add server classification model

models/__init__.py

@@ -7,14 +7,14 @@ from . import flat_2, pauls_networks, renes_networks
 def get_models_by_params(params: dict):
     # decomposing param section
     # mainly embedding model
-    network_type = params.get("type")
+    # network_type = params.get("type")
     network_depth = params.get("depth")
     embedding_size = params.get("embedding")
     input_length = params.get("input_length")
     filter_embedding = params.get("filter_embedding")
     kernel_embedding = params.get("kernel_embedding")
     hidden_embedding = params.get("dense_embedding")
-    dropout = params.get("dropout")
+    # dropout = params.get("dropout")
     # mainly prediction model
     flow_features = params.get("flow_features")
     window_size = params.get("window_size")
@@ -44,7 +44,36 @@ def get_models_by_params(params: dict):
     return embedding_model, old_model, new_model
 
 
-def get_metrics():
+def get_server_model_by_params(params: dict):
+    # decomposing param section
+    # mainly embedding model
+    network_depth = params.get("depth")
+    embedding_size = params.get("embedding")
+    input_length = params.get("input_length")
+    filter_embedding = params.get("filter_embedding")
+    kernel_embedding = params.get("kernel_embedding")
+    hidden_embedding = params.get("dense_embedding")
+    # mainly prediction model
+    flow_features = params.get("flow_features")
+    domain_length = params.get("domain_length")
+    dense_dim = params.get("dense_main")
+    # create models
+    if network_depth == "flat1":
+        networks = pauls_networks
+    elif network_depth == "flat2":
+        networks = flat_2
+    elif network_depth == "deep1":
+        networks = renes_networks
+    else:
+        raise Exception("network not found")
+    
+    embedding_model = networks.get_embedding(embedding_size, input_length, filter_embedding, kernel_embedding,
+                                             hidden_embedding, 0.5)
+    
+    return networks.get_server_model(flow_features, domain_length, dense_dim, embedding_model)
+
+
+def get_custom_objects():
     return dict([
         ("precision", precision),
         ("recall", recall),

models/flat_2.py

@@ -3,7 +3,8 @@ from collections import namedtuple
 import keras
 from keras.activations import elu
 from keras.engine import Input, Model as KerasModel
-from keras.layers import Conv1D, Dense, Dropout, Embedding, GlobalAveragePooling1D, GlobalMaxPooling1D, TimeDistributed
+from keras.layers import BatchNormalization, Conv1D, Dense, Dropout, Embedding, GlobalAveragePooling1D, \
+    GlobalMaxPooling1D, TimeDistributed
 
 import dataset
 
@@ -40,6 +41,8 @@ def get_model(cnnDropout, flow_features, domain_features, window_size, domain_le
     ipt_domains = Input(shape=(window_size, domain_length), name="ipt_domains")
     encoded = TimeDistributed(cnn, name="domain_cnn")(ipt_domains)
     ipt_flows = Input(shape=(window_size, flow_features), name="ipt_flows")
+    ipt_flows = BatchNormalization()(ipt_flows)
+    ipt_flows = Dense(dense_dim, activation=selu)(ipt_flows)
     merged = keras.layers.concatenate([encoded, ipt_flows], -1)
     # CNN processing a small slides of flow windows
     y = Conv1D(cnn_dims,

models/pauls_networks.py

@@ -89,3 +89,16 @@ def get_new_model(dropout, flow_features, domain_features, window_size, domain_l
     out_client = Dense(1, activation='sigmoid', name="client")(y)
 
     return Model(ipt_domains, ipt_flows, out_client, out_server)
+
+
+def get_server_model(flow_features, domain_length, dense_dim, cnn):
+    ipt_domains = Input(shape=(domain_length,), name="ipt_domains")
+    ipt_flows = Input(shape=(flow_features,), name="ipt_flows")
+    encoded = cnn(ipt_domains)
+    merged = keras.layers.concatenate([encoded, ipt_flows], -1)
+    y = Dense(dense_dim,
+              activation="relu",
+              name="dense_server")(merged)
+    out_server = Dense(1, activation="sigmoid", name="server")(y)
+    
+    return KerasModel(inputs=[ipt_domains, ipt_flows], outputs=out_server)