All Questions
Tagged with autoencoder lstm
98 questions
0
votes
0
answers
40
views
Pytorch LSTM-VAE not able to learn
I have some problem to make a LSTM-VAE for anomalies detection on multivariate signals (no constant duration). I found some informations in this forum and original papers to apply good practices. Even,...
- 73
0
votes
0
answers
22
views
LSTM autoencoder very poor results
I am working on blockchain transaction anomaly detection system and testing various models. Currently I am stuck on a LSTM autoencoder. I have preprocessed transaction data from ethereum network (used ...
1
vote
0
answers
49
views
RuntimeError: shape '[1, 13, 13]' is invalid for input of size 13
I use LSTM-Autoencoder, took the model by this guy https://colab.research.google.com/drive/1_J2MrBSvsJfOcVmYAN2-WSp36BtsFZCa#scrollTo=vgUChGd_A-Bv,
for anomaly detection in time series
and got problem ...
- 11
0
votes
0
answers
956
views
LSTM inputs, different sequences with different lengths
I'm building a Recurrent Auto-encoder to make feature extraction on some time series sequences. All this sequences have different lengths and looking at different tutorials it seems that LSTM input ...
- 36
0
votes
1
answer
520
views
How do I get the Latent Space Representation from an LSTM based Autoencoder?
I'm trying to construct an encoder to get the latent space in order to plot it. I don't really know if I can get it from the RepeatVector or if I have to add a Dense layer.
Here is my code:
model = ...
- 3
0
votes
0
answers
183
views
Tensor Flow Error: required broadcastable shapes when training Variable Auto Encoder for Text Posts
Good morning,
I'm attempting apply and adapt a variational auto encoder that I found here to a dataset consisting of news headlines. The data will feed into the neural network, but the neural network ...
- 11
0
votes
1
answer
732
views
Using the LSTM layer in encoder in Pytorch
I want to build an autoencoder with LSTM layers. But, at the first step of the encoder, I got an error. Could you please help me with that?
Here is the model which I tried to build:
import numpy
...
- 730
1
vote
1
answer
459
views
LSTM Autoencoder set-up for multiple features using Pytorch
I am building an LSTM autoencoder to denoise signals and will take more than 1 feature as it's input.
I have setup the model Encoder part as follows which works for single feature inputs (i.e. ...
- 364
1
vote
0
answers
98
views
How to reconstruct the decoder from an LSTM-AE?
I have a trained LSTM-AE, of which the architecture is as follows:
In brief, I have an LSTM-AE of depth 3, the number of cells on the LSTM layers on the encoder side are [120, 80, 50] (and symmetric ...
- 95
2
votes
3
answers
2k
views
Training autoencoder for variant length time series - Tensorflow
I am trying to train a LSTM model to reconstruct time series data. I have a data set of ~1800 univariant time-series.
Basically I'm trying to solve a problem similar to this one Anomaly detection in ...
- 35
1
vote
0
answers
111
views
how to reshape inputs for sequence data in LSTM
I am trying to apply (LSTM + autoencoder) for anomaly detection on my sequential data having total of 64 days data , 3 months, and total 64 days, data is recorded for 24 hours a day. For clarity you ...
- 761
0
votes
1
answer
773
views
How to deal with dropout in between LSTM layers when using PackedSequence in PyTorch?
I'm creating an LSTM Autoencoder for feature extraction for my master's thesis. However, I'm having a lot of trouble with combining dropout with LSTM layers.
Since it's an Autoencoder, I'm having a ...
- 11
2
votes
1
answer
140
views
Why some of the hidden units return zero in the GRU autoencoder?
I have implemented a recurrent neural network autoencoder as below:
def AE_GRU(X):
inputs = Input(shape=(X.shape[1], X.shape[2]), name="input")
L1 = GRU(8, activation="relu"...
- 183
0
votes
0
answers
122
views
How to mix continuous and discrete categorical signals in LSTM-Autoencoder or other anomaly detection methods?
I want to detect anomalies in a system that includes continuous data as well as some switches and other sources giving categorical input. Something like:
sensor signals (speed, angle,etc.)
controller ...
2
votes
1
answer
623
views
LSTM autoencoder noisy reconstruction
I am trying to build an LSTM autoencoder for the compression of time series (currently only one dimensional, but could also be for multiple dimensions).
A little bit of context first:
I am developing ...
- 31