first version feature: grafical confusion matrix

src/classification/cnn_keras.py

@@ -522,3 +522,9 @@ class CNNKeras(Classifier):
             class_mode="categorical")
 
         return train_generator, validation_generator, test_generator
+
+    def single_classify(self, image_path, directory, extractors, dict_classes):
+        from matplotlib.pylab im imread
+        image = imread(image_path)
+        predict = self.model.predict([image])[0]
+        return dict_classes[predict]
\ No newline at end of file

src/classification/weka_classifiers.py

@@ -269,3 +269,18 @@ class WekaClassifiers(Classifier):
         """
         self.data = None
         self.classifier = None
+
+    def single_classify(self, image_path, directory, extractors, dict_classes):
+        '''
+        '''
+        from extraction import FeatureExtractor
+        from os import remove
+        test_file = 'temp'
+        fextractor=FeatureExtractor(extractors)
+        fextractor.extract_one_file(directory, image_path, output_file = test_file)
+        
+        predicted = self.classify(directory, test_dir='.tmp', test_data=test_file+'.arff', image=None)
+
+        remove(directory+'/'+test_file+'.arff')
+        return predicted[0]
+    
\ No newline at end of file

src/main.py

@@ -89,7 +89,8 @@ if __name__ == "__main__":
     tk.add_command("Load h5 weight (only for CNNs)", act.open_weight)
     tk.add_command("Execute", act.run_classifier, 'C')
     tk.add_command("Execute folder", act.run_classifier_folder)
-
+    tk.add_command("Execute Graphical Confusion Matrix", act.run_grafic_confusion_matrix)
+    
     tk.add_menu("Experimenter")
     tk.add_check_button("Ground Truth", act.toggle_ground_truth, default_state = False)
     tk.add_separator()

src/pynovisao.py

@@ -45,6 +45,7 @@ class Act(object):
             Arguments of program.
         """
         self.tk = tk
+        self.has_trained = False
         
         self.segmenter = [segmentation._segmenter_list[segmenter].meta for segmenter in segmentation._segmenter_list
                             if segmentation._segmenter_list[segmenter].value == True ][0]()
@@ -329,6 +330,7 @@ class Act(object):
             self.tk.refresh_panel_classes(self.classes)
             
             if self.classifier: self.classifier.reset()
+        self.has_trained=False
             
     def toggle_dataset_generator(self):
         """Enable/disable the dataset generator on click in image.
@@ -628,6 +630,7 @@ class Act(object):
             self.tk.append_log("DONE (%0.3f seconds)",  (TimeUtils.get_time() - start_time))
         
         self._image = self._const_image
+        self.has_trained=True
 
     
     def _show_ground_truth(self, list_segments, len_segments, labels, start_time):
@@ -941,3 +944,78 @@ class Act(object):
         np.savetxt(f, all_frequency_weighted_IU, fmt='%.5f')
         f.close()
 
+    def run_grafic_confusion_matrix(self):
+        '''
+
+        '''
+        
+        if not self.has_trained:
+            message='Dataset Must Be Trained.'
+            IException(message)
+        
+        from os.path import abspath
+
+        directory = self.tk.utils.ask_directory()
+        if not directory:
+            message = 'No directory selected.'
+            IException(message)
+            return
+        directory = abspath(directory)
+        dataset = abspath(self.dataset)
+        if directory == self.dataset:
+            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
+        
+        from shutil import rmtree
+        from os import mkdir, listdir
+        from os.path import isdir
+        from os import symlink
+        
+        def create_folder_struct(matrix_path, class_names, human, computer):
+            try:
+                rmtree(matrix_path)
+            except Exception as e:
+                print str(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)
+
+        index=directory[-2::-1].index('/')
+        matrix_path=directory[:-(index+1)]+'folder_confusion_matrix'
+        class_names, classes=listdir(directory), {}
+        
+        for i in range(len(class_names)-1,-1,-1):
+            if isdir(dataset+'/'+class_names[i]):
+                if class_names[i][0] is not '.':
+                    continue
+            del class_names[i]
+        for i, name in enumerate(class_names):
+            classes[name], classes[i]=i, name
+        images=[]
+        
+        for classe in class_names:
+            image_names=listdir(directory+'/'+classe)
+            for i in range(len(image_names)):
+                image_names[i]=directory+'/',classe ,'/'+image_names[i]
+            images.extend(image_names)
+        
+        human, computer = '/human_', '/computer_'
+        create_folder_struct(matrix_path, class_names, human, computer)
+        
+        for image_path in images:
+            original=reduce(lambda a,b:a+b, image_path)
+            real_class_path=matrix_path+human+image_path[1]
+            predicted=self.classifier.single_classify(original, directory, self.extractors, classes)
+            predicted_class_path = real_class_path+computer+predicted
+            name_predicted=predicted_class_path+image_path[2]
+            symlink(original, name_predicted)
+        
+        message = 'Graphical Confusion Matrix saved in '+matrix_path
+        self.tk.append_log(message)