added some argparse arguments to main

main.py

@@ -1,9 +1,63 @@
+import argparse
+
 import numpy as np
 from keras.utils import np_utils
 
 import dataset
 import models
 
+parser = argparse.ArgumentParser()
+
+parser.add_argument("--modes", action="store", dest="modes", nargs="+")
+
+# parser.add_argument("--data", action="store", dest="data",
+#                     default="data/")
+#
+# parser.add_argument("--h5data", action="store", dest="h5data",
+#                     default="")
+#
+# parser.add_argument("--model", action="store", dest="model",
+#                     default="model_x")
+#
+# parser.add_argument("--pred", action="store", dest="pred",
+#                     default="")
+#
+# parser.add_argument("--type", action="store", dest="model_type",
+#                     default="simple_conv")
+#
+parser.add_argument("--batch", action="store", dest="batch_size",
+                    default=64, type=int)
+
+parser.add_argument("--epochs", action="store", dest="epochs",
+                    default=10, type=int)
+
+# parser.add_argument("--samples", action="store", dest="samples",
+#                     default=100000, type=int)
+#
+# parser.add_argument("--samples_val", action="store", dest="samples_val",
+#                     default=10000, type=int)
+#
+# parser.add_argument("--area", action="store", dest="area_size",
+#                     default=25, type=int)
+#
+# parser.add_argument("--queue", action="store", dest="queue_size",
+#                     default=50, type=int)
+#
+# parser.add_argument("--p", action="store", dest="p_train",
+#                     default=0.5, type=float)
+#
+# parser.add_argument("--p_val", action="store", dest="p_val",
+#                     default=0.01, type=float)
+#
+# parser.add_argument("--gpu", action="store", dest="gpu",
+#                     default=0, type=int)
+#
+# parser.add_argument("--tmp", action="store_true", dest="tmp")
+#
+# parser.add_argument("--test", action="store", dest="test_image",
+#                     default=6, choices=range(7), type=int)
+
+args = parser.parse_args()
 
 # config = tf.ConfigProto(log_device_placement=True)
 # config.gpu_options.per_process_gpu_memory_fraction = 0.5
@@ -31,7 +85,6 @@ def main():
     threshold = 3
     minFlowsPerUser = 10
     numEpochs = 100
-    timesNeg = -1
 
     char_dict = dataset.get_character_dict()
     user_flow_df = dataset.get_user_flow_data()
@@ -39,7 +92,7 @@ def main():
     print("create training dataset")
     (X_tr, hits_tr, names_tr, server_tr, trusted_hits_tr) = dataset.create_dataset_from_flows(
         user_flow_df, char_dict,
-        maxLen=maxLen, windowSize=windowSize)
+        max_len=maxLen, window_size=windowSize)
     # make client labels discrete with 4 different values
     # TODO: use trusted_hits_tr for client classification too
     client_labels = np.apply_along_axis(lambda x: dataset.discretize_label(x, 3), 0, np.atleast_2d(hits_tr))
@@ -65,12 +118,14 @@ def main():
                   loss='binary_crossentropy',
                   metrics=['accuracy'])
 
-    epochNumber = 0
     client_labels = np_utils.to_categorical(client_labels, 2)
     server_labels = np_utils.to_categorical(server_labels, 2)
-    model.fit(X_tr, [client_labels, server_labels], batch_size=128,
-              epochs=epochNumber + 1, shuffle=True, initial_epoch=epochNumber)  # ,
-    # validation_data=(testData,testLabel))
+    model.fit(X_tr,
+              [client_labels, server_labels],
+              batch_size=args.batch_size,
+              epochs=args.epochs,
+              shuffle=True)
+    # TODO: for validation we use future data -> validation_data=(testData,testLabel))
 
 
 if __name__ == "__main__":

models.py

@@ -45,8 +45,8 @@ def get_top_cnn(cnn, numFeatures, maxLen, windowSize, domainFeatures, filters, k
     maxPool = GlobalMaxPooling1D()(cnn)
     cnnDropout = Dropout(cnnDropout)(maxPool)
     cnnDense = Dense(cnnHiddenDims, activation='relu')(cnnDropout)
-    cnnOutput1 = Dense(2, activation='softmax')(cnnDense)
-    cnnOutput2 = Dense(2, activation='softmax')(cnnDense)
+    cnnOutput1 = Dense(2, activation='softmax', name="client")(cnnDense)
+    cnnOutput2 = Dense(2, activation='softmax', name="server")(cnnDense)
 
     # We define a trainable model linking the
     # tweet inputs to the predictions