fixes some warnings, model names chanages

classes/model/{pix2code2.py → Main_Model.py}

@@ -11,10 +11,10 @@ from .autoencoder_image import *
 import os
 
 
-class pix2code2(AModel):
+class Main_Model(AModel):
     def __init__(self, input_shape, output_size, output_path):
         AModel.__init__(self, input_shape, output_size, output_path)
-        self.name = "pix2code2"
+        self.name = "Main_Model"
 
         visual_input = Input(shape=input_shape)
 
@@ -39,7 +39,7 @@ class pix2code2(AModel):
         hidden_layer_model = Dropout(0.3)(hidden_layer_model)
         hidden_layer_result = RepeatVector(CONTEXT_LENGTH)(hidden_layer_model)
 
-        # Make sure the loaded hidden_layer_model_freeze will no longer be updated
+        # Making sure the loaded hidden_layer_model_freeze will no longer be updated
         for layer in hidden_layer_model_freeze.layers:
             layer.trainable = False
 
@@ -59,7 +59,7 @@ class pix2code2(AModel):
 
         self.model = Model(inputs=[visual_input, textual_input], outputs=decoder)
 
-        optimizer = RMSprop(lr=0.0001, clipvalue=1.0)
+        optimizer = RMSprop(learning_rate=0.0001, clipvalue=1.0)
         self.model.compile(loss='categorical_crossentropy', optimizer=optimizer)
 
     def fit_generator(self, generator, steps_per_epoch):

main_program.py

@@ -7,12 +7,12 @@ import os.path
 from os.path import basename
 
 from classes.Sampler import *
-from classes.model.pix2code2 import *
+from classes.model.Main_Model import *
 
 
 def dsl_code_generation(input_image):
     trained_weights_path = "classes/model/bin"
-    trained_model_name = "pix2code2"
+    trained_model_name = "Main_Model"
     input_path = input_image
     output_path = "data/output/"
     search_method = "greedy"
@@ -20,7 +20,7 @@ def dsl_code_generation(input_image):
     input_shape = meta_dataset[0]
     output_size = meta_dataset[1]
 
-    model = pix2code2(input_shape, output_size, trained_weights_path)
+    model = Main_Model(input_shape, output_size, trained_weights_path)
     model.load(trained_model_name)
 
     sampler = Sampler(trained_weights_path, input_shape, output_size, CONTEXT_LENGTH)