V1.1

ConvolutionalNeuralNetwor.py

@@ -24,8 +24,7 @@ X_valid, y_valid = shuffle(X_valid, y_valid)
 X_train_norm = X_train / 255
 X_valid_norm = X_valid / 255
 
-
-
+#Wähle Klassen 0-19
 mask = np.isin(y_train, range(20))
 X_train_subset = X_train_norm[mask]
 y_train_subset = y_train[mask]
@@ -58,7 +57,7 @@ model.compile(optimizer = 'Adam', loss = 'sparse_categorical_crossentropy', metr
 history = model.fit(x = X_train_subset,
                     y = y_train_subset,
                     batch_size = 32,
-                    epochs = 1,
+                    epochs = 10000,
                     verbose = 1,
                     validation_data = (X_valid_subset, y_valid_subset))
 

FullyConnectedNeuralNetwork.py

@@ -24,8 +24,7 @@ X_valid, y_valid = shuffle(X_valid, y_valid)
 X_train_norm = X_train / 255
 X_valid_norm = X_valid / 255
 
-
-
+#Wähle Klassen 0-19
 mask = np.isin(y_train, range(20))
 X_train_subset = X_train_norm[mask]
 y_train_subset = y_train[mask]
@@ -58,7 +57,7 @@ model.compile(optimizer = 'Adam', loss = 'sparse_categorical_crossentropy', metr
 history = model.fit(x = X_train_subset,
                     y = y_train_subset,
                     batch_size = 32,
-                    epochs = 10,
+                    epochs = 10000,
                     verbose = 1,
                     validation_data = (X_valid_subset, y_valid_subset))
 

TestMitValid.py

@@ -24,13 +24,13 @@ X_valid, y_valid = shuffle(X_valid, y_valid)
 X_train_norm = X_train / 255
 X_valid_norm = X_valid / 255
 
-
-
+#Wähle Klassen 0-19
 mask = np.isin(y_valid, range(20))
 X_valid_subset = X_valid_norm[mask]
 y_valid_subset = y_valid[mask]
 
 
+
 #convolutionalNeuralNetwork
 #fullyConnectedNeuralNetwork
 model = tf.keras.models.load_model('saved_model/convolutionalNeuralNetwork.h5')

TestOnePicture.py

@@ -24,14 +24,15 @@ X_valid, y_valid = shuffle(X_valid, y_valid)
 X_train_norm = X_train / 255
 X_valid_norm = X_valid / 255
 
-
+#TakeOnePicture
 filtered_indices = [i for i, label in enumerate(y_valid) if label >= 0 and label <= 19]
 indice = random.choice(filtered_indices)
 X_valid_subset = X_valid[indice][np.newaxis, ...]
 y_valid_subset = y_valid[indice][np.newaxis, ...]
-
 print(y_valid_subset)
 
+
+
 #convolutionalNeuralNetwork
 #fullyConnectedNeuralNetwork
 model = tf.keras.models.load_model('saved_model/fullyConnectedNeuralNetwork.h5')