diff --git a/AirShower_WGAN/ShowerGAN.py b/AirShower_WGAN/ShowerGAN.py
index f879d906fa88e3de2b498b16459703688bafa651..dcf5e323a058b57c18e0244d49f2986ef0d16228 100644
--- a/AirShower_WGAN/ShowerGAN.py
+++ b/AirShower_WGAN/ShowerGAN.py
@@ -8,7 +8,6 @@ from keras.layers.advanced_activations import LeakyReLU
 from functools import partial
 from keras.utils import plot_model
 import keras.backend.tensorflow_backend as KTF
-import glob
 import utils
 import tensorflow as tf
 
@@ -16,22 +15,19 @@ import tensorflow as tf
 KTF.set_session(utils.get_session())  # Allows 2 jobs per GPU, Please do not change this during the tutorial
 log_dir="."
 
-EPOCHS = 3
+EPOCHS = 10
 GRADIENT_PENALTY_WEIGHT = 10
 BATCH_SIZE = 256
 NCR = 5
 latent_size = 512
-# load trainings data
-
-filenames=glob.glob("*.npz")
 
-shower_maps, Energy = utils.ReadInData(filenames)
-#shower_maps = shower_maps[:,:,:,1,np.newaxis]
-#np.savez("Data", Energy=Energy, shower_maps=shower_maps)
-Energy = Energy/np.max(Energy)
+# load trainings data
+shower_maps, Energy = utils.ReadInData()
+N = shower_maps.shape[0]
+# plot real signal patterns
 utils.plot_multiple_signalmaps(shower_maps[:,:,:,0], log_dir=log_dir, title='Footprints', epoch='Real')
 
-N = shower_maps.shape[0]
+
 
 class RandomWeightedAverage(_Merge):
     """Takes a randomly-weighted average of two tensors. In geometric terms, this outputs a random point on the line
@@ -116,6 +112,7 @@ critic_loss = []
 iterations_per_epoch = N//((NCR+1)*BATCH_SIZE)
 for epoch in range(EPOCHS):
     print "epoch: ", epoch
+    # plot berfore each epoch generated signal patterns
     generated_map = generator.predict_on_batch(np.random.randn(BATCH_SIZE, latent_size))
     utils.plot_multiple_signalmaps(generated_map[:,:,:,0], log_dir=log_dir, title='Generated Footprints Epoch: ', epoch=str(epoch))
     for iteration in range(iterations_per_epoch):
@@ -131,6 +128,6 @@ for epoch in range(EPOCHS):
 utils.plot_loss(critic_loss, name="critic", log_dir=log_dir)
 utils.plot_loss(generator_loss, name="generator",log_dir=log_dir)
 
-# plot some generated figures
+# plot some generated signal patterns
 generated_map = generator.predict(np.random.randn(BATCH_SIZE, latent_size))
 utils.plot_multiple_signalmaps(generated_map[:,:,:,0], log_dir=log_dir, title='Generated Footprints', epoch='Final')
diff --git a/AirShower_WGAN/utils.py b/AirShower_WGAN/utils.py
index ef1772ccea69ee1fb759f44b8f8f55fc773a5539..886c619531c5c5c67f71df2f5467b4a2cb49f141 100644
--- a/AirShower_WGAN/utils.py
+++ b/AirShower_WGAN/utils.py
@@ -15,17 +15,11 @@ def get_session(gpu_fraction=0.40):
     return tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
 
 
-def ReadInData(filenames):
+def ReadInData():
     '''Reads in the trainings data'''
-    N = 100000 *len(filenames)
-    a = 100000
-    shower_maps = np.zeros(N*9*9*1).reshape(N,9,9,1)
-    Energy = np.zeros(N)
-    for i in range(0, len(filenames)):
-        data = np.load(filenames[i])
-        Energy[a*i:a*(i+1)] = data['Energy']
-        shower_maps[a*i:a*(i+1)] = data['shower_maps'].reshape(a,9,9,1)
-    return shower_maps, Energy
+    filenames="/net/scratch/JGlombitza/Public/HAPWorkshop2018/data/Data.npz"
+    data = np.load(filenames)
+    return  data['shower_maps'], data['Energy']
 
 
 def make_trainable(model, trainable):