Questions tagged [keras]

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

237 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
5
votes
0answers
518 views

traditional state-space models and LSTMs

I am trying to understand the nature of LSTMs in relation to intuitions from traditional state-space models (e.g., Kalman filtering). The code below aims to simulate a simple univariate linear state-...
4
votes
1answer
836 views

Trouble training LSTM for sequence to sequence learning of sensor time series

I'm experimenting with using RNNs/LSTMs in place of a Kalman Filter (KF) for sensor fusion. I'm struggling to make much progress, and would appreciate some feedback/advice. I have several multi-...
3
votes
1answer
193 views

Choosing activation and loss functions in autoencoder

I am following this keras tutorial to create an autoencoder using the MNIST dataset. Here is the tutorial: https://blog.keras.io/building-autoencoders-in-keras.html. However, I am confused with the ...
3
votes
0answers
27 views

Are there extant deep learning analogs to random coefficient (aka mixed) models?

Random coef models, applied to longitudinal data, capture response heterogeneity by cross-sectional unit. I've got a longitudinal prediction problem, in which I know that some "features" (or ...
3
votes
0answers
173 views

Image classification with large images

I am new to image classification and hope to set up a model which will classify large images (I am using R keras). Each image will represent a 10m by 10m square with pixels representing 1 cm. I need ...
3
votes
0answers
38 views

Bagging of models with link functions

I'm trying to predict proportion data, and I've got a small dataset (~4000), so holding out a test and validation set isn't practical. However, bagging is practical because the cost of training isn't ...
3
votes
0answers
985 views

Validation loss is less than training loss by 5 units. How this result is interpreted?

Iam training a Keras model for end-to-end speech recognition. I have my own dataset of speech containing about 400 wave files. Text transcriptions is also given as input. Model summary is: ...
3
votes
0answers
1k views

input image size for deep learinng models

i have two set of images. One of size 120*60 and other of size 1022*81. Most of the deep learning models require size 224*224 or some other standard dimension as an input. Can i put these images ...
3
votes
0answers
2k views

LSTM for stock prices and trends prediction

I have an assignment to create a LSTM network predicting price and trend of cryptocurrencies based on stock market data from the past. The network I am using is a multilayered LSTM, where layers are ...
3
votes
0answers
148 views

Is this normal convolution or something special?

I am currently studying this paper (page 53) (mirror), in which the suggest convolution to be done in a special manner. This is the formula: \begin{equation} \tag{1}\label{1} q_{j,m} = \sigma \left(...
3
votes
2answers
5k views

How to train a LSTM model for a next basket recommendation problem?

I try to use a LSTM model for a problem of next basket recommendation. I would like to apply the same approach as this article in Python using Keras : A Dynamic Recurrent Model for Next Basket ...
2
votes
0answers
6 views

What are good values for sample weights for UNet?

I'm trying to implement U-Net (https://arxiv.org/abs/1505.04597) from scratch using Keras. The thing about UNet apart from its architecture, is that it's using weight-maps from the input images in the ...
2
votes
0answers
32 views

Resize images before training object detection

I am training an object detector. I didn't resize my image before labeling because the of assumption that the model does this automatically to fit its input shape. ...
2
votes
0answers
65 views

Cross validation with Early Stopping

I would like to use EarlyStopping in k-fold cross-validation framework but not to find the optimal number of epochs, but only to reduce overfitting during the trainings runs. However, I would like to ...
2
votes
1answer
128 views

How to feed multivariate spatio-temporal data into cnn?

After trying to find an example for quite a while, I finally came to ask my question here: What I have: I have a temporal sequence of 2d spatial data with 100 cells(or pixels) in longitude and 30 ...
2
votes
0answers
106 views

Accuracy of Keras Model is Very Low for Identifying Differently Colored Objects

I am using transfer learning approach to train my keras model to identify objects which have same structure but the colors are different i.e objects are to be identified by their respective color. ...
2
votes
0answers
810 views

loss function in CRF keras-contrib returns Nan in join mode

I use a BiLSTM-CRF architecture to assign some labels to a sequence of the sentences in a paper. We have 150 papers each of which contains 380 sentences and each sentence is represented by a double ...
2
votes
0answers
52 views

A mistake in Tensorflow's documation?

Tensorflow's documentation gives an example for text generation using a RNN with eager execution. To the best of my understanding, this examples defines a simple RNN (with a GRU cell and a projection ...
2
votes
0answers
279 views

How to choose suitable Autoencoder (LSTM) architecture?

I am new to Autoencoders and I am a bit confused on which model to try for my situation and what is the difference between all the different models I have seen in tutorials. So, I have a set of time-...
2
votes
0answers
99 views

Neural network training: going backward to go forward?

I am working on CNN models which are intended to predict a protein's structure from its amino acid sequence. I have a decently large data set, 750 protein structures containing over 100,000 amino ...
2
votes
0answers
186 views

Training a bidirectional LSTM is unstable

I'm trying to solve timeseries classification problem. That's my model: ...
2
votes
1answer
318 views

How can I overfit a fully-connected neural network to predict RGB values from (x,y) coordinates?

The problem is the following: Given a single 3-channel image (e.g. 200x150), I constructed a dataset where the features are the pairs of (x,y) coordinates and the targets are the (R,G,B) values. Each {...
2
votes
0answers
115 views

LSTM - Learning a sinus function with linear part

I have recently build a simple LSTM-Network to predict a sinus function, which worked fine. Now I wanted to fit a sinus function containing a linear part with the same network but the results are ...
2
votes
2answers
475 views

How can I train my deep learning model on another similar yet different dataset

I am doing semantic segmentation (multi-class classification of image pixels) using convolutional neural networks (CNN) in Keras. In particular, I am applying this to aerial images of crops (...
2
votes
0answers
172 views

LSTM good at hallucinating, useless at ground truth prediction?

I was interested in this project, so I cloned it and trained it on Moby Dick, for this challenge. The goal is to predict the next character given the past ground-truth characters. Overfitting is not ...
2
votes
0answers
1k views

How to use Keras pre-trained 'Embedding' layer?

guys! I've trained model in keras using Embedding on specific corpus of articles. I use this tutorial http://adventuresinmachinelearning.com/word2vec-keras-tutorial/ Now I want use it as layer in my ...
2
votes
1answer
177 views

Classify the main semantic relation of a sentence using keras

I tried to ask in SO, but they told me to ask here. I have a big dataset like this: ...
2
votes
0answers
1k views

Adding weather forecast to RNN LSTM Keras for time series prediction

[worked on it for the last month] Assumptions: predicted value (demand for heat in a district heating system)(*) depends on: -weather -hour of the day -day of the week -past pattern (of the ...
2
votes
0answers
380 views

Sequence classification of binary vector with keras

I'm trying to classify a vector of 0s and 1s of arbitrary length. For that I'm sliding a window over the vector and use the subvector as input for a deep neural network. I would now like to improve ...
2
votes
0answers
74 views

How can I improve this basic Classification model? Have I implemented it correctly and validated the data?

I'm a student that is new to this field, I've played with the GUI version of Weka and made Neural Nets in that with premade datasets but now is the first time I've implemented one using Keras (Theano ...
2
votes
0answers
697 views

LSTM for classification

I have a dataset which consists of $n_\text{samples}$ different measurements. Each measurement contains $n_\text{features}$ features. These features are for example ...
1
vote
0answers
12 views

LSTM for multivariate time-series classification with unequal timesteps

I am attempting to use RNN or LSTM for multivariate time-series classification of my data. A sample corresponds to an actor, a time-step corresponds to an action and a single action consists of many ...
1
vote
0answers
41 views

Machine learning to select features to create predictive model

Sorry if this is a little confused! I am experimenting Forex data using keras to attempt to find phenomena that predicts a rise or fall in a forex symbol's price. My dataset is millions of prices per ...
1
vote
0answers
23 views

How to approach a multilabel classification problem where the proportions of the predicted labels matter?

My original task was to classify various cell types (the classes) based on gene expression patterns and this problem simply involves predicting one label from multiple classes. This was done easily ...
1
vote
0answers
11 views

Accuracy in DNN

How does number of batch size and steps per epoch affects the accuracy of the model? Edit: Training and validation accuracy both. I trained a model using CNN where the accuracy is changing relatively ...
1
vote
1answer
20 views

Understanding the output layer formation of an LSTM unit in Keras

I'm struggling to get my head around how the output shape of an LSTM layer formed. How is the output unit value physically implemented in the layer? For example, if I have an input shape of (128 x 6) ...
1
vote
0answers
21 views

NAN loss while training a image segmentation model with non-object images

I am currently working on a multi-class image segmentation application. A fraction of dataset contains images whose corresponding ground-truth images do not contain any object (completely black ...
1
vote
1answer
36 views

How to understand network neural network architecture from a research paper

Hello everyone I have the following architecture from the DELP-DAR research paper (https://www.sciencedirect.com/science/article/pii/S0167865519303216) and I dont really understand two things, first ...
1
vote
1answer
24 views

How to specify features that are common to all timesteps in a keras LSTM Model?

I am trying to build an LSTM model to predict temperature for a given day using say past 7 days of temperature, rainfall etc of a Zipcode or PinCode. I understand that the training dataset needs to be ...
1
vote
1answer
26 views

why does my model fluctuate on validation set and is smooth on the training set?

I use the below architecture in keras for dog-vs-cat dataset ...
1
vote
0answers
12 views

Implementing ICC in Keras model

I have a custom ResNet-50 that I am training with a set of 3D brain images to predict the category of atrophy in patients. However, the scale for categorization is a visual scale, as opposed to a ...
1
vote
0answers
16 views

Adam converges while SGD does not improve at all

I am trying to build a model based movie recommendation system with a neural network. The architecture looks as follows: ...
1
vote
1answer
34 views

Low memory time series input for deep learning

Background I have some data that looks like this: ...
1
vote
0answers
126 views

How to add a $\beta$ and capacity term to a variational autoencoder?

Vanilla variational autoencoders add a Kullback–Leibler divergence (KL) term to the loss function, i.e. the loss is a combination of the reconstruction error (e.g. cross entropy or MSE) and the KL ...
1
vote
0answers
27 views

My validation loss and binary accuracy has overshoots

I have built MLP network using 10 hidden layers I am seeing a lot of overshoots in the validation for loss and accuracy. Does anyone know why this is happening? I have 66 input variables and each ...
1
vote
0answers
17 views

Use LSTM to predict the proportion of steps with nonzero feature values

I am trying to do a simple regression for sequences. Each input $X_i$ is a $n=2000$ by 1 matrix, formatted as $n_i$ 0-s followed by $(n-n_i)$ 1-s. The output $y_i$ should be $n_i/n$, i.e. the ...
1
vote
1answer
100 views

CNN filters with different size using Keras

CNN can have multiple number of filters on raw input data. Normally I specify the number of filters needed as 'filters= 250 ' and the size of the filter as 'kernel_size= 3'. (This means I will make ...
1
vote
0answers
67 views

Tensorboard: Why does validation loss get evaluated after training loss stops?

When I monitor my model through Tensorboard, I notice that Tensorboard stops plotting the training loss but not the validation loss. Since the early stopping module, as I set it up below, is ...
1
vote
0answers
34 views

Tensorflow - simple multilayer perceptron not stabilizing around mean of normally distributed y-values

I'm building an FX trading model where I'm trying to predict the +/- movement of a currency pair 5 minutes into the future. I've had some promising results adapting the model as a classifier (i.e., ...
1
vote
0answers
124 views

How to update a keras LSTM weights to avoid Concept Drift

I´m trying to update a Keras LSTM to avoid the concept of drift. For that I´m following the approach proposed in this paper [1] on which they compute an anomaly score and they apply it to update the ...

1
2 3 4 5