From: Mart Lubbers <mart@martlubbers.net>
Date: Wed, 26 Apr 2017 09:59:01 +0000 (+0200)
Subject: verbosity added
X-Git-Url: https://git.martlubbers.net/?a=commitdiff_plain;h=c1032d366aa18bf2e5f3942af5852c74dcb4a895;p=asr1617data.git

verbosity added
---

diff --git a/experiments.py b/experiments.py
index adf76b1..989643e 100644
--- a/experiments.py
+++ b/experiments.py
@@ -17,6 +17,7 @@ from keras.layers import Dense, Dropout  # , Activation
 # Testset ratio
 testset = 0.10
 samplerate = 16000
+verbosity = 1
 
 def get_datafiles():
     files = glob.glob(os.path.join(os.getcwd(), 'textgrid', '*.TextGrid'))
@@ -67,7 +68,8 @@ def run(typ, winlen, winstep, modelfun, modelname):
     labels = []
 
     for tg, wavp in get_datafiles():
-        (d, l) = features_from_wav(tg, wavp, winlen=winlen, winstep=winstep, typ=typ)
+        (d, l) = features_from_wav(
+            tg, wavp, winlen=winlen, winstep=winstep, typ=typ)
         datas.append(d)
         labels.append(l)
 
@@ -88,16 +90,18 @@ def run(typ, winlen, winstep, modelfun, modelname):
 
     #Train
     model.fit(traindata, trainlabels, epochs=10, batch_size=32, shuffle=False,
-            verbose=0)
+              verbose=verbosity)
 
     #Test
-    loss, acc = model.evaluate(testdata, testlabels, batch_size=32, verbose=0)
+    loss, acc = model.evaluate(testdata, testlabels, batch_size=32,
+                               verbose=verbosity)
     print('{}\t{}\t{}\t{}\t{}\n'.format(
         winlen, winstep, modelname, loss, acc))
 
 def simplemodel(d):
     model = Sequential()
-    model.add(Dense(d.shape[1]*2, input_shape=(d.shape[1],), activation='relu'))
+    model.add(
+        Dense(d.shape[1]*2, input_shape=(d.shape[1],), activation='relu'))
     model.add(Dense(100, activation='relu'))
     model.add(Dense(1, activation='sigmoid'))
     model.compile(optimizer='rmsprop',
@@ -107,7 +111,8 @@ def simplemodel(d):
 
 def bottlemodel(d):
     model = Sequential()
-    model.add(Dense(d.shape[1]*2, input_shape=(d.shape[1],), activation='relu'))
+    model.add(
+        Dense(d.shape[1]*2, input_shape=(d.shape[1],), activation='relu'))
     model.add(Dense(13, activation='relu'))
     model.add(Dense(1, activation='sigmoid'))
     model.compile(optimizer='rmsprop',