pynovisao.py 43 KB
Newer Older
1 2
#
"""
3 4 5 6
    This file must contain the implementation code for all actions of pynovisao.
    
    Name: pynovisao.py
    Author: Alessandro dos Santos Ferreira ( santosferreira.alessandro@gmail.com )
7
"""
8
import sys
9
import gc
10
from collections import OrderedDict
11
import numpy as np
12
import os
13
import interface
14 15
import types
import cv2
16
from interface.interface import InterfaceException as IException
17
from PIL import Image
18

19
import segmentation
20
import extraction
21
from extraction import FeatureExtractor
22

23
import classification
24
from classification import Classifier
25

26
import util
27 28
from extraction.extractor_frame_video import ExtractFM

29
from util.config import Config
30
from util.file_utils import File
31
from util.utils import TimeUtils
32 33
from util.utils import MetricUtils
from util.x11_colors import X11Colors
34 35 36 37
import multiprocessing
from multiprocessing import Process, Manager
import  threading
from tqdm import tqdm
38
class Act(object):
39
    """Store all actions of Pynovisao."""
40

Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
41
    def __init__(self, tk, args):
42 43 44 45 46 47 48 49 50
        """Constructor.

        Parameters
        ----------
        tk : Interface
            Pointer to interface that handles UI.
        args : Dictionary
            Arguments of program.
        """
51
        self.tk = tk
52
        self.has_trained = False
53 54 55
        
        self.segmenter = [segmentation._segmenter_list[segmenter].meta for segmenter in segmentation._segmenter_list
                            if segmentation._segmenter_list[segmenter].value == True ][0]()
56 57 58
        
        self.extractors = [extraction._extractor_list[extractor].meta for extractor in extraction._extractor_list
                            if extraction._extractor_list[extractor].value == True ]
59 60 61 62 63 64
        
        try:
            self.classifier = [classification._classifier_list[classifier].meta for classifier in classification._classifier_list
                                if classification._classifier_list[classifier].value == True ][0]()
        except:
            self.classifier = None
65

66 67
        self._image = None
        self._const_image = None
68
        self._mask_image = None
69
        self._image_name = None
70
        self._image_path = None
71
                    
72 73
        self._init_dataset(args["dataset"])
        self._init_classes(args["classes"], args["colors"])
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
74

75
        self._dataset_generator = True
76 77
        self._ground_truth = False
        self._gt_segments = None
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
78
        self.weight_path = None
79

80
    
81
    def _init_dataset(self, directory):
82 83 84 85 86 87 88
        """Initialize the directory of image dataset.

        Parameters
        ----------
        directory : string
            Path to directory.
        """
89 90 91 92
        if(directory[-1] == '/'):
            directory = directory[:-1]
            
        self.dataset = directory
93
        File.create_dir(self.dataset)
94
    
95
    def _init_classes(self, classes = None, colors = None):
96 97 98 99 100 101 102 103 104 105
        """Initialize the classes of dataset.

        Parameters
        ----------
        classes : list of string, optional, default = None
            List of classes. If not informed, the metod set as classes all classes in dataset. 
            If there's no classes in dataset, adds two default classes.
        colors : list of string, optional, default = None
            List de colors representing the color of classe, in same order. If not informed, chooses a color at random.
        """
106
        self.classes = []
107 108 109 110 111 112 113 114 115 116 117 118 119 120

        dataset_description_path = File.make_path(self.dataset, '.dataset_description.txt')

        if os.path.exists(dataset_description_path):
            colors = []
            classes = []
            file = open(dataset_description_path, "r") 
            for line in file:
                class_info = line.replace("\n", "").split(",")
                classes.append(class_info[0])
                colors.append(class_info[1])                 
        else:
            classes = sorted(File.list_dirs(self.dataset)) if classes is None else classes.split()
            colors = [] if colors is None else colors.split()
121 122 123 124 125 126 127

        if(len(classes) > 0):
            for i in range(0, len(classes)):
                self.add_class(dialog = False, name=classes[i], color=colors[i] if i < len(colors) else None)
        else:
            self.add_class(dialog = False, color='Green')
            self.add_class(dialog = False, color='Yellow')
128
                
129
        self._current_class = 0
130
        
131

132
    def open_image(self, imagename = None):
133 134 135 136 137 138 139
        """Open a new image.

        Parameters
        ----------
        imagename : string, optional, default = None
            Filepath of image. If not informed open a dialog to choose.
        """
140 141
        
        def onclick(event):
142
            """Binds dataset generator event to click on image."""
143
            print(event)
144
            if event.xdata != None and event.ydata != None and int(event.ydata) != 0 and self._dataset_generator == True:
145 146
                x = int(event.xdata)
                y = int(event.ydata)
147 148 149 150 151 152 153
                self.tk.write_log("Coordinates: x = %d y = %d", x, y)
                
                segment, size_segment, idx_segment, run_time = self.segmenter.get_segment(x, y)
                
                if size_segment > 0:
                    self.tk.append_log("\nSegment = %d: %0.3f seconds", idx_segment, run_time)
                    
154
                    self._image, run_time = self.segmenter.paint_segment(self._image, self.classes[self._current_class]["color"].value, x, y)
155
                    self.tk.append_log("Painting segment: %0.3f seconds", run_time)
156
                    self.tk.refresh_image(self._image)
157
                    
158 159 160 161
                    if self._ground_truth == True:
                        self._gt_segments[idx_segment] = self.classes[self._current_class]["name"].value

                    elif self._dataset_generator == True:
162
                        filepath = File.save_class_image(segment, self.dataset, self.classes[self._current_class]["name"].value, self._image_name, idx_segment)
163 164
                        if filepath:
                            self.tk.append_log("\nSegment saved in %s", filepath)
165 166 167
        
        if imagename is None:
            imagename = self.tk.utils.ask_image_name()
168 169

        if imagename:
170 171
            self._image = File.open_image(imagename)
            self._image_name = File.get_filename(imagename)
172

173 174 175
            self.tk.write_log("Opening %s...", self._image_name)
            self.tk.add_image(self._image, self._image_name, onclick)
            self._const_image = self._image
176
            
177
            self.segmenter.reset()
178
            self._gt_segments = None
179

180
        
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
181 182 183 184

    def open_weight(self):
        """Open a new weight."""
        self.weight_path = self.tk.utils.ask_weight_name()
185
        self.classifier.weight_path = self.weight_path
186
        print(self.weight_path)
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
187
        
188
    def restore_image(self):
189 190
        """Refresh the image and clean the segmentation.
        """
191 192 193 194
        if self._const_image is not None:
            self.tk.write_log("Restoring image...")
            self.tk.refresh_image(self._const_image)
            
195
            self.segmenter.reset()
196
            self._gt_segments = None
197 198
        
    def close_image(self):
199
        """Close the image.
200
        
201 202 203 204 205
        Raises
        ------
        IException 'Image not found'
            If there's no image opened.
        """
206
        if self._const_image is None:
207
            raise IException("Image not found!  Open an image to test, select in the menu the option File>Open Image!")
208 209 210
        
        if self.tk.close_image():
            self.tk.write_log("Closing image...")
211
            self._const_image = None
212
            self._image = None
213
            self._image_path = None
214 215

    def add_class(self, dialog = True, name = None, color = None):
216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232
        """Add a new class.

        Parameters
        ----------
        dialog : boolean, optional, default = True
            If true open a config dialog to add the class.
        name : string, optional, default = None
            Name of class. If not informed set the name 'Class_nn' to class.
        color : string, optional, default = None
            Name of color in X11Color format, representing the class. It will used to paint the segments of class.
            If not informed choose a color at random.
            
        Raises
        ------
        IException 'You have reached the limite of %d classes'
            If you already have created self.tk.MAX_CLASSES classes.
        """
233 234 235
        n_classes = len(self.classes)
        if n_classes >= self.tk.MAX_CLASSES:
            raise IException("You have reached the limite of %d classes" % self.tk.MAX_CLASSES)
236
                
237
        def edit_class(index):
238
            """Calls method that edit the class."""
239
            self.edit_class(index)
240 241
            
        def update_current_class(index):
242
            """Calls method that update the class."""
243
            self.update_current_class(index)
244 245
        
        def process_config():
246
            """Add the class and refresh the panel of classes."""
247
            new_class = self.tk.get_config_and_destroy()
248
            new_class["name"].value = '_'.join(new_class["name"].value.split())
249 250 251

            self.classes.append( new_class )
            self.tk.write_log("New class: %s", new_class["name"].value)
252
            self.tk.refresh_panel_classes(self.classes, self._current_class)
253
            
254 255
        if name is None:
            name = "Class_%02d" % (n_classes+1)
256
        if color is None:
257
            color = util.X11Colors.random_color()
258 259
            
        class_config = OrderedDict()
260
        class_config["name"] = Config(label="Name", value=name, c_type=str)
261
        class_config["color"] = Config(label="Color (X11 Colors)", value=color, c_type='color')
262 263
        class_config["callback"] = Config(label=None, value=update_current_class, c_type=None, hidden=True)
        class_config["callback_color"] = Config(label=None, value=edit_class, c_type=None, hidden=True)
264 265 266 267 268 269 270
        class_config["args"] = Config(label=None, value=n_classes, c_type=int, hidden=True)
        
        if dialog == False:
            self.classes.append( class_config )
            return 

        title = "Add a new classe"
271 272 273
        self.tk.dialogue_config(title, class_config, process_config)        
      

274
    def edit_class(self, index):
275 276 277 278 279 280 281
        """Edit a class.

        Parameters
        ----------
        index : integer.
            Index of class in list self.classes.
        """
282
        def process_update(index):
283
            """Update the class."""
284
            updated_class = self.tk.get_config_and_destroy()
285
            updated_class["name"].value = '_'.join(updated_class["name"].value.split())
286 287 288
            
            self.classes[index] = updated_class
            self.tk.write_log("Class updated: %s", updated_class["name"].value)
289
            self.tk.refresh_panel_classes(self.classes, self._current_class)
290 291 292 293 294 295
        
        current_config = self.classes[index]
            
        title = "Edit class %s" % current_config["name"].value
        self.tk.dialogue_config(title, current_config, lambda *_ : process_update(index))
            
296
    def update_current_class(self, index):
297 298
        """Update the current class.
        """
299
        self._current_class = index
300 301
        
    def get_class_by_name(self, name):
302 303 304 305
        """Return the index for class.
        
        Parameters
        ----------
306
        name : string
307 308 309 310
            Name of class.
            
        Returns
        -------
311
        index : integer
312 313 314 315 316 317 318
            Index of class in list self.classes.

        Raises
        ------
        Exception 'Class not found'
            If name not found in self.classes.
        """
319 320 321 322 323 324
        name = name.strip()
        
        for cl in self.classes:
            if cl["name"].value == name:
                return cl
        raise Exception("Class not found")
325

326
        
327
    def set_dataset_path(self):
328 329
        """Open a dialog to choose the path to directory of image dataset.
        """
330 331
        directory = self.tk.utils.ask_directory(default_dir = self.dataset)
        if directory:
332
            self._init_dataset(directory)
333 334
            self.tk.write_log("Image dataset defined: %s", self.dataset)
            
335
            self._init_classes()
336
            self.tk.refresh_panel_classes(self.classes)
337
            
338
            if self.classifier: self.classifier.reset()
339
        self.has_trained=False
340
            
341
    def toggle_dataset_generator(self):
342 343
        """Enable/disable the dataset generator on click in image.
        """
344
        self._dataset_generator = not self._dataset_generator
345

346 347
            
    def select_segmenter(self):
348 349
        """Open a dialog to choose the segmenter.
        """
350 351
        title = "Choosing a segmenter"
        self.tk.write_log(title)
352

353
        current_config = segmentation.get_segmenter_config()
354
        
355
        def process_config():
356
            """Update the current segmenter."""
357
            new_config = self.tk.get_config_and_destroy()
358

359 360 361
            self.segmenter = [new_config[segmenter].meta for segmenter in new_config
                                if new_config[segmenter].value == True ][0]()

362
            self.tk.append_log("\nSegmenter: %s\n%s", str(self.segmenter.get_name()), str(self.segmenter.get_summary_config()))
363 364 365 366 367
            segmentation.set_segmenter_config(new_config)

        self.tk.dialogue_choose_one(title, current_config, process_config)

    def config_segmenter(self):
368 369
        """Open a dialog to configure the current segmenter.
        """
370 371 372 373 374 375
        title = "Configuring %s" % self.segmenter.get_name()
        self.tk.write_log(title)

        current_config = self.segmenter.get_config()
        
        def process_config():
376
            """Update the configs of current segmenter."""
377 378 379
            new_config = self.tk.get_config_and_destroy()

            self.segmenter.set_config(new_config)
380
            self.tk.append_log("\nConfig updated:\n%s", str(self.segmenter.get_summary_config()))
381
            self.segmenter.reset()
382 383

        self.tk.dialogue_config(title, current_config, process_config)
384
        
385
    def run_segmenter(self, refresh_image=True):
386
        """Do the segmentation of image, using the current segmenter.
387
        
388 389 390 391 392
        Raises
        ------
        IException 'Image not found'
            If there's no image opened.
        """
393
        if self._const_image is None:
394
            raise IException("Image not found!  Open an image to test, select in the menu the option File>Open Image!")
395
        
396
        self.tk.write_log("Running %s...", self.segmenter.get_name())
397 398 399 400 401

        self.tk.append_log("\nConfig: %s", str(self.segmenter.get_summary_config()))
        self._image, run_time = self.segmenter.run(self._const_image)
        self.tk.append_log("Time elapsed: %0.3f seconds", run_time)
        
402 403
        self._gt_segments = [None]*(max(self.segmenter.get_list_segments())+1)
        
404 405
        if refresh_image:
            self.tk.refresh_image(self._image)
406 407


408
    def select_extractors(self):
409
        """Open a dialog to select the collection of extractors.
410
        
411 412 413 414 415
        Raises
        ------
        IException 'Please select at least one extractor'
            If no extractor was selected.
        """
416 417 418 419 420 421
        title = "Selecting extractors"
        self.tk.write_log(title)

        current_config = extraction.get_extractor_config()
        
        def process_config():
422
            """Update the collection of extractors."""
423 424 425 426
            new_config = self.tk.get_config_and_destroy()

            self.extractors = [new_config[extractor].meta for extractor in new_config
                                if new_config[extractor].value == True ]
427
            
428
            if len(self.extractors) == 0:
429
                raise IException("Please select an extractor from the menu under Features Extraction> Select extractors! ")
430
            
431 432 433 434 435 436
            self.tk.append_log("\nConfig updated:\n%s", 
                                '\n'.join(["%s: %s" % (new_config[extractor].label, "on" if new_config[extractor].value==True else "off")
                                            for extractor in new_config]))
            extraction.set_extractor_config(new_config)

        self.tk.dialogue_select(title, current_config, process_config)
437 438
        
    def run_extractors(self):
439 440
        """Perform a feature extraction on all images of dataset, using the current collection of extractors.
        """
441
        self.tk.write_log("Running extractors on all images in %s", self.dataset)
442 443
        self.tk._root.update_idletasks()
        fextractor = FeatureExtractor(self.extractors,self.tk)
444 445
        self.tk.append_log("%s", '\n'.join([extraction._extractor_list[extractor].label for extractor in extraction._extractor_list
                                                if extraction._extractor_list[extractor].value == True ]))
446
        
447
        output_file, run_time = fextractor.extract_all(self.dataset, "training")
448 449
        self.tk.append_log("\nOutput file saved in %s", output_file)
        self.tk.append_log("Time elapsed: %0.3f seconds", run_time)
450 451
        
        if self.classifier: self.classifier.reset()
452

453 454 455 456 457
    def run_extract_frame(self):
        self.tk.write_log("Running extract frames from videos")
        extract_frame=ExtractFM()
        extract_frame.run(self.tk)

458
    def select_classifier(self):
459 460 461 462 463 464 465
        """Open a dialog to select the classifier.
        
        Raises
        ------
        IException 'You must install python-weka-wrapper'
            The user must install the required dependencies to classifiers.
        """
466
        if self.classifier is None:
467
            raise IException("Classifier not found! Select from the menu the option Training>Choose Classifier!")
468 469 470 471 472
        
        title = "Choosing a classifier"
        self.tk.write_log(title)

        current_config = classification.get_classifier_config()
473

474 475
        
        def process_config():
476
            """Update the current classifier."""
477
            new_config = self.tk.get_config_and_destroy()
Geazy Menezes's avatar
Geazy Menezes committed
478
            
479 480 481 482 483 484 485 486 487
            self.classifier = [new_config[classifier].meta for classifier in new_config
                                if new_config[classifier].value == True ][0]()

            self.tk.append_log("\nClassifier: %s\n%s", str(self.classifier.get_name()), str(self.classifier.get_summary_config()))
            classification.set_classifier_config(new_config)

        self.tk.dialogue_choose_one(title, current_config, process_config)
        
    def configure_classifier(self):
488 489 490 491 492 493 494
        """Set the configuration of current classifier.
        
        Raises
        ------
        IException 'You must install python-weka-wrapper'
            The user must install the required dependencies to classifiers.
        """
495
        if self.classifier is None:
496
            raise IException("Classifier not found! Select from the menu the option Training>Choose Classifier!")
497 498 499 500 501 502 503 504 505 506 507
        
        title = "Configuring %s" % self.classifier.get_name()
        self.tk.write_log(title)

        current_config = self.classifier.get_config()
        
        def process_config():
            new_config = self.tk.get_config_and_destroy()

            self.classifier.set_config(new_config)
            self.tk.append_log("\nConfig updated:\n%s", str(self.classifier.get_summary_config()))
508 509
            
            if self.classifier: self.classifier.reset()
510 511 512 513 514

        self.tk.dialogue_config(title, current_config, process_config)
    
    
    def run_classifier(self):
515 516
        """Run the classifier on the current image.
        As result, paint the image with color corresponding to predicted class of all segment.
517

518 519 520 521 522 523 524
        Raises
        ------
        IException 'You must install python-weka-wrapper'
            The user must install the required dependencies to classifiers.
        IException 'Image not found'
            If there's no image opened.
        """
525
        if self.classifier is None:
526 527
            raise IException("Classifier not found! Select from the menu the option Training>Choose Classifier!")

528
        if self._const_image is None:
529 530
            raise IException("Image not found!  Open an image to test, select in the menu the option File>Open Image!")

531 532
        self.tk.write_log("Running %s...", self.classifier.get_name())
        self.tk.append_log("\n%s", str(self.classifier.get_summary_config()))
533

534
        #self.classifier.set
535

536 537
        start_time = TimeUtils.get_time()

538
        # Perform a segmentation, if needed.
539 540 541
        list_segments = self.segmenter.get_list_segments()
        if len(list_segments) == 0:
            self.tk.append_log("Running %s... (%0.3f seconds)", self.segmenter.get_name(), (TimeUtils.get_time() - start_time))
542

543
            self._image, _ = self.segmenter.run(self._const_image)
544
            self.tk.refresh_image(self._image)
545
            list_segments = self.segmenter.get_list_segments()
546
            self._gt_segments = [None]*(max(list_segments)+1)
547

548
        #  New and optimized classification
549
        tmp = ".tmp"
550
        File.remove_dir(File.make_path(self.dataset, tmp))
551

552
        self.tk.append_log("Generating test images... (%0.3f seconds)", (TimeUtils.get_time() - start_time))
553

554
        len_segments = {}
555 556 557 558 559 560 561 562 563 564 565

        print("Wait to complete processes all images!")
        with tqdm(total=len(list_segments)) as pppbar:
            for idx_segment in list_segments:
                segment, size_segment, idx_segment = self.segmenter.get_segment(self, idx_segment=idx_segment)[:-1]
                # Problem here! Dataset removed.
                filepath = File.save_only_class_image(segment, self.dataset, tmp, self._image_name, idx_segment)
                len_segments[idx_segment] = size_segment
                pppbar.update(1)
            pppbar.close()

566

567
        # Perform the feature extraction of all segments in image ( not applied to ConvNets ).
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
568
        if self.classifier.must_extract_features():
569 570
            self.tk.append_log("Running extractors on test images... (%0.3f seconds)", (TimeUtils.get_time() - start_time))
            fextractor = FeatureExtractor(self.extractors)
571
            output_file, _ = fextractor.extract_all(self.dataset, "test", dirs=[tmp])
572

573
        self.tk.append_log("Running classifier on test data... (%0.3f seconds)", (TimeUtils.get_time() - start_time))
574 575

        # Get the label corresponding to predict class for each segment of image.
576 577
        labels = self.classifier.classify(self.dataset, test_dir=tmp, test_data="test.arff", image=self._const_image)
        File.remove_dir(File.make_path(self.dataset, tmp))
578

579 580 581
        # Result is the class for each superpixel
        if type(labels) is types.ListType:
            self.tk.append_log("Painting segments... (%0.3f seconds)", (TimeUtils.get_time() - start_time))
582

583 584 585
            # If ground truth mode, show alternative results
            if self._ground_truth == True:
                return self._show_ground_truth(list_segments, len_segments, labels, start_time)
586

587 588
            # Create a popup with results of classification.
            popup_info = "%s\n" % str(self.classifier.get_summary_config())
589

590 591
            len_total = sum([len_segments[idx] for idx in len_segments])
            popup_info += "%-16s%-16s%0.2f%%\n" % ("Total", str(len_total), (len_total*100.0)/len_total)
592

593 594 595 596 597
            # Paint the image.
            self._mask_image = np.zeros(self._const_image.shape[:-1], dtype="uint8")
            height, width, channels = self._image.shape
            self.class_color = np.zeros((height,width,3), np.uint8)
            for (c, cl) in enumerate(self.classes):
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
598
                idx_segment = [ list_segments[idx] for idx in range(0, len(labels)) if cl["name"].value == labels[idx] or c == labels[idx]]
599 600 601 602 603
                if len(idx_segment) > 0:
                    self._image, _ = self.segmenter.paint_segment(self._image, cl["color"].value, idx_segment=idx_segment, border=False)
                    for idx in idx_segment:
                        self._mask_image[self.segmenter._segments == idx] = c
                        self.class_color[self.segmenter._segments == idx] = X11Colors.get_color(cl["color"].value)
604

605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621
                len_classes = sum([len_segments[idx] for idx in idx_segment])
                popup_info += "%-16s%-16s%0.2f%%\n" % (cl["name"].value, str(len_classes), (len_classes*100.0)/len_total)


            self.tk.refresh_image(self._image)
            self.tk.popup(popup_info)
        else:
            # Result is an image
            self._mask_image = labels
            height, width, channels = self._image.shape
            self.class_color = np.zeros((height,width,3), np.uint8)

            for (c, cl) in enumerate(self.classes):
                self.class_color[labels == c] = X11Colors.get_color(cl["color"].value)

            self._image = cv2.addWeighted(self._const_image, 0.7, self.class_color, 0.3, 0)
            self.tk.refresh_image(self._image)
622

623

624
        end_time = TimeUtils.get_time()
625

626 627
        self.tk.append_log("\nClassification finished")
        self.tk.append_log("Time elapsed: %0.3f seconds", (end_time - start_time))
628
        gc.collect()
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
629 630 631

    def run_training(self):
        start_time = TimeUtils.get_time()
632
        
633 634 635
        # Training do not need an image opened (consider removing these two lines)
        #      if self._const_image is None:
        #          raise IException("Image not found")
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
636 637 638 639 640 641 642 643 644 645
        
        if self.classifier.must_train():
            
            if self.classifier.must_extract_features():
                self.tk.append_log("Creating training data... (%0.3f seconds)", (TimeUtils.get_time() - start_time))
                fextractor = FeatureExtractor(self.extractors)
                output_file, run_time = fextractor.extract_all(self.dataset, "training", overwrite = False)
        
            self.tk.append_log("Training classifier...")
            
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
646
            self.classifier.train(self.dataset, "training")
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
647 648 649 650

            self.tk.append_log("DONE (%0.3f seconds)",  (TimeUtils.get_time() - start_time))
        
        self._image = self._const_image
651
        self.has_trained=True
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
652

653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693
    
    def _show_ground_truth(self, list_segments, len_segments, labels, start_time):
        """Paint only wrong classified segments and show ground truth confusion matrix.
        
        Parameters
        ----------
        list_segments : list of integer
            List of index segments.
        len_segments : list of integer
            List of segments sizes.
        labels : list of string
            List of predicted class name for each segment.
        start_time : floating point
            Start time of classification.
        """
        classes = list(set(labels))
        classes.sort()
        
        n_segments = len(labels)
        spx_matrix = np.zeros((len(classes), len(classes)), np.int) 
        px_matrix = np.zeros((len(classes), len(classes)), np.int) 

        # Create the confusion matrix and paint wrong classified segments individually.
        for idx_segment in list_segments:
            if self._gt_segments[idx_segment] is not None:
                gt_class = classes.index(self._gt_segments[idx_segment])
                predicted_class = classes.index(labels[idx_segment])
                
                spx_matrix[ gt_class ][ predicted_class ] += 1
                px_matrix[ gt_class ][ predicted_class ] += len_segments[idx_segment]
        
                if gt_class != predicted_class:
                    self._image, _ = self.segmenter.paint_segment(self._image, self.get_class_by_name(labels[idx_segment])["color"].value, idx_segment=[idx_segment], border=False)
        
        # Create a popup with results of classification.
        popup_info = "%s\n" % str(self.classifier.get_summary_config())
        popup_info += Classifier.confusion_matrix(classes, spx_matrix, "Superpixels")
        popup_info += Classifier.confusion_matrix(classes, px_matrix, "PixelSum")
        
        self.tk.refresh_image(self._image)
        self.tk.popup(popup_info)
694

695 696 697 698 699
        end_time = TimeUtils.get_time()
            
        self.tk.append_log("\nClassification finished")
        self.tk.append_log("Time elapsed: %0.3f seconds", (end_time - start_time))
        
700

701 702 703 704 705
    def toggle_ground_truth(self):
        """Enable/disable ground truth mode.
        """
        self._ground_truth = not self._ground_truth
        
706
    def cross_validation(self):
707 708 709 710 711 712 713
        """Run a cross validation on all generated segments in image dataset.
        
        Raises
        ------
        IException 'You must install python-weka-wrapper'
            The user must install the required dependencies to classifiers.
        """
714
        if self.classifier is None:
715
            raise IException("Classifier not found! Select from the menu the option Training>Choose Classifier!")
716 717 718 719 720 721 722 723 724 725 726 727 728 729
        
        if self.classifier.must_train():
            self.tk.write_log("Creating training data...")
            
            fextractor = FeatureExtractor(self.extractors)
            output_file, run_time = fextractor.extract_all(self.dataset, "training", overwrite = False)
            self.classifier.train(self.dataset, "training")
        
        self.tk.write_log("Running Cross Validation on %s...", self.classifier.get_name())
        self.tk.append_log("\n%s", str(self.classifier.get_summary_config()))
        
        popup_info = self.classifier.cross_validate()
        self.tk.append_log("Cross Validation finished")
        self.tk.popup(popup_info)
730 731
        
    def experimenter_all(self):
732 733 734 735 736 737 738
        """Perform a test in all availabel classifiers e show the results.
        
        Raises
        ------
        IException 'You must install python-weka-wrapper'
            The user must install the required dependencies to classifiers.
        """
739
        if self.classifier is None:
740
            raise IException("Classifier not found! Select from the menu the option Training>Choose Classifier!")
741 742 743 744
        
        if self.tk.ask_ok_cancel("Experimenter All", "This may take several minutes to complete. Are you sure?"):
            if self.classifier.must_train():
                self.tk.write_log("Creating training data...")
745

746 747 748 749 750 751 752 753 754
                fextractor = FeatureExtractor(self.extractors)
                output_file, run_time = fextractor.extract_all(self.dataset, "training", overwrite = False)
                self.classifier.train(self.dataset, "training")
                
            self.tk.write_log("Running Experimenter All on %s...", self.classifier.get_name())
            
            popup_info = self.classifier.experimenter()
            self.tk.append_log("\nExperimenter All finished")
            self.tk.popup(popup_info)
755 756


757
    def about(self):
758
        self.tk.show_info("Pynovisao\n\nVersion 1.0.0\n\nAuthors:\nAdair da Silva Oliveira Junior\nAlessandro dos Santos Ferreira\nDiego Andre Sant Ana\nDiogo Nunes Goncalves\nEverton Castelao Tetila\nFelipe Silveira\nGabriel Kirsten Menezes\nGilberto Astolfi\nHemerson Pistori\nNicolas Alessandro de Souza Belete")
759 760
        
            
761
    def func_not_available(self):
762
        """Use this method to bind menu options not available."""
763
        self.tk.write_log("This functionality is not available right now.")
764

765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868
    def assign_using_labeled_image(self, imagename = None, refresh_image=True):
        """Open a new image.

        Parameters
        ----------
        imagename : string, optional, default = None
            Filepath of image. If not informed open a dialog to choose.
        """

        if len(self.segmenter.get_list_segments()) == 0:
            self.tk.write_log("Error: Image not segmented")
            return

        if self._image is None:
            self.tk.write_log("Error: Open the image to be targeted")
            return

        if imagename is None:
            imagename = self.tk.utils.ask_image_name()

        if imagename:
            self._image_gt = File.open_image_lut(imagename)
            self._image_gt_name = File.get_filename(imagename)

            self.tk.write_log("Opening %s...", self._image_gt_name)

            qtd_classes = len(self.classes)
            qtd_superpixel = len(self.segmenter.get_list_segments())

        tam_gt = self._image_gt.shape
        tam_im = self._image.shape
        if len(tam_gt) > 2:
            self.tk.write_log("Color image is not supported. You must open a gray-scale image")
            return

        if tam_gt[0] != tam_im[0] or tam_gt[1] != tam_im[1]:
            self.tk.write_log("Images with different sizes")
            return
            
        #hist_classes_superpixels = np.zeros((qtd_superpixel, qtd_classes), np.int)      
    
        #for i in range(0, tam_gt[0]):
        #    for j in range(0, tam_gt[1]):          
        #        class_pixel = self._image_gt[i,j]
        #        if class_pixel > qtd_classes:
        #            self.tk.write_log("There is no class for the pixel [%d,%d] = %d on the image", i, j, class_pixel)
        #        else:
        #            #segment, size_segment, idx_segment, run_time = self.segmenter.get_segment(px = j, py = i)
        #            idx_segment = self.segmenter._segments[i, j]
        #            hist_classes_superpixels[idx_segment, class_pixel] = hist_classes_superpixels[idx_segment, class_pixel] + 1
        #    if i % 10 == 0:
        #        self.tk.write_log("Annotating row %d of %d", i, tam_gt[0])
                
        qtd_bad_superpixels = 0
        
        for idx_segment in range(0, qtd_superpixel):
            hist_classes_superpixels = np.histogram(self._image_gt[self.segmenter._segments == idx_segment], bins=range(0,len(self.classes)+1))[0]

            idx_class = np.argmax(hist_classes_superpixels)
            sum_vector = np.sum(hist_classes_superpixels)
            if refresh_image:
                self._image, run_time = self.segmenter.paint_segment(self._image, self.classes[idx_class]["color"].value, idx_segment = [idx_segment])
            #self.tk.append_log("posicao maior = %x  --  soma vetor %d", x, sum_vector)
            if hist_classes_superpixels[idx_class]/sum_vector < 0.5:
                qtd_bad_superpixels = qtd_bad_superpixels + 1

            if self._ground_truth == True:
                self._gt_segments[idx_segment] = self.classes[self._current_class]["name"].value

            elif self._dataset_generator == True:
                if idx_segment % 10 == 0:
                    self.tk.write_log("Saving %d of %d", (idx_segment+1), qtd_superpixel)

                segment, size_segment, idx_segment, run_time = self.segmenter.get_segment(idx_segment = idx_segment)
                filepath = File.save_class_image(segment, self.dataset, self.classes[idx_class]["name"].value, self._image_name, idx_segment)
                if filepath:
                    self.tk.append_log("\nSegment saved in %s", filepath)

        self.tk.refresh_image(self._image)
        self.tk.write_log("%d bad annotated superpixels of %d superpixel (%0.2f)", qtd_bad_superpixels, qtd_superpixel, (float(qtd_bad_superpixels)/qtd_superpixel)*100)



    def run_segmenter_folder(self, foldername=None):

        if foldername is None:
            foldername = self.tk.utils.ask_directory()

        valid_images_extension = ['.jpg', '.png', '.gif', '.jpeg', '.tif']

        fileimages = [name for name in os.listdir(foldername)
                    if os.path.splitext(name)[-1].lower() in valid_images_extension]

        for (i,file) in enumerate(fileimages):
            path_file = os.path.join(foldername, file)
            self.open_image(path_file)
            self.run_segmenter(refresh_image=False)
            label_image = (os.path.splitext(file)[-2] + '_json')
            self.assign_using_labeled_image(os.path.join(foldername, label_image, 'label.png'), refresh_image=False)
            self.tk.write_log("%d of %d images", i, len(fileimages))

    def run_classifier_folder(self, foldername=None):

        if self.classifier is None:
869
            raise IException("Classifier not found! Select from the menu the option Training>Choose Classifier!")
870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964

        if foldername is None:
            foldername = self.tk.utils.ask_directory()

        valid_images_extension = ['.jpg', '.png', '.gif', '.jpeg', '.tif']

        fileimages = [name for name in os.listdir(foldername)
                    if os.path.splitext(name)[-1].lower() in valid_images_extension]

        fileimages.sort()

        all_accuracy = []
        all_IoU = []
        all_frequency_weighted_IU = []

        for file in fileimages:
            path_file = os.path.join(foldername, file)
            self.open_image(path_file)
            self.run_classifier()
            label_image = os.path.join(foldername, (os.path.splitext(file)[-2] + '_json'), 'label.png')
            self._image_gt = File.open_image_lut(label_image)
            self._image_gt_name = File.get_filename(label_image)

            tam_gt = self._image_gt.shape
            tam_im = self._mask_image.shape
            if len(tam_gt) > 2:
                self.tk.write_log("Color image is not supported. You must open a gray-scale image")
                return

            if tam_gt[0] != tam_im[0] or tam_gt[1] != tam_im[1]:
                self.tk.write_log("Images with different sizes")
                return

            
            confusion_matrix = MetricUtils.confusion_matrix(self._mask_image, self._image_gt)
            [mean_accuracy, accuracy] = MetricUtils.mean_accuracy(self._mask_image, self._image_gt)
            [mean_IoU, IoU] = MetricUtils.mean_IU(self._mask_image, self.