Stack Overflow
Stack Overflow

Questions tagged [seq2seq]

Seq2Seq is a sequence to sequence learning add-on for the python deep learning library.

318 questions
1
vote
1 answer

When to use RNN or LSTM

What is the difference between RNNs and LSTMs and when do we use either of these models?
subho
  • 491
  • 1
  • 4
  • 13
1
vote
1 answer

How to convert checkpoint to .pb model for model deployment?

I have trained a seq2seq language translation model on tensorflow and save in the form of checkpoints with the following files in my train folder. translate.ckpt-157450.data-00000-of-00001 translate.ckpt-157450.index translate.ckpt-157450.meta…
Sandeep
  • 369
  • 1
  • 5
  • 16
1
vote
0 answers

In Seq2Seq tasks, could bidirectional RNN(LSTM, GRU) be decoder?

In the decoder part of Seq2seq, it is like a language modeling to be given an input word and the hidden state, to predict the next word. How bidirectional information could be used in this mechanism? Also, is that we also have to generate sentence…
温志远
  • 11
  • 2
1
vote
1 answer

Where to place and tags in seq2seq translations?

I went through a number of tutorials where the answer to my question was different. So, for seq2seq model ( English to French translation ), I have encoder_input_data which has English phrases without and tags. I am confused with the…
Shubham Panchal
  • 4,061
  • 2
  • 11
  • 36
1
vote
0 answers

How to connect multi-layered Bi-directional LSTM encoder to a decoder?

I'm making a seq2seq model which uses a Bi-LSTM as encoder and Attention mechanism in decoder. For a single layer of LSTM model is working fine. My encoder looks something like this. Encoder: def encoding_layer(self, rnn_inputs, rnn_size,…
h s
  • 404
  • 1
  • 5
  • 17
1
vote
2 answers

Need advice in seq2seq model implementation

I am implementing seq2seq model for text summerization using tensorflow. For encoder I'm using a bidirectional RNN layer. encoding layer: def encoding_layer(self, rnn_inputs, rnn_size, num_layers, keep_prob, …
h s
  • 404
  • 1
  • 5
  • 17
1
vote
0 answers

Am I applying embedding layer in seq2seq correctly in inference model?

I am new to NLP and Keras and am still learning. I tried to follow this guide: https://blog.keras.io/a-ten-minute-introduction-to-sequence-to-sequence-learning-in-keras.html and have added an embedding layer. I am using fra2eng dataset. However, I…
zheng rong
  • 11
  • 2
1
vote
0 answers

Why is simple seq2seq in pytorch always returning NaN?

I have the following trimmed down model: import torch.nn as nn import torch import argparse import torch import torch.utils.data from torch import nn, optim from torch.autograd import Variable from torch.nn import functional as F from torchvision…
lightning
  • 389
  • 1
  • 9
1
vote
0 answers

tensorflow Seq2seq model: inference result is totally different from expected

I tried to use seq2seq model with attention handling video caption problem. You may aware theres no updated version of using new(1.40+ version) tensorflow to do this. I just rewrite the whole thing. To implement attention, I just tried "Luong" and…
Derek Wang
  • 11
  • 2
1
vote
0 answers

Tensorflow GPU Out Of Memory during runtime using dynamic_rnn

I'm having trouble training a seq2seq model using Tensorflow on an Nvidia P100 GPU. Here are the versions I'm using: TensorFlow 1.10.0, Keras 2.2.2, Python 3.6.3, CUDA 9.2.148.1, cuDNN 7.2.1 I currently get an OOM error well in the middle of…
aquaktus
  • 11
  • 2
1
vote
0 answers

Training with tensorflow seq2seq model

I am currently working with lstm. I have a dataset of a number of sentences about transactional info and I want to extract information, suppose amount, date and transactionWith. I already tried with basic lstm where my system tried to predict each…
Shehab Ahmed Sayem
  • 127
  • 2
  • 8
1
vote
0 answers

What is the use of attention_layer_size?

I am following a code to learn the seq2seq API. I am unable to figure out what the attention_layer_size parameter is for and why is it set to num_units/2
Raghuram Vadapalli
  • 1,190
  • 2
  • 13
  • 27
1
vote
0 answers

Tensorflow Beamsearch Decoder unable to decode the value

I am trying to code seq2seq example with Tensorflow with Beam Search and Attention. Till now I have found no concrete example which explains the both the decoding and/or attention together using current tf version. Either the previous versions have…
gaurus
  • 426
  • 1
  • 4
  • 16
1
vote
1 answer

In Tensorflow I can't use any MultiRNNCell instance in dynamic decode, but a single RNNCell instance can work on it

I make a seq2seq model using tensorflow and meet a problem that my program throws an error when I use MultiRNNCell in tf.contrib.seq2seq.dynamic_decode. The problem happens over here: defw_rnn=tf.nn.rnn_cell.MultiRNNCell([ …
Zyzy
  • 11
  • 2
1
vote
0 answers

Concatenate encoder hidden states/cells/outputs from different sources for attention calculation - issues?

I am using Pytorch for an LSTM encoder-decoder sequence-to-sequence prediction problem. As a first step, I would like to forecast 2D trajectories (trajectory x, trajectory y) from multivariate input - 2-D or more (trajectory x, trajectory y, speed,…
user3530347
  • 11
  • 2
1 2 3
…
21 22