fix classify with load saved model

examples/labels.txt

-FolhasLargas
-Solo
-Soja
-Gramineas
\ No newline at end of file
+arvore
+fundo

src/classification/cnn_keras.py

@@ -29,7 +29,7 @@ from keras import backend as K
 from numpy import resize, expand_dims
 from keras.preprocessing.image import load_img, img_to_array
         
-
+import glob
 from interface.interface import InterfaceException as IException
 from classification.classifier import Classifier
 
@@ -96,6 +96,7 @@ class CNNKeras(Classifier):
         self.model = None
 
         self.trained = False
+        self.labels_file = Config("LabelsFile", '../examples/labels.txt', str)
 
     def get_config(self):
         """Return configuration of classifier.
@@ -194,8 +195,9 @@ class CNNKeras(Classifier):
             List of predicted classes for each instance in test data in ordered way.
         """
 
-        predict_directory = File.make_path(dataset, test_dir)
-
+        predict_directory=File.make_path(dataset, test_dir)
+        CLASS_NAMES = np.loadtxt(self.labels_file.value, str)
+        # Create a Keras class
         # Create a Keras class
         if not os.path.exists(File.make_path(predict_directory, "png")):
             os.makedirs(File.make_path(predict_directory, "png"))
@@ -213,17 +215,9 @@ class CNNKeras(Classifier):
                     print(e)
             else:
                 print(File.make_path(predict_directory, file))
-                os.symlink(File.make_path(predict_directory, file),
-                           File.make_path(predict_directory, 'png', file))
-
-        classify_datagen = ImageDataGenerator()
-
-        classify_generator = classify_datagen.flow_from_directory(
-            File.make_path(predict_directory, 'png'),
-            target_size=(IMG_HEIGHT, IMG_WIDTH),
-            batch_size=1,
-            shuffle=False,
-            class_mode=None)
+                #os.symlink(File.make_path(predict_directory, file),File.make_path(predict_directory, 'png', file))
+               
+        print(CLASS_NAMES)
 
         try:
             # self.model.load_weights(
@@ -231,29 +225,47 @@ class CNNKeras(Classifier):
             K.clear_session()
             if self.weight_path is not None:
                 self.model = load_model(self.weight_path)
-                path_classes = self.weight_path.replace(
-                    "_model.h5", "_classes.npy")
+                #path_classes = self.weight_path.replace(                    "_model.h5", "_classes.npy")
                 print("Load Model H5:"+self.weight_path)
-                np_load_old = np.load
-		# modify the default parameters of np.load
-                np.load = lambda *a,**k: np_load_old(*a, allow_pickle=True, **k)
+                #np_load_old = np.load
+                #modify the default parameters of np.load
+                #np.load = lambda *a,**k: np_load_old(*a, allow_pickle=True, **k)
 
-                CLASS_NAMES = np.load(path_classes).item().keys()
+                #CLASS_NAMES = np.load(path_classes).item().keys()
         except Exception as e:
             raise IException("Can't load the model in " +
                              str(e))
 
-        output_classification = self.model.predict_generator(
-            classify_generator)
+        classify_datagen=ImageDataGenerator(rescale=1. / 255)
 
-        one_hot_output = np.argmax(output_classification, axis=1)
+        classify_generator=classify_datagen.flow_from_directory(
+            os.path.dirname(os.path.realpath(File.make_path(predict_directory, "png"))),
+            target_size=(IMG_HEIGHT, IMG_WIDTH),
+            batch_size=1,
+            shuffle=False,
+            class_mode="categorical")
+        print("Examples:")
+        print(classify_generator.samples)
+        output_classification=self.model.predict_generator(
+            classify_generator, classify_generator.samples, verbose=2)
 
-        one_hot_output = one_hot_output.tolist()
+        one_hot_output=np.argmax(output_classification, axis=1)
+        print(len(one_hot_output))        
+        print(one_hot_output)
 
-        for index in range(0, len(one_hot_output)):
-            one_hot_output[index] = CLASS_NAMES[one_hot_output[index]]
 
-        return one_hot_output
+
+        #output_classification = self.model.predict_generator(classify_generator)
+
+        #one_hot_output = np.argmax(output_classification, axis=1)
+
+        #one_hot_output = one_hot_output.tolist()
+        classes=[]
+        for index in range(0, len(one_hot_output)):
+            #print(index)
+            classes.append(CLASS_NAMES[one_hot_output[index]])
+        #print(len(classes))   
+        return classes
 
     def train(self, dataset, training_data, force=False):
         """Perform the training of classifier.

src/pynovisao.py

@@ -12,6 +12,7 @@ import numpy as np
 import os
 import interface
 import types
+
 import cv2
 from interface.interface import InterfaceException as IException
 from PIL import Image
@@ -39,6 +40,7 @@ from multiprocessing import Process, Manager
 import threading as th
 from tqdm import tqdm
 import psutil
+
 class Act(object):
     """Store all actions of Pynovisao."""
 
@@ -556,7 +558,7 @@ class Act(object):
             self._gt_segments = [None]*(max(list_segments)+1)
 
         #  New and optimized classification
-        tmp = ".tmp"
+        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))
@@ -584,10 +586,11 @@ class Act(object):
 
         # Get the label corresponding to predict class for each segment of image.
         labels = self.classifier.classify(self.dataset, test_dir=tmp, test_data="test.arff", image=self._const_image)
+        print(labels)
         File.remove_dir(File.make_path(self.dataset, tmp))
 
         # Result is the class for each superpixel
-        if type(labels) is types.ListType:
+        if len(labels)>0:
             self.tk.append_log("Painting segments... (%0.3f seconds)", (TimeUtils.get_time() - start_time))
 
             # If ground truth mode, show alternative results
@@ -615,7 +618,7 @@ class Act(object):
                 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: