move vocab_size into implementation (not user dependent)

models/__init__.py

@@ -1,6 +1,5 @@
 import keras.backend as K
 
-import dataset
 from . import pauls_networks
 from . import renes_networks
 
@@ -9,7 +8,6 @@ def get_models_by_params(params: dict):
     # decomposing param section
     # mainly embedding model
     network_type = params.get("type")
-    vocab_size = len(dataset.get_character_dict()) + 1
     embedding_size = params.get("embedding_size")
     input_length = params.get("input_length")
     filter_embedding = params.get("filter_embedding")
@@ -26,8 +24,8 @@ def get_models_by_params(params: dict):
     dense_dim = params.get("dense_main")
     # create models
     networks = renes_networks if network_type == "rene" else pauls_networks
-    embedding_model = networks.get_embedding(vocab_size, embedding_size, input_length,
-                                             filter_embedding, kernel_embedding, hidden_embedding, drop_out=dropout)
+    embedding_model = networks.get_embedding(embedding_size, input_length, filter_embedding, kernel_embedding,
+                                             hidden_embedding, drop_out=dropout)
 
     predict_model = networks.get_model(dropout, flow_features, domain_features, window_size, domain_length,
                                        filter_main, kernel_main, dense_dim, embedding_model)

models/pauls_networks.py

@@ -2,6 +2,8 @@ import keras
 from keras.engine import Input, Model
 from keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, Dense, Dropout, Activation, TimeDistributed
 
+import dataset
+
 best_config = {
     "type": "paul",
     "batch_size": 64,
@@ -24,11 +26,10 @@ best_config = {
 }
 
 
-def get_embedding(vocab_size, embedding_size, input_length,
-                  filters, kernel_size, hidden_dims, drop_out=0.5):
+def get_embedding(embedding_size, input_length, filter_size, kernel_size, hidden_dims, drop_out=0.5):
     x = y = Input(shape=(input_length,))
-    y = Embedding(input_dim=vocab_size, output_dim=embedding_size)(y)
-    y = Conv1D(filters, kernel_size, activation='relu')(y)
+    y = Embedding(input_dim=dataset.get_vocab_size(), output_dim=embedding_size)(y)
+    y = Conv1D(filter_size, kernel_size, activation='relu')(y)
     y = GlobalMaxPooling1D()(y)
     y = Dropout(drop_out)(y)
     y = Dense(hidden_dims)(y)

models/renes_networks.py

@@ -3,11 +3,12 @@ from keras.engine import Input, Model
 from keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, Dense, Dropout, TimeDistributed, MaxPool1D, \
     GlobalAveragePooling1D
 
+import dataset
 
-def get_embedding(vocab_size, embedding_size, input_length,
-                  filter_size, kernel_size, hidden_dims, drop_out=0.5):
+
+def get_embedding(embedding_size, input_length, filter_size, kernel_size, hidden_dims, drop_out=0.5):
     x = y = Input(shape=(input_length,))
-    y = Embedding(input_dim=vocab_size, output_dim=embedding_size)(y)
+    y = Embedding(input_dim=dataset.get_vocab_size(), output_dim=embedding_size)(y)
     y = Conv1D(filter_size, kernel_size=5, activation='relu')(y)
     y = Conv1D(filter_size, kernel_size=3, activation='relu')(y)
     y = Conv1D(filter_size, kernel_size=3, activation='relu')(y)