG_AU_data(users_train, users_valid, au, rest_aus, UNBC_dir, features_dir);
+    
+    % Binarizing the data
+    train_labels(train_labels > 1) = 1;
+    valid_labels(valid_labels > 1) = 1;
+    
+    train_samples = sparse(train_samples);
+    valid_samples = sparse(valid_samples);
+
+    %% Cross-validate here                
+    [ best_params, ~ ] = validate_grid_search_no_par(svm_train, svm_test, false, train_samples, train_labels, valid_samples, valid_labels, hyperparams);
+
+    model = svm_train(train_labels, train_samples, best_params);        
+
+    [prediction, a, actual_vals] = predict(valid_labels, valid_samples, model);
+
+    % Go from raw data to the prediction
+    w = model.w(1:end-1)';
+    b = model.w(end);
+
+    svs = bsxfun(@times, PC, 1./scaling') * w;
+
+    name = sprintf('models/AU_%d_static.dat', au);
+
+    pos_lbl = model.Label(1);
+    neg_lbl = model.Label(2);
+        
+    write_lin_svm(name, means, svs, b, pos_lbl, neg_lbl);
+
+    name = sprintf('results_UNBC_devel/AU_%d_static.mat', au);
+
+    tp = sum(valid_labels == 1 & prediction == 1);
+    fp = sum(valid_labels == 0 & prediction == 1);
+    fn = sum(valid_labels == 1 & prediction == 0);
+    tn = sum(valid_labels == 0 & prediction == 0);
+
+    precision = tp/(tp+fp);
+    recall = tp/(tp+fn);
+
+    f1 = 2 * precision * recall / (precision + recall);    
+    
+    save(name, 'model', 'f1', 'precision', 'recall', 'best_params', 'valid_labels', 'prediction', 'users_valid');
+        
+end
+
+end
+
+

pkg/OpenFace/model_training/AU_training/experiments/UNBC/Script_HOG_SVM_train_dyn.m

@@ -0,0 +1,83 @@
+function Script_HOG_SVM_train_dyn()
+
+% Change to your downloaded location
+addpath('C:\liblinear\matlab')
+addpath('../training_code/');
+addpath('../utilities/');
+addpath('../../data extraction/');
+
+%% load shared definitions and AU data
+shared_defs;
+
+% Set up the hyperparameters to be validated
+hyperparams.c = 10.^(-9:0.5:1);
+hyperparams.e = 10.^(-3);
+
+hyperparams.validate_params = {'c', 'e'};
+
+% Set the training function
+svm_train = @svm_train_linear;
+    
+% Set the test function (the first output will be used for validation)
+svm_test = @svm_test_linear;
+
+all_recs = cat(2, train_recs, devel_recs);
+
+%%
+for a=1:numel(aus)
+    
+    au = aus(a);
+            
+    rest_aus = setdiff(all_aus, au);        
+
+    [users_train, users_valid] = get_balanced_fold(UNBC_dir, all_recs, au, 1/3, 1);
+    
+    % load the training and testing data for the current fold    
+    [train_samples, train_labels, valid_samples, valid_labels, ~, PC, means, scaling] = Prepare_HOG_AU_data_dynamic(users_train, users_valid, au, rest_aus, UNBC_dir, features_dir);
+    
+    train_samples = sparse(train_samples);
+    valid_samples = sparse(valid_samples);
+    
+    % Binarizing the data
+    train_labels(train_labels > 1) = 1;
+    valid_labels(valid_labels > 1) = 1;
+    
+    %% Cross-validate here                
+    [ best_params, ~ ] = validate_grid_search_no_par(svm_train, svm_test, false, train_samples, train_labels, valid_samples, valid_labels, hyperparams);
+
+    model = svm_train(train_labels, train_samples, best_params);        
+
+    [prediction, a, actual_vals] = predict(valid_labels, valid_samples, model);
+
+    % Go from raw data to the prediction
+    w = model.w(1:end-1)';
+    b = model.w(end);
+
+    svs = bsxfun(@times, PC, 1./scaling') * w;
+
+    name = sprintf('models/AU_%d_dyn.dat', au);
+
+    pos_lbl = model.Label(1);
+    neg_lbl = model.Label(2);
+        
+    write_lin_dyn_svm(name, means, svs, b, pos_lbl, neg_lbl);
+
+    name = sprintf('results_UNBC_devel/AU_%d_dyn.mat', au);
+
+    tp = sum(valid_labels == 1 & prediction == 1);
+    fp = sum(valid_labels == 0 & prediction == 1);
+    fn = sum(valid_labels == 1 & prediction == 0);
+    tn = sum(valid_labels == 0 & prediction == 0);
+
+    precision = tp/(tp+fp);
+    recall = tp/(tp+fn);
+
+    f1 = 2 * precision * recall / (precision + recall);    
+    
+    save(name, 'model', 'f1', 'precision', 'recall', 'best_params', 'valid_labels', 'prediction', 'users_valid');
+        
+end
+
+end
+
+

pkg/OpenFace/model_training/AU_training/experiments/UNBC/Script_HOG_SVR_train.m

@@ -0,0 +1,70 @@
+function Script_HOG_SVR_train()
+
+% Change to your downloaded location
+addpath('C:\liblinear\matlab')
+addpath('../training_code/');
+addpath('../utilities/');
+addpath('../../data extraction/');
+
+%% load shared definitions and AU data
+shared_defs;
+
+% Set up the hyperparameters to be validated
+hyperparams.c = 10.^(-7:1:4);
+hyperparams.p = 10.^(-2);
+
+hyperparams.validate_params = {'c', 'p'};
+
+% Set the training function
+svr_train = @svr_train_linear;
+    
+% Set the test function (the first output will be used for validation)
+svr_test = @svr_test_linear;
+
+all_recs = cat(2, train_recs, devel_recs);
+
+%%
+for a=1:numel(aus)
+    
+    au = aus(a);
+            
+    rest_aus = setdiff(all_aus, au);        
+    
+    [users_train, users_valid] = get_balanced_fold(UNBC_dir, all_recs, au, 1/3, 1);
+    
+    % load the training and testing data for the current fold    
+    [train_samples, train_labels, valid_samples, valid_labels, ~, PC, means, scaling, valid_ids, valid_success] = Prepare_HOG_AU_data(users_train, users_valid, au, rest_aus, UNBC_dir, features_dir);
+        
+    train_samples = sparse(train_samples);
+    valid_samples = sparse(valid_samples);
+
+    hyperparams.success = valid_success;    
+    
+    %% Cross-validate here                
+    [ best_params, ~ ] = validate_grid_search_no_par(svr_train, svr_test, false, train_samples, train_labels, valid_samples, valid_labels, hyperparams);
+
+    model = svr_train(train_labels, train_samples, best_params);        
+
+    [~, prediction] = svr_test(valid_labels, valid_samples, model);
+
+    % Go from raw data to the prediction
+    w = model.w(1:end-1)';
+    b = model.w(end);
+
+    svs = bsxfun(@times, PC, 1./scaling') * w;
+
+    name = sprintf('models/AU_%d_static_intensity.dat', au);
+
+    write_lin_svr(name, means, svs, b);
+
+    name = sprintf('results_UNBC_devel/AU_%d_static_intensity.mat', au);
+
+    [ accuracies, F1s, corrs, ccc, rms, classes ] = evaluate_regression_results( prediction, valid_labels );
+            
+    save(name, 'model', 'F1s', 'corrs', 'accuracies', 'ccc', 'rms', 'prediction', 'valid_labels', 'users_valid');
+        
+end
+
+end
+
+

pkg/OpenFace/model_training/AU_training/experiments/UNBC/Script_HOG_SVR_train_dyn.m

@@ -0,0 +1,70 @@
+function Script_HOG_SVR_train_dyn()
+
+% Change to your downloaded location
+addpath('C:\liblinear\matlab')
+addpath('../training_code/');
+addpath('../utilities/');
+addpath('../../data extraction/');
+
+%% load shared definitions and AU data
+shared_defs;
+
+% Set up the hyperparameters to be validated
+hyperparams.c = 10.^(-7:1:4);
+hyperparams.p = 10.^(-2);
+
+hyperparams.validate_params = {'c', 'p'};
+
+% Set the training function
+svr_train = @svr_train_linear;
+    
+% Set the test function (the first output will be used for validation)
+svr_test = @svr_test_linear;
+
+all_recs = cat(2, train_recs, devel_recs);
+
+%%
+for a=1:numel(aus)
+    
+    au = aus(a);
+            
+    rest_aus = setdiff(all_aus, au);        
+    
+    [users_train, users_valid] = get_balanced_fold(UNBC_dir, all_recs, au, 1/3, 1);
+    
+    % load the training and testing data for the current fold    
+    [train_samples, train_labels, valid_samples, valid_labels, ~, PC, means, scaling, valid_ids, valid_success] = Prepare_HOG_AU_data_dynamic(users_train, users_valid, au, rest_aus, UNBC_dir, features_dir);
+        
+    train_samples = sparse(train_samples);
+    valid_samples = sparse(valid_samples);
+
+    hyperparams.success = valid_success;
+
+    %% Cross-validate here                
+    [ best_params, ~ ] = validate_grid_search_no_par(svr_train, svr_test, false, train_samples, train_labels, valid_samples, valid_labels, hyperparams);
+
+    model = svr_train(train_labels, train_samples, best_params);        
+
+    [~, prediction] = svr_test(valid_labels, valid_samples, model);
+
+    % Go from raw data to the prediction
+    w = model.w(1:end-1)';
+    b = model.w(end);
+
+    svs = bsxfun(@times, PC, 1./scaling') * w;
+
+    name = sprintf('models/AU_%d_dyn_intensity.dat', au);
+
+    write_lin_dyn_svr(name, means, svs, b, 0);
+
+    name = sprintf('results_UNBC_devel/AU_%d_dyn_intensity.mat', au);
+
+    [ accuracies, F1s, corrs, ccc, rms, classes ] = evaluate_regression_results( prediction, valid_labels );
+            
+    save(name, 'model', 'F1s', 'corrs', 'accuracies', 'ccc', 'rms', 'prediction', 'valid_labels', 'users_valid');
+        
+end
+
+end
+
+

pkg/OpenFace/model_training/AU_training/experiments/UNBC/get_balanced_fold.m

@@ -0,0 +1,33 @@
+function [train_users, dev_users] = get_balanced_fold(UNBC_dir, users, au, prop_test, offset)
+
+
+    [ labels_train, valid_ids_train, filenames ] = extract_UNBC_labels(UNBC_dir, users, au);
+    
+    % trimming the filenames a bit
+    for f=1:numel(filenames)
+        filenames{f} = filenames{f}(1:5);
+    end
+    
+    counts = zeros(numel(users),1);
+    for k=1:numel(users)
+        counts(k) = sum(cat(1, labels_train{strcmp(filenames, users{k}(5:end))}));
+    end
+
+    [sorted, inds] = sort(counts);
+    
+    dev_users = users(inds(offset:round(1/prop_test):end));
+    train_users = setdiff(users, dev_users);
+    
+    count_dev = 0;
+    count_train = 0;
+    for k=1:numel(users)
+        if(any(strcmp(dev_users, users{k})))
+            count_dev = count_dev + counts(k);
+        else
+            count_train = count_train + counts(k);
+        end
+        
+    end
+    fprintf('Mean train %.2f, mean test %.2f\n', count_train / numel(train_users), count_dev / numel(dev_users));
+    
+end

pkg/OpenFace/model_training/AU_training/experiments/UNBC/shared_defs.m

@@ -0,0 +1,11 @@
+% this is data defined across the experiments (to make sure all of them have same user conventions)
+
+% Defining which AU's we are extracting (all corrs above 0.5)
+all_aus = [6, 7, 9, 10, 12, 25, 26];
+aus = [6, 7, 9, 10, 12, 25, 26];
+
+addpath('../../data extraction/');
+
+find_UNBC;
+
+features_dir = 'E:\datasets\face_datasets_processed\unbc';