Open source high-level neural network library for Python and R. Is capable of using TensorFlow or Theano as backend.
Questions tagged [keras]
681 questions
6
votes
1 answer
What is the meaning of fuzz factor?
I came across this documentation in keras for the list of
backend functions
One of which was keras.backend.epsilon()
The documentation says that it returns the value of the fuzz factor used in numeric expressions. However I could not understand what…
numpy
- 63
2
votes
1 answer
How can Keras training be stopped manually while also returning the best weights?
I am using Keras 2.2.4 and normally I use the Keras EarlyStopping callback to halt training while ensuring that the best weights observed during that training are returned. So, I have something like the following:
stop_early =…
BlandCorporation
- 141
2
votes
1 answer
What does Keras Concatenate actually do?
A simple question, but what does Keras Concatenate actually do?. If I have two input layers with size 200 each and pass them through a concat layer what has actually happened? Does it just mean the output of the concatenated layer is treated as a…
kPow989
- 123
2
votes
1 answer
Can MAE be higher than MSE?
I am using Mean Absolute Value(MAE) and Mean Squared Error(MSE) as my evaluation parameters for the regression model. I am trying to predict the future values for time series model and have used CNN fro the same. However, my CNN model is giving very…
Rohan Akut
- 23
1
vote
0 answers
How might a Keras model be exported to a mathematical expression?
What would be a way to export a trained Keras model (in this case an Inception CNN) to a mathematical expression, such as one suitable for inclusion in a LaTeX document?
I see an attempt here but it is faultering:…
BlandCorporation
- 141
0
votes
1 answer
Kernel dies when calling fit method
I am running Python 3.6.8 (Anaconda Distribution) on a MacBook Pro 2017. I keep running into this issue where my kernel dies when I try to called the fit method of a Keras model. This occurs in Spyder, as well as in Jupyter Notebook. The code I am…
Beane
- 301
0
votes
0 answers
Making a simple Keras classification with a low sample size
I am trying to learn Keras and rather than starting with a large dataset I dont understand, I figured it would be better to create a simple dataset that in theory should be abe to have a 100% succesful prediction rate, but it only predicts 16.67%…
MathiasRa
- 113
- 4
0
votes
1 answer
My NN in keras predict values always between 0 and 1
I have written a simple neural network by keras (R API) as follow:
# Creates dense embedding layer; outputs 3D tensor
# with shape (batch_size, sequence_length, output_dim)
layer_embedding(input_dim = 100,
output_dim = 30,
…
Jole
- 1
- 1
- 2