Implemented SEQ2SEQ_VAEP (Variational AutoEncoding Predictor) in models.py

source/model_utils.py

@@ -126,9 +126,9 @@ class KLDivergenceLayer(Layer):
 
         mu, log_var = inputs
 
-        kl_batch = -0.5 * K.sum(1 + log_var - K.square(mu) - K.exp(log_var), axis=-1)
+        kL_batch = -0.5 * K.sum(1 + log_var - K.square(mu) - K.exp(log_var), axis=-1)
 
-        self.add_loss(K.mean(kl_batch), inputs=inputs)
+        self.add_loss(K.mean(kL_batch), inputs=inputs)
 
         return inputs
 

source/models.py

@@ -458,13 +458,19 @@ class SEQ_2_SEQ_VAEP:
         x_decoded_mean = TimeDistributed(Dense(self.input_shape[2]))(generator)
 
         # Define and instantiate predictor
-        predictor = Dense(self.ENCODING, activation='relu', kernel_initializer=he_uniform())(z)
+        predictor = Dense(
+            self.ENCODING, activation="relu", kernel_initializer=he_uniform()
+        )(z)
         predictor = BatchNormalization()(predictor)
-        predictor = Dense(self.DENSE_2, activation='relu', kernel_initializer=he_uniform())(predictor)
+        predictor = Dense(
+            self.DENSE_2, activation="relu", kernel_initializer=he_uniform()
+        )(predictor)
         predictor = BatchNormalization()(predictor)
-        predictor = Dense(self.DENSE_1, activation='relu', kernel_initializer=he_uniform())(predictor)
+        predictor = Dense(
+            self.DENSE_1, activation="relu", kernel_initializer=he_uniform()
+        )(predictor)
         predictor = BatchNormalization()(predictor)
-        predictor = RepeatVector(self.input_shape[1]-1)(predictor)
+        predictor = RepeatVector(self.input_shape[1] - 1)(predictor)
         predictor = Bidirectional(
             LSTM(
                 self.LSTM_units_1,