fix classification CNN with h.5

src/classification/cnn_keras.py

@@ -22,7 +22,7 @@ from PIL import Image
 from keras import applications
 from keras.preprocessing.image import ImageDataGenerator
 from keras import optimizers
-from keras.models import Model, load_model
+from keras.models import Model 
 from keras.layers import Dropout, Flatten, Dense
 from keras.callbacks import ModelCheckpoint, TensorBoard
 from keras import backend as K
@@ -38,8 +38,8 @@ from collections import OrderedDict
 from util.config import Config
 from util.file_utils import File
 from util.utils import TimeUtils
-        
 
+from tensorflow.keras.models import load_model
 
 logger = logging.getLogger('PIL')
 logger.setLevel(logging.WARNING)
@@ -60,7 +60,8 @@ dict_preprocessing[2] = applications.vgg19.preprocess_input, applications.vgg19.
 dict_preprocessing[3] = applications.resnet50.preprocess_input, applications.resnet50.decode_predictions
 dict_preprocessing[4] = applications.inception_v3.preprocess_input, applications.inception_v3.decode_predictions
 dict_preprocessing[5] = applications.mobilenet.preprocess_input, applications.mobilenet.decode_predictions
-
+dict_preprocessing[6] = applications.densenet.preprocess_input, applications.densenet.decode_predictions
+dict_preprocessing[7] = applications.resnet_v2.preprocess_input, applications.resnet_v2.decode_predictions
 class CNNKeras(Classifier):
     """ Class for CNN classifiers based on Keras applications """
 
@@ -370,6 +371,14 @@ class CNNKeras(Classifier):
                 self.app = 5
                 model = applications.MobileNet(
                     weights="imagenet", include_top=False, input_shape=(IMG_WIDTH, IMG_HEIGHT, 3))
+            elif self.architecture.value == "DenseNet201":
+                self.app = 6
+                model = applications.DenseNet201(
+                    weights="imagenet", include_top=False, input_shape=(IMG_WIDTH, IMG_HEIGHT, 3))
+            elif self.architecture.value == "ResNet152V2":
+                self.app = 7
+                model = applications.ResNet152V2(
+                    weights="imagenet", include_top=False, input_shape=(IMG_WIDTH, IMG_HEIGHT, 3))
 
             for layer in model.layers[:int(len(model.layers) * (self.fine_tuning_rate.value / 100.0))]:
                 layer.trainable = False
@@ -399,6 +408,14 @@ class CNNKeras(Classifier):
                 self.app = 5
                 model = applications.MobileNet(
                     weights=None, include_top=False, input_shape=(IMG_WIDTH, IMG_HEIGHT, 3))
+            elif self.architecture.value == "DenseNet201":
+                self.app = 6
+                model = applications.DenseNet201(
+                    weights=None, include_top=False, input_shape=(IMG_WIDTH, IMG_HEIGHT, 3))
+            elif self.architecture.value == "ResNet152V2":
+                self.app = 7
+                model = applications.ResNet152V2(
+                    weights=None, include_top=False, input_shape=(IMG_WIDTH, IMG_HEIGHT, 3))                    
             for layer in model.layers:
                 layer.trainable = True
 

src/pynovisao.py

@@ -619,6 +619,7 @@ class Act(object):
                 popup_info += "%-16s%-16s%0.2f%%\n" % (cl["name"].value, str(len_classes), (len_classes*100.0)/len_total)
 
             print(popup_info)
+            cv2.imwrite("rf2000.png",self._image)
             self.tk.refresh_image(self._image)
             self.tk.popup(popup_info)
         else: