Keras Input/Output

Question

I am struggling with a challenge in Tensorflow / keras, would be great if someone could help me.

I have build a neural net in Keras with input_dim=3, then 10 Neurons and Output 1.

The input is a 3d-vector with floats, the output should be a simple float value.

My problem is, that I dont know how the floats should be formatted (>1, from 0 to 1?, etc...) and which loss function could work out for this task (nothing binary i guess). I want the neural net to compute out of the 3d vector a simple float value. But it never works out because my outputs are always the same.

If I have forgotten something please let me know, if you have some ideas to it, it would be great!

Greetings

Edit: Im aware of the fact that I need an introduction into the whole topic of machine learning, which I am doing right now. In the mean time I would like to know how to use keras to verifiy/practically use machine learning. I am sorry for asking 'stupid' questions but I hope that maybe someone could help me.

Input: I think the input might be 'wrong' formatted, its not normalized etc., but I transformed the values i get to an interval mentioned below.

This is my simple model:

model = Sequential()
model.add(Dense(10, input_dim=3, init='normal', activation='sigmoid'))
model.add(Dense(1, init='normal', activation='sigmoid'))
model.compile(loss='mse', optimizer='sgd', metrics=['accuracy'])
model.fit(X_Train, Y_Train, nb_epoch=100, batch_size=32, verbose=1)

X_Train and Y_Train are values extracted from a .csv file. For example my input values are [a,b,c,d], where 0 < a,b,c < 1 and -1 < d < 1 (d is output).

Output:

Epoch 500/500

32/32 [==============================] - 0s - loss: 0.0813 - acc: 0.0000e+00

Example (random generated values), all output is nearly the same around 0.43:

[ 0.97650245 0.30383579 0.74829968] [[ 0.43473071]]

[ 0.94985165 0.75347051 0.72609185] [[ 0.43473399]]

[ 0.18072594 0.18540003 0.20763266] [[ 0.43947196]]

please share some code (maybe as a git gist) and exact output. what does "But it never works out because my outputs are always the same" mean? How one can tell you why they are same without seeing your code? — Dima Lituiev
– Dima Lituiev, Commented Oct 17, 2016 at 16:18
From the vocabulary you are using, I believe you would benefit from a good introduction to the gist of machine learning. Eg. the notion of formatting input vectors in ML doesn't seem familiar. Normalizing, yes — Arnaud P
– Arnaud P, Commented Oct 17, 2016 at 17:36

Jie HE · Accepted Answer · 2017-07-31 13:57:33Z

3

Firstly, there is no need for normalizing (or formatting) the input samples.

Secondly, for the problem of zero accuracy, it's because you used the "accuracy" as metrics which is used for classification model. In your case, you should use something like "mse" or "mae" (in Keras) as metrics in your compile method, e.g.,

model.compile(loss='mse', optimizer='sgd', metrics=['mae'])

edited Jul 31, 2017 at 13:57

answered Apr 6, 2017 at 13:40

Jie HE

1731 silver badge8 bronze badges

Sign up to request clarification or add additional context in comments.

Comments

itvai · Accepted Answer · 2016-10-20 06:36:51Z

2

I'm answering my own question:

The problem here is the optimizer! The training data and every other setting is not that important. You have to try other optimizers, to vary the results. Its possible to close this question now. Thank you for your help!

answered Oct 20, 2016 at 6:36

itvai

314 bronze badges

Comments

kochol · Accepted Answer · 2019-05-11 22:10:52Z

0

Change your output layer to following model.add(Dense(1))

See this regression guide that talks about one output. https://www.tensorflow.org/tutorials/keras/basic_regression

answered May 11, 2019 at 22:10

kochol

637 bronze badges

Collectives™ on Stack Overflow

Keras Input/Output

3 Answers 3

Comments

Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

3 Answers 3

Comments

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related