CODEWITHSUNDEEP
machine-learningkerasdeep-learning
user3773676
user3773676

Reputation: 5

Keras output looks different than others

When I run the below code :

from keras.models import Sequential
from keras.layers import Dense
import numpy
import time

# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# load dataset

dataset = numpy.loadtxt("C:/Users/AQader/Desktop/Keraslearn/mammm.csv", delimiter=",")
# split into input (X) and output (Y) variables
X = dataset[:,0:5]
Y = dataset[:,5]

# create model
model = Sequential()
model.add(Dense(50, input_dim=5, init='uniform', activation='relu'))
model.add(Dense(25, init='uniform', activation='tanh'))
model.add(Dense(15, init='uniform', activation='tanh'))
model.add(Dense(1, init='uniform', activation='sigmoid'))

# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

# Fit the model
model.fit(X, Y, nb_epoch=200, batch_size=20, verbose = 0)
time.sleep(0.1)

# evaluate the model
scores = model.evaluate(X, Y)
print("%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))

I end up receiving the following.

32/829 [>.............................] - ETA: 0sacc: 84.20%

That's it. Only one line that shows up after a half minute of training. After looking through other questions, the usual output looks like:

Epoch 1/20
1213/1213 [==============================] - 0s - loss: 0.1760     
Epoch 2/20
1213/1213 [==============================] - 0s - loss: 0.1840     
Epoch 3/20
1213/1213 [==============================] - 0s - loss: 0.1816     
Epoch 4/20
1213/1213 [==============================] - 0s - loss: 0.1915     
Epoch 5/20
1213/1213 [==============================] - 0s - loss: 0.1928     
Epoch 6/20
1213/1213 [==============================] - 0s - loss: 0.1964     
Epoch 7/20
1213/1213 [==============================] - 0s - loss: 0.1948     
Epoch 8/20
1213/1213 [==============================] - 0s - loss: 0.1971     
Epoch 9/20
1213/1213 [==============================] - 0s - loss: 0.1899     
Epoch 10/20
1213/1213 [==============================] - 0s - loss: 0.1957

Can anyone tell me what may be wrong here? I am a beginner in this yet this doesn't seem normal. Please note that there are no errors in the "code" sections. What I mean is that the 0sacc is what shows up. I'm running this in the Anaconda Environment Python 2.7 on a Windows 7 64-bit machine. 8GB RAM and Core i5 5th gen.

Upvotes: 0

Views: 147

Answers (1)

Christian Hirsch
Christian Hirsch

Reputation: 2056

By calling model.fit with verbose = 0 you have suppressed detailed output. Try setting verbose = 1.

Upvotes: 1

Related Questions