Questions tagged [keras]

Open source high-level neural network library for Python and R. Is capable of using TensorFlow or Theano as backend.

173 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
0
votes
0answers
105 views

Neural Network Parallel Architecture

I am a beginner to Machine Learning. While working on a personal project with VAEs, I had an idea. I will first give some background. Sometimes I have seen that it is common practice, when creating ...
0
votes
1answer
335 views

How to get consistency in neural network and eliminate possibility of NaN values?

I'm using a neural network(Keras,LSTM) for time series regression. Whenever I run the network, I get different outputs for the prediction. This is presumably due to the randomised weight ...
0
votes
0answers
61 views

Keras L2 regularized LogReg with Dense Layer yields too small bias

I just started using Tensorflow and Keras. To start with I thought it might be a good idea to implement a logistic regression for practise and testing. Having done that I am facing the problem, that ...
0
votes
0answers
455 views

Auxiliary loss function keras

I'm trying to write the custom loss function called ( Auxiliary loss function) which are two softmax loss functions put together that controls both the Context path and Spatial path of the network. ...
0
votes
0answers
78 views

GAN generated images all similar per epoch

I'm working on a GAN using cifar-10 images. After each epoch I create 10 new random z noise vectors, and use them to create 10 images using the generator. All of the 10 images look very similar, but ...
0
votes
0answers
154 views

keras embedding training optimization objective

I am aware of this and this existing questions, as well as this issue on github. Unless I am missing something though, all these fail to explain how the example in the keras docs makes sense: ...
0
votes
0answers
159 views

Different results for stratified cross validation and train test split for CNN

I am trying to develop an image classifier using conventional neural networks. Now I was looking at evaluating the model using 10-fold cross validation and through repeated train test splitting (hold ...
0
votes
0answers
65 views

Neural network not learning with custom loss function

I have implemented a custom loss function that is supposed to enhance a binary cross entropy loss function, by weighting incorrect decisions depending on an opportunity cost. The whole code is listed ...
0
votes
1answer
86 views

What are different methods to find the slow decrease in training/validation loss

I am training YOLO network consisting of resnet50 architecture.This problem is to find different text labels on the image and predict bounding boxes During training, I am seeing very less change in ...
0
votes
1answer
46 views

why does data external from training and testing my neural network perform much worse than statistical accuracy?

I've got a problem with my neural network (used to recognize audio signals, an expansion of the UrbanSound dataset problem): when I fit the model the accuracy of both train and validation is near 90%. ...
0
votes
1answer
1k views

How to design a many-to-many LSTM RNN in Keras

I have timeseries data with 1 minute cadence with 4 features, and I want to try to predict the time-evolution of 2 of these features using a RNN using LSTMs in Keras. My aim is to predict the e.g. ...
0
votes
0answers
39 views

Deep learning evaluation result

A CNN model in Keras gave me the following result. Code: ...
0
votes
0answers
89 views

Neural network performance degradation when input is standardised and mean-centered

In an effort to do some debugging of my simple multi-layer-perceptron regression problem, I have one input feature $x$ and one output feature $x$, meaning that the network should simply output ...
0
votes
0answers
224 views

Not smooth validation accuracy vs test accuracy. When to stop

I have a convolutional model with this training history. Validation accuracy is growing slowly but it is almost flat. The net is a two conv+maxpool layers and 3 dense layers. The training dataset ...
0
votes
0answers
27 views

Handling sequences with the same beginning but different ending with LSTM

I recently read this answer on LSTM internals, but some things are still not clear to me. Say an LSTM (many to many) is supposed to learn 2 sequences ...
0
votes
1answer
4k views

How do I increase accuracy with Keras using LSTM

I will start with saying I am a complete beginner and doing this assignment for a class, and having some issues on how to get this to be accurate and (somewhat) show it's working! Can someone that ...
0
votes
0answers
494 views

How to visualize char-rnn model

I am looking for any resource or tutorial which can help me to understand the visualization done by Andrej Karpathy’s blog (http://karpathy.github.io/2015/05/21/rnn-effectiveness/) or the simpler ...
0
votes
1answer
2k views

Validation accuracy reach to 1.000 in very first epoch

I am using below small 3D CNN to predict whether 32*32*32 image cube in a CT scan is malignant or not. ...
0
votes
0answers
1k views

LSTM for multivariate time series forecasting with unknown response

I am working on a LSTM model whose purpose is to estimate (in real time) the arrival date (eta) of a boat, based on the remaining kilometers to destination and several other variables. My data frame ...
0
votes
1answer
2k views

Keras - text classification, overfitting, and how to improve my model?

i am developing a text classification neural network based on this two articles - https://github.com/jiegzhan/multi-class-text-classification-cnn-rnn https://machinelearningmastery.com/sequence-...
0
votes
0answers
1k views

How to prepare sequence data for input/output for a LSTM generative model?

I've a set of data containing midi message information such as pitch, velocity, note on/off and delta time between the messages. These messages basically just act like the different musical notes. I ...
0
votes
1answer
35 views

Can I convolve over spatially remote pixels in 1DConv in Keras

I was successfully able to use keras's Conv1D layer for sentence multi-category classification. Now I would like to use it for binary classification deciding whether a person is going to ask for a ...
0
votes
1answer
61 views

What changes should I make to this NN to get a better loss/epoch curve?

I am attempting to train a neural network to fit some data with the following architecture: ...