Update app.py

app.py

@@ -45,7 +45,7 @@ def prepare_sequences(notes, pitchnames, n_vocab , seq_length):
     n_patterns = len(network_input)
 
     # reshape the input into a format compatible with LSTM layers
-    normalized_input = numpy.reshape(network_input, (n_patterns, sequence_length, 1))
+    normalized_input = np.reshape(network_input, (n_patterns, sequence_length, 1))
     # normalize input
     normalized_input = normalized_input / float(n_vocab)
 
@@ -84,7 +84,7 @@ def create_network(network_input, n_vocab):
 def generate_notes(model, network_input, pitchnames, n_vocab , x):
     """ Generate notes from the neural network based on a sequence of notes """
     # pick a random sequence from the input as a starting point for the prediction
-    start = numpy.random.randint(0, len(network_input)-1)
+    start = np.random.randint(0, len(network_input)-1)
 
     int_to_note = dict((number, note) for number, note in enumerate(pitchnames))
 
@@ -93,12 +93,12 @@ def generate_notes(model, network_input, pitchnames, n_vocab , x):
 
     # generate x notes (x entered by user)
     for note_index in range(x):
-        prediction_input = numpy.reshape(pattern, (1, len(pattern), 1))
+        prediction_input = np.reshape(pattern, (1, len(pattern), 1))
         prediction_input = prediction_input / float(n_vocab)
 
         prediction = model.predict(prediction_input, verbose=0)
 
-        index = numpy.argmax(prediction)
+        index = np.argmax(prediction)
         result = int_to_note[index]
         prediction_output.append(result)