pynovisao.py 41.4 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 9
"""

from collections import OrderedDict
10
import numpy as np
11
import os
12
import interface
13 14
import types
import cv2
15
from interface.interface import InterfaceException as IException
16
from PIL import Image
17

18
import segmentation
19
import extraction
20
from extraction import FeatureExtractor
21
import classification
22
from classification import Classifier
23

24 25
import util
from util.config import Config
26
from util.file_utils import File
27
from util.utils import TimeUtils
28 29
from util.utils import MetricUtils
from util.x11_colors import X11Colors
30

Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
31

32
class Act(object):
33
    """Store all actions of Pynovisao."""
34

Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
35
    def __init__(self, tk, args):
36 37 38 39 40 41 42 43 44
        """Constructor.

        Parameters
        ----------
        tk : Interface
            Pointer to interface that handles UI.
        args : Dictionary
            Arguments of program.
        """
45
        self.tk = tk
46
        self.has_trained = False
47 48 49
        
        self.segmenter = [segmentation._segmenter_list[segmenter].meta for segmenter in segmentation._segmenter_list
                            if segmentation._segmenter_list[segmenter].value == True ][0]()
50 51 52
        
        self.extractors = [extraction._extractor_list[extractor].meta for extractor in extraction._extractor_list
                            if extraction._extractor_list[extractor].value == True ]
53 54 55 56 57 58
        
        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
59

60 61
        self._image = None
        self._const_image = None
62
        self._mask_image = None
63
        self._image_name = None
64
        self._image_path = None
65
                    
66 67
        self._init_dataset(args["dataset"])
        self._init_classes(args["classes"], args["colors"])
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
68

69
        self._dataset_generator = True
70 71
        self._ground_truth = False
        self._gt_segments = None
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
72
        self.weight_path = None
73

74
    
75
    def _init_dataset(self, directory):
76 77 78 79 80 81 82
        """Initialize the directory of image dataset.

        Parameters
        ----------
        directory : string
            Path to directory.
        """
83 84 85 86
        if(directory[-1] == '/'):
            directory = directory[:-1]
            
        self.dataset = directory
87
        File.create_dir(self.dataset)
88
    
89
    def _init_classes(self, classes = None, colors = None):
90 91 92 93 94 95 96 97 98 99
        """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.
        """
100
        self.classes = []
101 102 103 104 105 106 107 108 109 110 111 112 113 114

        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()
115 116 117 118 119 120 121

        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')
122
                
123
        self._current_class = 0
124
        
125

126
    def open_image(self, imagename = None):
127 128 129 130 131 132 133
        """Open a new image.

        Parameters
        ----------
        imagename : string, optional, default = None
            Filepath of image. If not informed open a dialog to choose.
        """
134 135
        
        def onclick(event):
136
            """Binds dataset generator event to click on image."""
137
            if event.xdata != None and event.ydata != None and int(event.ydata) != 0 and self._dataset_generator == True:
138 139
                x = int(event.xdata)
                y = int(event.ydata)
140 141 142 143 144 145 146
                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)
                    
147
                    self._image, run_time = self.segmenter.paint_segment(self._image, self.classes[self._current_class]["color"].value, x, y)
148
                    self.tk.append_log("Painting segment: %0.3f seconds", run_time)
149
                    self.tk.refresh_image(self._image)
150
                    
151 152 153 154
                    if self._ground_truth == True:
                        self._gt_segments[idx_segment] = self.classes[self._current_class]["name"].value

                    elif self._dataset_generator == True:
155
                        filepath = File.save_class_image(segment, self.dataset, self.classes[self._current_class]["name"].value, self._image_name, idx_segment)
156 157
                        if filepath:
                            self.tk.append_log("\nSegment saved in %s", filepath)
158 159 160
        
        if imagename is None:
            imagename = self.tk.utils.ask_image_name()
161 162

        if imagename:
163 164
            self._image = File.open_image(imagename)
            self._image_name = File.get_filename(imagename)
165

166 167 168
            self.tk.write_log("Opening %s...", self._image_name)
            self.tk.add_image(self._image, self._image_name, onclick)
            self._const_image = self._image
169
            
170
            self.segmenter.reset()
171
            self._gt_segments = None
172

173
        
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
174 175 176 177

    def open_weight(self):
        """Open a new weight."""
        self.weight_path = self.tk.utils.ask_weight_name()
178
        self.classifier.weight_path = self.weight_path
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
179
        
180
    def restore_image(self):
181 182
        """Refresh the image and clean the segmentation.
        """
183 184 185 186
        if self._const_image is not None:
            self.tk.write_log("Restoring image...")
            self.tk.refresh_image(self._const_image)
            
187
            self.segmenter.reset()
188
            self._gt_segments = None
189 190
        
    def close_image(self):
191
        """Close the image.
192
        
193 194 195 196 197
        Raises
        ------
        IException 'Image not found'
            If there's no image opened.
        """
198
        if self._const_image is None:
199 200 201 202
            raise IException("Image not found")
        
        if self.tk.close_image():
            self.tk.write_log("Closing image...")
203
            self._const_image = None
204
            self._image = None
205
            self._image_path = None
206 207

    def add_class(self, dialog = True, name = None, color = None):
208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224
        """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.
        """
225 226 227
        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)
228
                
229
        def edit_class(index):
230
            """Calls method that edit the class."""
231
            self.edit_class(index)
232 233
            
        def update_current_class(index):
234
            """Calls method that update the class."""
235
            self.update_current_class(index)
236 237
        
        def process_config():
238
            """Add the class and refresh the panel of classes."""
239
            new_class = self.tk.get_config_and_destroy()
240
            new_class["name"].value = '_'.join(new_class["name"].value.split())
241 242 243

            self.classes.append( new_class )
            self.tk.write_log("New class: %s", new_class["name"].value)
244
            self.tk.refresh_panel_classes(self.classes, self._current_class)
245
            
246 247
        if name is None:
            name = "Class_%02d" % (n_classes+1)
248
        if color is None:
249
            color = util.X11Colors.random_color()
250 251
            
        class_config = OrderedDict()
252
        class_config["name"] = Config(label="Name", value=name, c_type=str)
253
        class_config["color"] = Config(label="Color (X11 Colors)", value=color, c_type='color')
254 255
        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)
256 257 258 259 260 261 262
        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"
263 264 265
        self.tk.dialogue_config(title, class_config, process_config)        
      

266
    def edit_class(self, index):
267 268 269 270 271 272 273
        """Edit a class.

        Parameters
        ----------
        index : integer.
            Index of class in list self.classes.
        """
274
        def process_update(index):
275
            """Update the class."""
276
            updated_class = self.tk.get_config_and_destroy()
277
            updated_class["name"].value = '_'.join(updated_class["name"].value.split())
278 279 280
            
            self.classes[index] = updated_class
            self.tk.write_log("Class updated: %s", updated_class["name"].value)
281
            self.tk.refresh_panel_classes(self.classes, self._current_class)
282 283 284 285 286 287
        
        current_config = self.classes[index]
            
        title = "Edit class %s" % current_config["name"].value
        self.tk.dialogue_config(title, current_config, lambda *_ : process_update(index))
            
288
    def update_current_class(self, index):
289 290
        """Update the current class.
        """
291
        self._current_class = index
292 293
        
    def get_class_by_name(self, name):
294 295 296 297
        """Return the index for class.
        
        Parameters
        ----------
298
        name : string
299 300 301 302
            Name of class.
            
        Returns
        -------
303
        index : integer
304 305 306 307 308 309 310
            Index of class in list self.classes.

        Raises
        ------
        Exception 'Class not found'
            If name not found in self.classes.
        """
311 312 313 314 315 316
        name = name.strip()
        
        for cl in self.classes:
            if cl["name"].value == name:
                return cl
        raise Exception("Class not found")
317

318
        
319
    def set_dataset_path(self):
320 321
        """Open a dialog to choose the path to directory of image dataset.
        """
322 323
        directory = self.tk.utils.ask_directory(default_dir = self.dataset)
        if directory:
324
            self._init_dataset(directory)
325 326
            self.tk.write_log("Image dataset defined: %s", self.dataset)
            
327
            self._init_classes()
328
            self.tk.refresh_panel_classes(self.classes)
329
            
330
            if self.classifier: self.classifier.reset()
331
        self.has_trained=False
332
            
333
    def toggle_dataset_generator(self):
334 335
        """Enable/disable the dataset generator on click in image.
        """
336
        self._dataset_generator = not self._dataset_generator
337

338 339
            
    def select_segmenter(self):
340 341
        """Open a dialog to choose the segmenter.
        """
342 343
        title = "Choosing a segmenter"
        self.tk.write_log(title)
344

345
        current_config = segmentation.get_segmenter_config()
346
        
347
        def process_config():
348
            """Update the current segmenter."""
349
            new_config = self.tk.get_config_and_destroy()
350

351 352 353
            self.segmenter = [new_config[segmenter].meta for segmenter in new_config
                                if new_config[segmenter].value == True ][0]()

354
            self.tk.append_log("\nSegmenter: %s\n%s", str(self.segmenter.get_name()), str(self.segmenter.get_summary_config()))
355 356 357 358 359
            segmentation.set_segmenter_config(new_config)

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

    def config_segmenter(self):
360 361
        """Open a dialog to configure the current segmenter.
        """
362 363 364 365 366 367
        title = "Configuring %s" % self.segmenter.get_name()
        self.tk.write_log(title)

        current_config = self.segmenter.get_config()
        
        def process_config():
368
            """Update the configs of current segmenter."""
369 370 371
            new_config = self.tk.get_config_and_destroy()

            self.segmenter.set_config(new_config)
372
            self.tk.append_log("\nConfig updated:\n%s", str(self.segmenter.get_summary_config()))
373
            self.segmenter.reset()
374 375

        self.tk.dialogue_config(title, current_config, process_config)
376
        
377
    def run_segmenter(self, refresh_image=True):
378
        """Do the segmentation of image, using the current segmenter.
379
        
380 381 382 383 384
        Raises
        ------
        IException 'Image not found'
            If there's no image opened.
        """
385 386 387
        if self._const_image is None:
            raise IException("Image not found")
        
388
        self.tk.write_log("Running %s...", self.segmenter.get_name())
389 390 391 392 393

        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)
        
394 395
        self._gt_segments = [None]*(max(self.segmenter.get_list_segments())+1)
        
396 397
        if refresh_image:
            self.tk.refresh_image(self._image)
398 399


400
    def select_extractors(self):
401
        """Open a dialog to select the collection of extractors.
402
        
403 404 405 406 407
        Raises
        ------
        IException 'Please select at least one extractor'
            If no extractor was selected.
        """
408 409 410 411 412 413
        title = "Selecting extractors"
        self.tk.write_log(title)

        current_config = extraction.get_extractor_config()
        
        def process_config():
414
            """Update the collection of extractors."""
415 416 417 418
            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 ]
419
            
420 421
            if len(self.extractors) == 0:
                raise IException("Please select at least one extractor")
422
            
423 424 425 426 427 428
            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)
429 430
        
    def run_extractors(self):
431 432
        """Perform a feature extraction on all images of dataset, using the current collection of extractors.
        """
433
        self.tk.write_log("Running extractors on all images in %s", self.dataset)
434

435 436 437
        fextractor = FeatureExtractor(self.extractors)
        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 ]))
438
        
439
        output_file, run_time = fextractor.extract_all(self.dataset, "training")
440 441
        self.tk.append_log("\nOutput file saved in %s", output_file)
        self.tk.append_log("Time elapsed: %0.3f seconds", run_time)
442 443
        
        if self.classifier: self.classifier.reset()
444

445 446
        
    def select_classifier(self):
447 448 449 450 451 452 453
        """Open a dialog to select the classifier.
        
        Raises
        ------
        IException 'You must install python-weka-wrapper'
            The user must install the required dependencies to classifiers.
        """
454
        if self.classifier is None:
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
455
            raise IException("Classifier not found!")
456 457 458 459 460
        
        title = "Choosing a classifier"
        self.tk.write_log(title)

        current_config = classification.get_classifier_config()
461

462 463
        
        def process_config():
464
            """Update the current classifier."""
465
            new_config = self.tk.get_config_and_destroy()
Geazy Menezes's avatar
Geazy Menezes committed
466
            
467 468 469 470 471 472 473 474 475
            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):
476 477 478 479 480 481 482
        """Set the configuration of current classifier.
        
        Raises
        ------
        IException 'You must install python-weka-wrapper'
            The user must install the required dependencies to classifiers.
        """
483
        if self.classifier is None:
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
484
            raise IException("Classifier not found!")
485 486 487 488 489 490 491 492 493 494 495
        
        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()))
496 497
            
            if self.classifier: self.classifier.reset()
498 499 500 501 502

        self.tk.dialogue_config(title, current_config, process_config)
    
    
    def run_classifier(self):
503 504 505 506 507 508 509 510 511 512
        """Run the classifier on the current image.
        As result, paint the image with color corresponding to predicted class of all segment.
        
        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.
        """
513
        if self.classifier is None:
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
514
            raise IException("Classifier not found!")
515 516 517 518 519 520 521
        
        if self._const_image is None:
            raise IException("Image not found")
        
        self.tk.write_log("Running %s...", self.classifier.get_name())
        self.tk.append_log("\n%s", str(self.classifier.get_summary_config()))
        
522 523
        #self.classifier.set
        
524 525
        start_time = TimeUtils.get_time()

526
        # Perform a segmentation, if needed.
527 528 529 530 531 532 533
        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))
            
            self._image, _ = self.segmenter.run(self._const_image)
            self.tk.refresh_image(self._image)        
            list_segments = self.segmenter.get_list_segments()
534
            self._gt_segments = [None]*(max(list_segments)+1)
535 536
        
        #  New and optimized classification
537
        tmp = ".tmp"
538
        File.remove_dir(File.make_path(self.dataset, tmp))
539

540 541 542 543 544
        self.tk.append_log("Generating test images... (%0.3f seconds)", (TimeUtils.get_time() - start_time))
        
        len_segments = {}
        for idx_segment in list_segments:
            segment, size_segment, idx_segment = self.segmenter.get_segment(self, idx_segment=idx_segment)[:-1]
545
            
546
            filepath = File.save_class_image(segment, self.dataset, tmp, self._image_name, idx_segment)
547
            len_segments[idx_segment] = size_segment
548
            
549
        # Perform the feature extraction of all segments in image ( not applied to ConvNets ).
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
550
        if self.classifier.must_extract_features():
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
551 552
            self.tk.append_log("Running extractors on test images... (%0.3f seconds)", (TimeUtils.get_time() - start_time))    
            fextractor = FeatureExtractor(self.extractors)        
553 554 555
            output_file, _ = fextractor.extract_all(self.dataset, "test", dirs=[tmp])
                
        self.tk.append_log("Running classifier on test data... (%0.3f seconds)", (TimeUtils.get_time() - start_time))
556 557

        # Get the label corresponding to predict class for each segment of image.
558 559
        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))
560

561 562 563 564 565 566 567
        # 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))
            
            # If ground truth mode, show alternative results
            if self._ground_truth == True:
                return self._show_ground_truth(list_segments, len_segments, labels, start_time)
568

569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603
            # Create a popup with results of classification.
            popup_info = "%s\n" % str(self.classifier.get_summary_config())
            
            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)
            
            # 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):
                idx_segment = [ list_segments[idx] for idx in range(0, len(labels)) if cl["name"].value == labels[idx]]
                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)
                  
                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)
604 605

        
606 607 608 609
        end_time = TimeUtils.get_time()
            
        self.tk.append_log("\nClassification finished")
        self.tk.append_log("Time elapsed: %0.3f seconds", (end_time - start_time))
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
610 611 612

    def run_training(self):
        start_time = TimeUtils.get_time()
613
        
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
614 615 616 617 618 619 620 621 622 623 624 625
        if self._const_image is None:
            raise IException("Image not found")
        
        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
626
            self.classifier.train(self.dataset, "training")
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
627 628 629 630

            self.tk.append_log("DONE (%0.3f seconds)",  (TimeUtils.get_time() - start_time))
        
        self._image = self._const_image
631
        self.has_trained=True
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
632

633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673
    
    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)
674

675 676 677 678 679
        end_time = TimeUtils.get_time()
            
        self.tk.append_log("\nClassification finished")
        self.tk.append_log("Time elapsed: %0.3f seconds", (end_time - start_time))
        
680

681 682 683 684 685
    def toggle_ground_truth(self):
        """Enable/disable ground truth mode.
        """
        self._ground_truth = not self._ground_truth
        
686
    def cross_validation(self):
687 688 689 690 691 692 693
        """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.
        """
694
        if self.classifier is None:
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
695
            raise IException("Classifier not found!")
696 697 698 699 700 701 702 703 704 705 706 707 708 709
        
        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)
710 711
        
    def experimenter_all(self):
712 713 714 715 716 717 718
        """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.
        """
719
        if self.classifier is None:
Gabriel Kirsten's avatar
 
Gabriel Kirsten committed
720
            raise IException("Classifier not found!")
721 722 723 724 725 726 727 728 729 730 731 732 733 734
        
        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...")
                
                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)
735 736


737 738 739 740
    def about(self):
        self.tk.show_info("Pynovisao\n\nVersion 1.0.0\n\nAuthors:\nAlessandro Ferreira\nHemerson Pistori")
        
            
741
    def func_not_available(self):
742
        """Use this method to bind menu options not available."""
743
        self.tk.write_log("This functionality is not available right now.")
744

745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944
    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:
            raise IException("Classifier not found!")

        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._image_gt)
            frequency_weighted_IU = MetricUtils.frequency_weighted_IU(self._mask_image, self._image_gt)

            print('Matriz de Confusao')
            print(confusion_matrix)

            print('Mean Pixel Accuracy')
            print(mean_accuracy)

            print('Pixel accuracy per class')
            print(accuracy)

            print('Mean Intersction over Union')
            print(mean_IoU)

            print('Intersction over Union per class')
            print(IoU)

            print('Frequency Weighted IU')
            print(frequency_weighted_IU)

            all_accuracy.append(accuracy)
            all_IoU.append(IoU)
            all_frequency_weighted_IU.append(frequency_weighted_IU)

            if not os.path.exists("../models_results/"):
                os.makedirs("../models_results/")
            
            path = File.make_path("../models_results/" + file + ".txt")
            path_img = File.make_path("../models_results/" + file + "_seg1.tif")
            path_img2 = File.make_path("../models_results/" + file + "_seg2.tif")

            img = Image.fromarray(self._image)
            img.save(path_img)
            img = Image.fromarray(self.class_color)
            img.save(path_img2)
            
            f=open(path,'ab')
            np.savetxt(f, ['Matriz de confusao'], fmt='%s')
            np.savetxt(f, confusion_matrix, fmt='%.5f')
            np.savetxt(f, ['\nAcuracia'], fmt='%s')
            np.savetxt(f, accuracy, fmt='%.5f')
            np.savetxt(f, ['\nInterseccao sobre uniao'], fmt='%s')
            np.savetxt(f, IoU, fmt='%.5f')
            np.savetxt(f, ['\nInterseccao sobre uniao com peso'], fmt='%s')
            np.savetxt(f, [frequency_weighted_IU], fmt='%.5f')
            f.close()


        path = File.make_path("../models_results/all_metrics.txt")
        f=open(path,'ab')
        np.savetxt(f, ['All Acuracia'], fmt='%s')
        np.savetxt(f, all_accuracy, fmt='%.5f')
        np.savetxt(f, ['\nAll IoU'], fmt='%s')
        np.savetxt(f, all_IoU, fmt='%.5f')
        np.savetxt(f, ['\nAll Frequency Weighted IU'], fmt='%s')
        np.savetxt(f, all_frequency_weighted_IU, fmt='%.5f')
        f.close()

945 946
    def run_grafic_confusion_matrix(self):
        '''
Geazy Menezes's avatar
Geazy Menezes committed
947
        Generate a a graphical confusion matrix where images are classified and according to classification go to the wrong or right folder.
948
        Just Available to WekaClassifier and CNNKeras.
949
        '''
950 951 952 953 954 955 956
        from classification import WekaClassifiers, CNNKeras
        
        is_weka = isinstance(self.classifier, WekaClassifiers)
        is_keras = isinstance(self.classifier, CNNKeras)
        if not (is_weka or is_keras):
            message='Only available to Weka and CNN Keras classifiers.'
            raise IException(message)
Geazy Menezes's avatar
Geazy Menezes committed
957

958 959 960
        
        if not self.has_trained:
            message='Dataset Must Be Trained.'
961
            raise IException(message)
962
        
963
        from os.path import abspath, isdir
964

965 966 967 968
        folder = self.tk.utils.ask_directory()
        if not folder:
            message = 'No selected directory.'
            raise IException(message)
969
            return
970 971
            
        folder = abspath(folder)
972
        dataset = abspath(self.dataset)
973
        if folder == self.dataset:
974 975 976 977 978
            title = 'Same Dataset'
            message = 'The dataset selected is the same of the trained. Are you sure that is right?'
            option=self.tk.ask_ok_cancel(title, message)
            if not option:
                return
979 980 981 982 983 984 985 986
                
        from os import listdir, mkdir
        listdirs=listdir(folder)
        size_dirs = reduce(lambda a,b: a+b, [0]+[len(listdir(folder+'/'+d)) for d in listdirs if isdir(folder+'/'+d)])
        if not size_dirs:
            message = 'Dataset has no content or the subfolder has no content.'
            raise IException(message)
            
987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001
        from shutil import rmtree
        from os import symlink
        
        def create_folder_struct(matrix_path, class_names, human, computer):
            try:
                rmtree(matrix_path)
            except Exception as e:
                pass
            mkdir(matrix_path, 0777)
            for class_ in class_names:
                real=matrix_path+human+class_+'/'
                mkdir(real, 0777)
                for _class in class_names:
                    mkdir(real+computer+_class, 0777)

1002 1003 1004 1005 1006

        header_output = 'Starting Graphical Confusion Matrix\n\n'
        index=folder[-2::-1].index('/')
        matrix_path=folder[:-(index+1)]+'folder_confusion_matrix'
        class_names, classes=listdir(folder), {}
1007 1008 1009
        
        for i in range(len(class_names)-1,-1,-1):
            if isdir(dataset+'/'+class_names[i]):
1010
                if class_names[i][0] != '.':
1011 1012 1013 1014 1015