Merge branch 'master' of http://git.inovisao.ucdb.br/inovisao/pynovisao into feature/pseudo-label

.gitignore

 *.pyc
 data/*
+models_checkpoints/*
+venv/*
 !data/demo.jpg
 !data/pynovisao.png
 !data/demo/.gitignore

INSTALL.sh

@@ -17,16 +17,16 @@ fi
 echo "[PYNOVISAO INSTALLER] Updating apt-get..."
 sudo apt-get -qq update
 echo "[PYNOVISAO INSTALLER] Installing prerequisites..."
-sudo apt-get -qq -y install libfreetype6-dev tk tk-dev python-pip default-jre default-jdk weka weka-doc python-tk python-matplotlib python-opencv
-
+sudo apt-get -qq -y install libfreetype6-dev tk tk-dev python-pip openjdk-8-jre openjdk-8-jdk weka weka-doc python-tk python-matplotlib
+source ~/.bashrc
 
 echo "[PYNOVISAO INSTALLER] Upgrading pip..."
-pip install --upgrade pip  --quiet
+sudo pip install --upgrade pip  --quiet
 # Numpy must be installed before installing javabridge
 echo "[PYNOVISAO INSTALLER] Installing numpy..."
-pip install numpy --quiet
+sudo pip install numpy==1.14.5 --quiet
 echo "[PYNOVISAO INSTALLER] Installing libraries..."
-pip install -r requeriments.txt --quiet
+sudo pip install -r requeriments.txt --quiet
 
 printf "${YELLOW} \n======== WARNING ========\n"
 printf "The Keras is necessary so that it is possible to use CNN. It is recommended to install the version for GPU processing (if available) but it is also possible to use CPU processing.\n"

README.md

 # Título: Pynovisao
-## Autores (ordem alfabética): Adair da Silva Oliveira Junior, Alessandro dos Santos Ferreira, Diego André Sant'Ana(diegoandresantana@gmail.com),Everton Castelão Tetila(evertontetila@gmail.com), Gabriel Kirsten Menezes(gabriel.kirsten@hotmail.com), Hemerson Pistori (pistori@ucdb.br), Nícolas Alessandro de Souza Belete(nicolas.belete@gmail.com)
+## Autores (ordem alfabética): Adair da Silva Oliveira Junior, Alessandro dos Santos Ferreira, Diego André Sant'Ana(diegoandresantana@gmail.com), Diogo Nunes Gonçalves(dnunesgoncalves@gmail.com), Everton Castelão Tetila(evertontetila@gmail.com), Felipe Silveira(eng.fe.silveira@gmail.com), Gabriel Kirsten Menezes(gabriel.kirsten@hotmail.com), Gilberto Astolfi(gilbertoastolfi@gmail.com), Hemerson Pistori (pistori@ucdb.br), Nícolas Alessandro de Souza Belete(nicolas.belete@gmail.com)
 
 ## Resumo:
 

requeriments.txt

@@ -7,15 +7,16 @@ sympy
 nose
 networkx
 scikit-image
-javabridge  
+javabridge==1.0.18  
 python-weka-wrapper
 cycler==0.10
 cython
 h5py
 scikit-learn
-tensorflow-gpu
 statistics
 pandas_ml
 pyxdg
 opencv-contrib-python
 python-interface
+tqdm
+sklearn

src/extraction/feature_extraction.py

@@ -11,8 +11,8 @@
 import io
 import itertools
 import os
-import threading
-
+import multiprocessing 
+from multiprocessing import Process, Manager
 from interface.interface import InterfaceException as IException
 
 from util.file_utils import File
@@ -23,7 +23,9 @@ from extractor import Extractor
 from tqdm import tqdm
 import sys
 
-
+if not sys.warnoptions:
+    import warnings
+    warnings.simplefilter("ignore")
 class FeatureExtractor(object):
     """Handle the feature extraction."""
 
@@ -40,13 +42,11 @@ class FeatureExtractor(object):
         self.tkParent=tkParent
 
     def extract_all(self, dataset, output_file=None, dirs=None, overwrite=True):
-        self.labels = []
-        self.types = []
-
-        self.data = []
+  
+        self.data = Manager().list() #is a necessary because have a problem with use Process and normaly declaration
         self.threads = []
-        self.labels = []
-        self.types = []
+        self.labels = Manager().list()
+        self.types = Manager().list()
         """Runs the feature extraction algorithms on all images of dataset.
 
         Parameters
@@ -101,6 +101,7 @@ class FeatureExtractor(object):
         with tqdm(total=len(self.threads)) as pbar:
             for  t in self.threads:
                  t.start()
+                 pbar.update(1)
             pbar.close()
 
         self.print_console("Waiting for workers to finish extracting attributes from images!")
@@ -108,7 +109,6 @@ class FeatureExtractor(object):
             for t in self.threads:
                 t.join()
                 ppbar.update(1)
-
             ppbar.close()
         self.print_console("The process was completed with "+str(len(self.threads))+" images!")
         if len(self.data) == 0:
@@ -116,7 +116,7 @@ class FeatureExtractor(object):
 
         # Save the output file in ARFF format
         # self._save_output(File.get_filename(dataset), classes, self.labels, self.types, self.data, output_file)
-        self._save_output(File.get_filename(dataset), classes, self.labels, self.types, self.data, output_file)
+        self._save_output(File.get_filename(dataset), classes, self.labels[0], self.types[0], self.data, output_file)
         end_time = TimeUtils.get_time()
 
         return output_file, (end_time - start_time)
@@ -130,9 +130,8 @@ class FeatureExtractor(object):
         for  item in  items :
             if item.startswith('.'):
                 continue
-
-            th = threading.Thread(target=self.sub_job_extractor,args=(item, dataset, cl, classes))
-
+            #th = threading.Thread(target=self.sub_job_extractor,args=(item, dataset, cl, classes))
+            th = multiprocessing.Process(target=self.sub_job_extractor,args=(item, dataset, cl, classes))
             self.threads.append(th)
 
 
@@ -149,14 +148,17 @@ class FeatureExtractor(object):
         if len(self.data) > 0:
             values = list(
                 itertools.chain.from_iterable(zip(*([extractor().run(image) for extractor in self.extractors]))[2]))
+	    
             self.data.append(values + [cl if cl in classes else classes[0]])
+	    
         else:
-            self.labels, self.types, values = [list(itertools.chain.from_iterable(ret))
+            labs, tys, values = [list(itertools.chain.from_iterable(ret))
                                                for ret in
                                                zip(*(extractor().run(image) for extractor in self.extractors))]
+            self.labels.append(labs)
+            self.types.append(tys)
             self.data.append(values + [cl if cl in classes else classes[0]])
 
-
     def extract_one_file(self, dataset, image_path, output_file=None):
         """Runs the feature extraction algorithms on specific image.
 

src/extraction/hog.py

@@ -8,6 +8,11 @@
     
     Name: hog.py
     Author: Alessandro dos Santos Ferreira ( santosferreira.alessandro@gmail.com )
+	
+    Change parameter Visualise for Visualize because is deprecaded
+    Date:02/01/2019
+    Author: Diego Andre Sant Ana		 	
+		
 """
 from skimage import feature
 
@@ -36,13 +41,13 @@ class HOG(Extractor):
         features : tuple
             Returns a tuple containing a list of labels, type and values for each feature extracted.
         """
-        image_grayscale = ImageUtils.image_grayscale(image, bgr = True)
+        image_grayscale = ImageUtils.image_grayscale(image, bgr=True)
         image_128x128 = ImageUtils.image_resize(image_grayscale, 128, 128)
-        
+
         values, _ = feature.hog(image_128x128, orientations=8, pixels_per_cell=(32, 32),
-                    cells_per_block=(1, 1), visualise=True)
-                    
-        labels = [m+n for m,n in zip(['hog_'] * len(values),map(str,range(0,len(values))))]
+                                cells_per_block=(1, 1), visualise=True)
+
+        labels = [m + n for m, n in zip(['hog_'] * len(values), map(str, range(0, len(values))))]
         types = [Extractor.NUMERIC] * len(labels)
 
         return labels, types, list(values)

src/extraction/image_moments.py

@@ -16,7 +16,7 @@ import cv2
 from util.utils import ImageUtils
 from skimage.measure import regionprops, moments, moments_central
 from skimage.morphology import label
-
+import numpy as np
 from extractor import Extractor
 
 class RawCentralMoments(Extractor):
@@ -53,8 +53,8 @@ class RawCentralMoments(Extractor):
         
         row = m[0, 1] / m[0, 0]
         col = m[1, 0] / m[0, 0]
-
-        mu = measure.moments_central(image_binary, row, col)
+	
+        mu = measure.moments_central(image_binary, center=(row, col), order=3)
         
         values_mu = [mu[p, q] for (p, q) in self._moments_order]
         labels_mu = [M+str(p)+str(q) for M,(p,q) in zip(['Mu_'] * len(self._moments_order), self._moments_order)]
@@ -104,8 +104,9 @@ class HuMoments(Extractor):
         image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
 
         values_hu= cv2.HuMoments(cv2.moments(image)).flatten()
+        values_hu = list(values_hu)
 
-
+        values_hu= np.nan_to_num(values_hu)
         labels_hu = [m+n for m,n in zip(['Hu_'] * len(values_hu),map(str,range(0,len(values_hu))))]
         
         labels = labels_hu

src/pynovisao.py

@@ -5,7 +5,7 @@
     Name: pynovisao.py
     Author: Alessandro dos Santos Ferreira ( santosferreira.alessandro@gmail.com )
 """
-
+import gc
 from collections import OrderedDict
 import numpy as np
 import os
@@ -30,8 +30,10 @@ from util.file_utils import File
 from util.utils import TimeUtils
 from util.utils import MetricUtils
 from util.x11_colors import X11Colors
-
-
+import multiprocessing
+from multiprocessing import Process, Manager
+import  threading
+from tqdm import tqdm
 class Act(object):
     """Store all actions of Pynovisao."""
 
@@ -199,7 +201,7 @@ class Act(object):
             If there's no image opened.
         """
         if self._const_image is None:
-            raise IException("Image not found")
+            raise IException("Image not found!  Open an image to test, select in the menu the option File>Open Image!")
         
         if self.tk.close_image():
             self.tk.write_log("Closing image...")
@@ -386,7 +388,7 @@ class Act(object):
             If there's no image opened.
         """
         if self._const_image is None:
-            raise IException("Image not found")
+            raise IException("Image not found!  Open an image to test, select in the menu the option File>Open Image!")
         
         self.tk.write_log("Running %s...", self.segmenter.get_name())
 
@@ -421,7 +423,7 @@ class Act(object):
                                 if new_config[extractor].value == True ]
             
             if len(self.extractors) == 0:
-                raise IException("Please select at least one extractor")
+                raise IException("Please select an extractor from the menu under Features Extraction> Select extractors! ")
             
             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")
@@ -459,7 +461,7 @@ class Act(object):
             The user must install the required dependencies to classifiers.
         """
         if self.classifier is None:
-            raise IException("Classifier not found!")
+            raise IException("Classifier not found! Select from the menu the option Training>Choose Classifier!")
         
         title = "Choosing a classifier"
         self.tk.write_log(title)
@@ -488,7 +490,7 @@ class Act(object):
             The user must install the required dependencies to classifiers.
         """
         if self.classifier is None:
-            raise IException("Classifier not found!")
+            raise IException("Classifier not found! Select from the menu the option Training>Choose Classifier!")
         
         title = "Configuring %s" % self.classifier.get_name()
         self.tk.write_log(title)
@@ -509,7 +511,7 @@ class Act(object):
     def run_classifier(self):
         """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'
@@ -518,48 +520,53 @@ class Act(object):
             If there's no image opened.
         """
         if self.classifier is None:
-            raise IException("Classifier not found!")
-        
+            raise IException("Classifier not found! Select from the menu the option Training>Choose Classifier!")
+
         if self._const_image is None:
-            raise IException("Image not found")
-        
+            raise IException("Image not found!  Open an image to test, select in the menu the option File>Open Image!")
+
         self.tk.write_log("Running %s...", self.classifier.get_name())
         self.tk.append_log("\n%s", str(self.classifier.get_summary_config()))
-        
+
         #self.classifier.set
-        
+
         start_time = TimeUtils.get_time()
 
         # Perform a segmentation, if needed.
         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)        
+            self.tk.refresh_image(self._image)
             list_segments = self.segmenter.get_list_segments()
             self._gt_segments = [None]*(max(list_segments)+1)
-        
+
         #  New and optimized classification
         tmp = ".tmp"
         File.remove_dir(File.make_path(self.dataset, tmp))
 
         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]
-            
-            # 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
-            
+
+        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()
+
+        gc.collect()
         # Perform the feature extraction of all segments in image ( not applied to ConvNets ).
         if self.classifier.must_extract_features():
-            self.tk.append_log("Running extractors on test images... (%0.3f seconds)", (TimeUtils.get_time() - start_time))    
-            fextractor = FeatureExtractor(self.extractors)        
+            self.tk.append_log("Running extractors on test images... (%0.3f seconds)", (TimeUtils.get_time() - start_time))
+            fextractor = FeatureExtractor(self.extractors)
             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))
 
         # Get the label corresponding to predict class for each segment of image.
@@ -569,17 +576,17 @@ class Act(object):
         # 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)
 
             # 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
@@ -591,7 +598,7 @@ class Act(object):
                     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)
 
@@ -610,18 +617,18 @@ class Act(object):
             self._image = cv2.addWeighted(self._const_image, 0.7, self.class_color, 0.3, 0)
             self.tk.refresh_image(self._image)
 
-        
+
         end_time = TimeUtils.get_time()
-            
+
         self.tk.append_log("\nClassification finished")
         self.tk.append_log("Time elapsed: %0.3f seconds", (end_time - start_time))
 
     def run_training(self):
         start_time = TimeUtils.get_time()
         
-  # Training do not need an image opened (consider removing these two lines)
-  #      if self._const_image is None:
-  #          raise IException("Image not found")
+        # Training do not need an image opened (consider removing these two lines)
+        #      if self._const_image is None:
+        #          raise IException("Image not found")
         
         if self.classifier.must_train():
             
@@ -701,7 +708,7 @@ class Act(object):
             The user must install the required dependencies to classifiers.
         """
         if self.classifier is None:
-            raise IException("Classifier not found!")
+            raise IException("Classifier not found! Select from the menu the option Training>Choose Classifier!")
         
         if self.classifier.must_train():
             self.tk.write_log("Creating training data...")
@@ -726,12 +733,12 @@ class Act(object):
             The user must install the required dependencies to classifiers.
         """
         if self.classifier is None:
-            raise IException("Classifier not found!")
+            raise IException("Classifier not found! Select from the menu the option Training>Choose Classifier!")
         
         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")
@@ -744,7 +751,7 @@ class Act(object):
 
 
     def about(self):
-        self.tk.show_info("Pynovisao\n\nVersion 1.0.0\n\nAuthors:\nAlessandro Ferreira\nHemerson Pistori")
+        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")
         
             
     def func_not_available(self):
@@ -855,7 +862,7 @@ class Act(object):
     def run_classifier_folder(self, foldername=None):
 
         if self.classifier is None:
-            raise IException("Classifier not found!")
+            raise IException("Classifier not found! Select from the menu the option Training>Choose Classifier!")
 
         if foldername is None:
             foldername = self.tk.utils.ask_directory()
@@ -951,6 +958,7 @@ class Act(object):
         np.savetxt(f, all_frequency_weighted_IU, fmt='%.5f')
         f.close()
 
+
     def run_grafic_confusion_matrix(self):
         '''
         Generate a a graphical confusion matrix where images are classified and according to classification go to the wrong or right folder.
@@ -1036,15 +1044,21 @@ class Act(object):
         self.tk.write_log(header_output_middle + 'Initializing...')
         
         total = str(len(images))
+        # internal function in method for create threads, cannot change for Process(Have a problem with JVM Instances)
+        total = str(len(images))
+        print("Waiting  finish classification!")
         for i, image_path in enumerate(images):
-            original_name=reduce(lambda a,b:a+b, image_path)
-            real_class_path=matrix_path+human+image_path[1]
-            predicted=self.classifier.single_classify(original_name, folder, self.extractors, classes)
+            original_name = reduce(lambda a, b: a + b, image_path)
+            real_class_path = matrix_path + human + image_path[1]
+            predicted = self.classifier.single_classify(original_name, folder, self.extractors, classes)
             message = header_output_middle + str(i + 1) + ' of ' + total + ' images classifield.'
             self.tk.write_log(message)
-            predicted_class_path = real_class_path+computer+predicted
-            predicted_name=predicted_class_path+image_path[2]
+            predicted_class_path = real_class_path + computer + predicted
+            predicted_name = predicted_class_path + image_path[2]
             symlink(original_name, predicted_name)
-        
+                
+
+
         message = header_output + 'Saved in ' + matrix_path
         self.tk.write_log(message)
+

src/util/split_convertall.sh

+#!/bin/bash
+
+#
+#    Script - convert tif to png
+#
+#    Name: script_convertall.sh
+#    Author: Gabriel Kirsten Menezes (gabriel.kirsten@hotmail.com)
+#
+
+echo "[SCRIPT CONVERT ALL] Initializing..."
+
+dir_train="../../data/demo_split/train"
+dir_validation="../../data/demo_split/validation"
+
+echo "[SCRIPT CONVERT ALL] Converting train..."
+
+for dir_class in `ls $dir_train`;
+do
+    echo "[SCRIPT CONVERT ALL] Converting class -" $dir_class;
+    convert $dir_train/$dir_class/* $dir_train/$dir_class/$dir_class.png
+    echo "[SCRIPT CONVERT ALL] Removing all .tif files in $dir_class ..."
+    rm $dir_train/$dir_class/*.tif
+done
+
+echo "[SCRIPT CONVERT ALL] Converting validation..."
+
+for dir_class in `ls $dir_validation`;
+do
+    echo "[SCRIPT CONVERT ALL] Converting class -" $dir_class;
+    convert $dir_validation/$dir_class/* $dir_validation/$dir_class/$dir_class.png
+    echo "[SCRIPT CONVERT ALL] Removing all .tif files in $dir_class ..."
+    rm $dir_validation/$dir_class/*.tif
+done
+
+echo "[SCRIPT CONVERT ALL] OK! DONE."