Browse Source

update of whole project for new thresholds

Jérôme BUISINE 10 months ago
parent
commit
9027fd20f9

File diff suppressed because it is too large
+ 0 - 879
analysis/svd_entropy_analysis.ipynb


File diff suppressed because it is too large
+ 1030 - 0
analysis/svd_entropy_diff_analysis.ipynb


File diff suppressed because it is too large
+ 1021 - 0
analysis/svd_entropy_gradient_analysis.ipynb


File diff suppressed because it is too large
+ 1036 - 0
analysis/svd_entropy_gradientabs_analysis.ipynb


File diff suppressed because it is too large
+ 1025 - 0
analysis/svd_entropy_minus_analysis.ipynb


File diff suppressed because it is too large
+ 96 - 55
analysis/svd_scenes_analysis.ipynb


+ 9 - 0
custom_config.py

@@ -1,9 +1,18 @@
 from modules.config.attributes_config import *
 
+import os
+
 # store all variables from global config
 context_vars = vars()
 
 # folders
+output_data_folder              = 'data'
+output_data_generated           = os.path.join(output_data_folder, 'generated')
+output_datasets                 = os.path.join(output_data_folder, 'datasets')
+output_zones_learned            = os.path.join(output_data_folder, 'learned_zones')
+output_models                   = os.path.join(output_data_folder, 'saved_models')
+output_results_folder           = os.path.join(output_data_folder, 'results')
+
 ## min_max_custom_folder           = 'custom_norm'
 ## correlation_indices_folder      = 'corr_indices'
 data_augmented_filename         = 'augmented_dataset.csv'

+ 14 - 8
display/display_svd_data_scene.py

@@ -1,6 +1,7 @@
 # main imports
 import sys, os, argparse
 import numpy as np
+import math
 
 # image processing imports
 from PIL import Image
@@ -151,6 +152,9 @@ def display_svd_values(p_scene, p_interval, p_indices, p_feature, p_mode, p_step
 
             for id, data in enumerate(svd_data):
 
+                # current_data = [ math.log10(d + 1.) for d in data ]
+                # print(current_data)
+
                 current_data = data
 
                 if not p_norm:
@@ -170,30 +174,32 @@ def display_svd_values(p_scene, p_interval, p_indices, p_feature, p_mode, p_step
             ax.set_facecolor('#FFFFFF')
             #fig.patch.set_facecolor('#F9F9F9')
 
-            ax.tick_params(labelsize=22)
+            ax.tick_params(labelsize=26)
             #plt.rc('xtick', labelsize=22)
             #plt.rc('ytick', labelsize=22)
 
             #plt.title(p_scene + ' scene interval information SVD['+ str(begin_data) +', '+ str(end_data) +'], from scenes indices [' + str(begin_index) + ', '+ str(end_index) + '], ' + p_feature + ' feature, ' + p_mode + ', with step of ' + str(p_step) + ', svd norm ' + str(p_norm), fontsize=24)
-            ax.set_ylabel('Component values', fontsize=28)
-            ax.set_xlabel('Vector features', fontsize=28)
+            ax.set_ylabel('Component values', fontsize=36)
+            ax.set_xlabel('Singular value component indices', fontsize=36)
 
             for id, data in enumerate(images_data):
 
-                p_label = p_scene + "_" + images_indices[id]
+                #p_label = p_scene + "_" + images_indices[id]
+                p_label = images_indices[id] + " samples"
 
                 if int(images_indices[id]) == int(threshold_image_zone):
-                    ax.plot(data, label=p_label + " (threshold mean)", lw=4, color='red')
+                    ax.plot(data, label=p_label + " (threshold mean)", lw=6, color='red')
                 else:
                     ax.plot(data, label=p_label)
 
-            plt.legend(bbox_to_anchor=(0.60, 0.98), loc=2, borderaxespad=0.2, fontsize=26)
+            plt.legend(bbox_to_anchor=(0.60, 0.98), loc=2, borderaxespad=0.2, fontsize=32)
 
             start_ylim, end_ylim = p_ylim
             ax.set_ylim(start_ylim, end_ylim)
 
             plot_name = p_scene + '_' + p_feature + '_' + str(p_step) + '_' + p_mode + '_' + str(p_norm) + '.png'
-            plt.savefig(plot_name, facecolor=ax.get_facecolor())
+            plt.title('Tend of Singular values at different samples of Flat scene', fontsize=40)
+            plt.savefig(plot_name, transparent=True)
 
 def main():
 
@@ -206,7 +212,7 @@ def main():
     parser.add_argument('--mode', type=str, help='Kind of normalization level wished', choices=cfg.normalization_choices)
     parser.add_argument('--step', type=int, help='Each step samples to display', default=10)
     parser.add_argument('--norm', type=int, help='If values will be normalized or not', choices=[0, 1])
-    parser.add_argument('--ylim', type=str, help='ylim interval to use', default='"0, 1"')
+    parser.add_argument('--ylim', type=str, help='ylim interval to use', default='0,1')
 
     args = parser.parse_args()
 

+ 2 - 0
generate/generate_all_data.py

@@ -163,6 +163,8 @@ def main():
     parser = argparse.ArgumentParser(description="Compute and prepare data of feature of all scenes (keep in memory min and max value found)")
 
     parser.add_argument('--feature', type=str, 
+                                    help="feature choice in order to compute data (use 'all' if all features are needed)", required=True)
+    parser.add_argument('--dataset', type=str, 
                                     help="feature choice in order to compute data (use 'all' if all features are needed)")
 
     args = parser.parse_args()

+ 225 - 0
generate/generate_all_data_file.py

@@ -0,0 +1,225 @@
+# main imports
+import sys, os, argparse
+import numpy as np
+import random
+import time
+import json
+
+# image processing imports
+from PIL import Image
+
+from ipfml.processing import transform, segmentation
+from ipfml import utils
+
+# modules imports
+sys.path.insert(0, '') # trick to enable import of main folder module
+
+import custom_config as cfg
+from modules.utils import data as dt
+from data_attributes import get_image_features
+
+
+# getting configuration information
+zone_folder             = cfg.zone_folder
+min_max_filename        = cfg.min_max_filename_extension
+
+# define all scenes values
+choices                 = cfg.normalization_choices
+zones                   = cfg.zones_indices
+seuil_expe_filename     = cfg.seuil_expe_filename
+
+features_choices        = cfg.features_choices_labels
+output_data_folder      = cfg.output_data_folder
+
+generic_output_file_svd = '_random.csv'
+
+def generate_data_feature(path, output, human_thresholds, data_type, mode):
+    """
+    @brief Method which generates all .csv files from scenes
+    @param data_type,  feature choice
+    @param mode, normalization choice
+    @return nothing
+    """
+
+    scenes = os.listdir(path)
+    # remove min max file from scenes folder
+    scenes = [s for s in scenes if min_max_filename not in s]
+
+    # keep in memory min and max data found from data_type
+    min_val_found = sys.maxsize
+    max_val_found = 0
+
+    output_path = os.path.join(cfg.output_data_generated, output)
+
+    if not os.path.exists(output_path):
+        os.makedirs(output_path)
+
+    data_min_max_filename = os.path.join(output_path, data_type + min_max_filename)
+
+    # go ahead each scenes
+    for folder_scene in human_thresholds:
+
+        print(folder_scene)
+        scene_path = os.path.join(path, folder_scene)
+        output_scene_path = os.path.join(output_path, folder_scene)
+
+        if not os.path.exists(output_scene_path):
+            os.makedirs(output_scene_path)
+
+        # getting output filename
+        output_svd_filename = data_type + "_" + mode + generic_output_file_svd
+
+        # construct each zones folder name
+        zones_folder = []
+        svd_output_files = []
+
+        # get zones list info
+        for index in zones:
+            index_str = str(index)
+            if len(index_str) < 2:
+                index_str = "0" + index_str
+
+            current_zone = "zone"+index_str
+            zones_folder.append(current_zone)
+
+            zone_path = os.path.join(scene_path, current_zone)
+            output_zone_path = os.path.join(output_scene_path, current_zone)
+
+            if not os.path.exists(output_zone_path):
+                os.makedirs(output_zone_path)
+
+            svd_file_path = os.path.join(output_zone_path, output_svd_filename)
+
+            # add writer into list
+            svd_output_files.append(open(svd_file_path, 'w'))
+
+        # get all images of folder
+        scene_images = sorted([os.path.join(scene_path, img) for img in os.listdir(scene_path) if cfg.scene_image_extension in img])
+        number_scene_image = len(scene_images)
+            
+        for id_img, img_path in enumerate(scene_images):
+            
+            current_image_postfix = dt.get_scene_image_postfix(img_path)
+
+            current_img = Image.open(img_path)
+            img_blocks = segmentation.divide_in_blocks(current_img, (200, 200))
+
+            for id_block, block in enumerate(img_blocks):
+
+                ###########################
+                # feature computation part #
+                ###########################
+
+                data = get_image_features(data_type, block)
+
+                ##################
+                # Data mode part #
+                ##################
+
+                # modify data depending mode
+                if mode == 'svdne':
+
+                    # getting max and min information from min_max_filename
+                    with open(data_min_max_filename, 'r') as f:
+                        min_val = float(f.readline())
+                        max_val = float(f.readline())
+
+                    data = utils.normalize_arr_with_range(data, min_val, max_val)
+
+                if mode == 'svdn':
+                    data = utils.normalize_arr(data)
+
+                # save min and max found from dataset in order to normalize data using whole data known
+                if mode == 'svd':
+
+                    current_min = data.min()
+                    current_max = data.max()
+
+                    if current_min < min_val_found:
+                        min_val_found = current_min
+
+                    if current_max > max_val_found:
+                        max_val_found = current_max
+
+                # now write data into current writer
+                current_file = svd_output_files[id_block]
+
+                # add of index
+                current_file.write(current_image_postfix + ';')
+
+                for val in data:
+                    current_file.write(str(val) + ";")
+
+                current_file.write('\n')
+
+            print(data_type + "_" + mode + "_" + folder_scene + " - " + "{0:.2f}".format((id_img + 1) / number_scene_image * 100.) + "%")
+            sys.stdout.write("\033[F")
+
+        for f in svd_output_files:
+            f.close()
+
+        print('\n')
+
+    # save current information about min file found
+    if mode == 'svd':
+        with open(data_min_max_filename, 'w') as f:
+            f.write(str(min_val_found) + '\n')
+            f.write(str(max_val_found) + '\n')
+
+    print("%s_%s : end of data generation\n" % (data_type, mode))
+
+
+def main():
+
+    parser = argparse.ArgumentParser(description="Compute and prepare data of feature of all scenes (keep in memory min and max value found)")
+
+    parser.add_argument('--feature', type=str, 
+                                    help="feature choice in order to compute data (use 'all' if all features are needed)", required=True)
+    parser.add_argument('--dataset', type=str, 
+                                    help="dataset with all scenes", required=True)
+    parser.add_argument('--output', type=str, 
+                                    help="output where data files are saved", required=True)
+
+    parser.add_argument('--thresholds', type=str, help='file with scene list information and thresholds', required=True)
+
+    args = parser.parse_args()
+
+    p_feature = args.feature
+    p_dataset = args.dataset
+    p_output  = args.output
+    p_thresholds = args.thresholds
+
+    # 1. retrieve human_thresholds
+    human_thresholds = {}
+
+    # extract thresholds
+    with open(p_thresholds) as f:
+        thresholds_line = f.readlines()
+
+        for line in thresholds_line:
+            data = line.split(';')
+            del data[-1] # remove unused last element `\n`
+            current_scene = data[0]
+            thresholds_scene = data[1:]
+
+            # TODO : check if really necessary
+            if current_scene != '50_shades_of_grey':
+                human_thresholds[current_scene] = [ int(threshold) for threshold in  thresholds_scene ]
+
+    # generate all or specific feature data
+    if p_feature == 'all':
+        for m in features_choices:
+            generate_data_feature(p_dataset, p_output, human_thresholds, m, 'svd')
+            generate_data_feature(p_dataset, p_output, human_thresholds, m, 'svdn')
+            generate_data_feature(p_dataset, p_output, human_thresholds, m, 'svdne')
+    else:
+
+        if p_feature not in features_choices:
+            raise ValueError('Unknown feature choice : ', features_choices)
+            
+        generate_data_feature(p_dataset, p_output, human_thresholds, p_feature, 'svd')
+        generate_data_feature(p_dataset, p_output, human_thresholds, p_feature, 'svdn')
+        generate_data_feature(p_dataset, p_output, human_thresholds, p_feature, 'svdne')
+
+if __name__== "__main__":
+    main()

+ 267 - 0
generate/generate_data_model_file.py

@@ -0,0 +1,267 @@
+# main imports
+import sys, os, argparse
+import numpy as np
+import pandas as pd
+import random
+
+# image processing imports
+from PIL import Image
+
+from ipfml import utils
+
+# modules imports
+sys.path.insert(0, '') # trick to enable import of main folder module
+
+import custom_config as cfg
+from modules.utils import data as dt
+from data_attributes import get_image_features
+
+
+# getting configuration information
+learned_folder          = cfg.learned_zones_folder
+min_max_filename        = cfg.min_max_filename_extension
+
+# define all scenes variables
+zones                   = cfg.zones_indices
+seuil_expe_filename     = cfg.seuil_expe_filename
+
+normalization_choices   = cfg.normalization_choices
+features_choices        = cfg.features_choices_labels
+output_data_folder      = cfg.output_datasets
+custom_min_max_folder   = cfg.min_max_custom_folder
+min_max_ext             = cfg.min_max_filename_extension
+zones_indices           = cfg.zones_indices
+
+generic_output_file_svd = '_random.csv'
+
+min_value_interval = sys.maxsize
+max_value_interval = 0
+
+def construct_new_line(threshold, interval, line, choice, each, norm):
+    begin, end = interval
+
+    line_data = line.split(';')
+    seuil = line_data[0]
+    features = line_data[begin+1:end+1]
+
+    features = [float(m) for id, m in enumerate(features) if id % each == 0 ]
+
+    if norm:
+        if choice == 'svdne':
+            features = utils.normalize_arr_with_range(features, min_value_interval, max_value_interval)
+        if choice == 'svdn':
+            features = utils.normalize_arr(features)
+
+    if threshold > int(seuil):
+        line = '1'
+    else:
+        line = '0'
+
+    for val in features:
+        line += ';'
+        line += str(val)
+    line += '\n'
+
+    return line
+
+def get_min_max_value_interval(path, _scenes_list, _interval, _feature):
+
+    global min_value_interval, max_value_interval
+
+    scenes = os.listdir(path)
+
+    # remove min max file from scenes folder
+    scenes = [s for s in scenes if min_max_filename not in s]
+
+    for folder_scene in scenes:
+
+        # only take care of maxwell scenes
+        if folder_scene in _scenes_list:
+
+            scene_path = os.path.join(path, folder_scene)
+
+            zones_folder = []
+            # create zones list
+            for index in zones:
+                index_str = str(index)
+                if len(index_str) < 2:
+                    index_str = "0" + index_str
+                zones_folder.append("zone"+index_str)
+
+            for zone_folder in zones_folder:
+                zone_path = os.path.join(scene_path, zone_folder)
+                data_filename = _feature + "_svd" + generic_output_file_svd
+                data_file_path = os.path.join(zone_path, data_filename)
+
+                # getting number of line and read randomly lines
+                f = open(data_file_path)
+                lines = f.readlines()
+
+                # check if user select current scene and zone to be part of training data set
+                for line in lines:
+
+                    begin, end = _interval
+
+                    line_data = line.split(';')
+                    features = line_data[begin+1:end+1]
+                    features = [float(m) for m in features]
+
+                    min_value = min(features)
+                    max_value = max(features)
+
+                    if min_value < min_value_interval:
+                        min_value_interval = min_value
+
+                    if max_value > max_value_interval:
+                        max_value_interval = max_value
+
+
+def generate_data_model(_filename, _data_path, _interval, _choice, _feature, _thresholds, _learned_zones, _step=1, _each=1, _norm=False, _custom=False):
+
+    output_train_filename = os.path.join(output_data_folder, _filename + ".train")
+    output_test_filename = os.path.join(output_data_folder,_filename + ".test")
+
+    # create path if not exists
+    if not os.path.exists(output_data_folder):
+        os.makedirs(output_data_folder)
+
+    train_file = open(output_train_filename, 'w')
+    test_file = open(output_test_filename, 'w')
+
+    # get zone indices
+    zones_indices = np.arange(16)
+
+    for folder_scene in _learned_zones:
+
+        # get train zones
+        train_zones = _learned_zones[folder_scene]
+        scene_thresholds = _thresholds[folder_scene]
+        scene_path = os.path.join(_data_path, folder_scene)
+
+        for id_zone, index_folder in enumerate(zones_indices):
+
+            index_str = str(index_folder)
+            if len(index_str) < 2:
+                index_str = "0" + index_str
+            current_zone_folder = "zone" + index_str
+
+            zone_path = os.path.join(scene_path, current_zone_folder)
+
+            # if custom normalization choices then we use svd values not already normalized
+            if _custom:
+                data_filename = _feature + "_svd" + generic_output_file_svd
+            else:
+                data_filename = _feature + "_" + _choice + generic_output_file_svd
+
+            data_file_path = os.path.join(zone_path, data_filename)
+
+            # getting number of line and read randomly lines
+            f = open(data_file_path)
+            lines = f.readlines()
+
+            num_lines = len(lines)
+
+            lines_indexes = np.arange(num_lines)
+            random.shuffle(lines_indexes)
+
+            counter = 0
+            # check if user select current scene and zone to be part of training data set
+            for index in lines_indexes:
+
+                image_index = int(lines[index].split(';')[0])
+
+                if image_index % _step == 0:
+                    line = construct_new_line(scene_thresholds[id_zone], _interval, lines[index], _choice, _each, _norm)
+
+                    if id_zone in train_zones:
+                        train_file.write(line)
+                    else:
+                        test_file.write(line)
+
+                counter += 1
+
+            f.close()
+
+    train_file.close()
+    test_file.close()
+
+
+def main():
+
+    # getting all params
+    parser = argparse.ArgumentParser(description="Generate data for model using correlation matrix information from data")
+
+    parser.add_argument('--output', type=str, help='output file name desired (.train and .test)', required=True)
+    parser.add_argument('--data', type=str, help='folder which contains data of dataset', required=True)
+    parser.add_argument('--thresholds', type=str, help='file with scene list information and thresholds', required=True)
+    parser.add_argument('--selected_zones', type=str, help='file which contains all selected zones of scene', required=True)  
+    parser.add_argument('--interval', type=str, help='Interval value to keep from svd', default='"0, 200"', required=True)
+    parser.add_argument('--kind', type=str, help='Kind of normalization level wished', choices=normalization_choices)
+    parser.add_argument('--feature', type=str, help='feature data choice', choices=features_choices, required=True)
+    parser.add_argument('--step', type=int, help='Photo step to keep for build datasets', default=1)
+    parser.add_argument('--each', type=int, help='Each features to keep from interval', default=1)
+    parser.add_argument('--custom', type=str, help='Name of custom min max file if use of renormalization of data', default=False)
+
+    args = parser.parse_args()
+
+    p_filename = args.output
+    p_data     = args.data
+    p_thresholds = args.thresholds
+    p_selected_zones = args.selected_zones
+    p_interval = list(map(int, args.interval.split(',')))
+    p_kind     = args.kind
+    p_feature  = args.feature
+    p_step     = args.step
+    p_each     = args.each
+    p_custom   = args.custom
+
+    # 1. retrieve human_thresholds
+    human_thresholds = {}
+
+    # extract thresholds
+    with open(p_thresholds) as f:
+        thresholds_line = f.readlines()
+
+        for line in thresholds_line:
+            data = line.split(';')
+            del data[-1] # remove unused last element `\n`
+            current_scene = data[0]
+            thresholds_scene = data[1:]
+
+            # TODO : check if really necessary
+            if current_scene != '50_shades_of_grey':
+                human_thresholds[current_scene] = [ int(threshold) for threshold in  thresholds_scene ]
+
+    # 2. get selected zones
+    selected_zones = {}
+    with(open(p_selected_zones, 'r')) as f:
+
+        for line in f.readlines():
+
+            data = line.split(';')
+            del data[-1]
+            scene_name = data[0]
+            thresholds = data[1:]
+
+            selected_zones[scene_name] = [ int(t) for t in thresholds ]
+
+    # find min max value if necessary to renormalize data
+    if p_custom:
+        get_min_max_value_interval(p_data, selected_zones, p_interval, p_feature)
+
+        # write new file to save
+        if not os.path.exists(custom_min_max_folder):
+            os.makedirs(custom_min_max_folder)
+
+        min_max_folder_path = os.path.join(os.path.dirname(__file__), custom_min_max_folder)
+        min_max_filename_path = os.path.join(min_max_folder_path, p_custom)
+
+        with open(min_max_filename_path, 'w') as f:
+            f.write(str(min_value_interval) + '\n')
+            f.write(str(max_value_interval) + '\n')
+
+    # create database using img folder (generate first time only)
+    generate_data_model(p_filename, p_data, p_interval, p_kind, p_feature, human_thresholds, selected_zones, p_step, p_each, p_custom)
+
+if __name__== "__main__":
+    main()

+ 104 - 0
generate/generate_selected_zones_file.py

@@ -0,0 +1,104 @@
+# main imports
+import numpy as np
+import pandas as pd
+import sys, os, argparse
+import random
+
+
+# modules and config imports
+sys.path.insert(0, '') # trick to enable import of main folder module
+
+import custom_config as cfg
+
+
+def save_learned_zones(output_name, scene, zones):
+
+    if not os.path.exists(cfg.output_zones_learned):
+        os.makedirs(cfg.output_zones_learned)
+
+    with open(os.path.join(cfg.output_zones_learned, output_name), 'a') as f:
+        f.write(scene + ';')
+
+        for zone in zones:
+            f.write(str(zone) + ';')
+
+        f.write('\n')
+
+
+def get_random_zones(scene, zones, n_zones):
+
+    random.shuffle(zones)
+
+    # specific case for 'Cuisine01' (zone 12 is also noisy even in reference image)
+    # if scene == 'Cuisine01':
+    #     while 12 in zones[0:n_zones]:
+    #         random.shuffle(zones)
+    
+    return zones[0:n_zones]
+
+def main():
+
+    parser = argparse.ArgumentParser(description="Read and compute entropy data file (using diff)")
+
+    parser.add_argument('--folder', type=str, help='dataset scene folder', required=True)
+    parser.add_argument('--n_zones', type=int, help='number of zones used in train', default=10)
+    parser.add_argument('--output', type=str, help='file with specific training zone', required=True)
+    parser.add_argument('--thresholds', type=str, help='file with specific thresholds (using only scene from this file', default='')
+
+    args = parser.parse_args()
+
+    p_folder       = args.folder
+    p_n_zones      = args.n_zones
+    p_output       = args.output
+    p_thresholds   = args.thresholds
+
+    # extract scenes to use if specified
+    available_scenes = None
+
+    if len(p_thresholds) > 0:
+        
+        available_scenes = []
+
+        with open(p_thresholds) as f:
+            thresholds_line = f.readlines()
+
+            for line in thresholds_line:
+                data = line.split(';')
+                del data[-1] # remove unused last element `\n`
+                current_scene = data[0]
+
+                # need to rename `current_name` because we only used part6
+                # scene_split = current_scene.split('_')
+                # del scene_split[-1]
+                # scene_name = '_'.join(scene_split)
+
+                available_scenes.append(current_scene)
+
+
+    # specific number of zones (zones indices)
+    zones = np.arange(16)
+
+    # get all scene names
+    scenes = os.listdir(p_folder)
+
+    # create output thresholds directory if necessary
+    folder, _ = os.path.split(p_output)
+
+    if len(folder) > 0:
+        os.makedirs(folder)
+
+    # for each scene we generate random zones choice
+    for folder_scene in scenes:
+
+        if available_scenes is not None:
+
+            if folder_scene in available_scenes:
+                selected_zones = get_random_zones(folder_scene, zones, p_n_zones)
+                save_learned_zones(p_output, folder_scene, selected_zones)
+        else:
+            selected_zones = get_random_zones(folder_scene, zones, p_n_zones)
+            save_learned_zones(p_output, folder_scene, selected_zones)
+            
+
+if __name__== "__main__":
+    main()