added some argparse arguments to main

This commit is contained in:
René Knaebel 2017-07-03 13:48:12 +02:00
parent c972963a19
commit 5f8a760a0c
2 changed files with 63 additions and 8 deletions

67
main.py
View File

@ -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__":

View File

@ -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