Top "Lstm" questions

Long short-term memory.

Tensorflow InvalidArgumentError (indices) while training with Keras

I'm trying to train a LSTM network on some data, unfortunately I keep running into following error: InvalidArgumentError: indices[] = is …

python tensorflow keras lstm one-hot-encoding
How to train an lstm for speech recognition

I'm trying to train lstm model for speech recognition but don't know what training data and target data to use. …

tensorflow speech-recognition keras speech-to-text lstm
Keras - stateful vs stateless LSTMs

I'm having a hard time conceptualizing the difference between stateful and stateless LSTMs in Keras. My understanding is that at …

tensorflow deep-learning keras lstm
Multi layer RNN with LSTM in Tensorflow

I have coded a single layer RNN with LSTM in Tensorflow (ver 1.5) by Python (ver 3.6). I would like to add 3 …

python-3.x tensorflow lstm recurrent-neural-network multi-layer
Using Keras for video prediction (time series)

I want to predict the next frame of a (greyscale) video given N previous frames - using CNNs or RNNs …

machine-learning neural-network time-series keras lstm
Bidirectional LSTM output question in PyTorch

Hi I have a question about how to collect the correct result from a BI-LSTM module’s output. Suppose I …

machine-learning neural-network deep-learning lstm pytorch
How to connect LSTM layers in Keras, RepeatVector or return_sequence=True?

I'm trying to develop an Encoder model in keras for timeseries. The shape of data is (5039, 28, 1), meaning that my seq_…

tensorflow keras deep-learning lstm autoencoder
Siamese Neural Network in TensorFlow

I'm trying to implement a Siamese Neural Network in TensorFlow but I cannot really find any working example on the …

neural-network tensorflow deep-learning lstm
TensorFlow: How to use CudnnLSTM with variable input length (like dynamic_rnn)?

I would like to speed up my LSTM network, but as I am using it for a OCR (where sequences …

tensorflow lstm cudnn
Why do I get a Keras LSTM RNN input_shape error?

I keep getting an input_shape error from the following code. from keras.models import Sequential from keras.layers.core …

python time-series deep-learning keras lstm