Stack Overflow
Stack Overflow

Questions tagged [seq2seq]

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

318 questions
0
votes
1 answer

Decoder targets required for RNN inference

I have been trying to run some experiments using the deepfix tool (https://bitbucket.org/iiscseal/deepfix) which is a seq2seq model for correcting common programming errors. I made changes to the code so that it is compatible to TF-1.12, as the…
Shivam Mittal
  • 1
  • 2
0
votes
0 answers

Embedding version seq2seq model (Keras)

I want to build up an embedding version seq2seq model by modifying the example on keras github. https://github.com/keras-team/keras/blob/master/examples/lstm_seq2seq.py I've tried the np.reshape but it won't work. from keras.layers.embeddings…
jjlin
  • 39
  • 5
0
votes
0 answers

Keras seq2seq example save issue

. Hello everyone! I just tried keras seq2seq example(link). It works well, but the problem happens when I try to save the trained model. I had never fixed the code. Is there anyone who already know about this issue? Please help…
INDI
  • 43
  • 7
0
votes
0 answers

Tensorflow - Seq2Seq model weights are not loaded properly

I am working on an encoder-decoder chat bot that consists of an embedding layer, two layers of LSTM and a fully connected layer on top of the decoder. After I load the checkpoint file, the loss is way higher than it was the last time I saved the…
liellahat
  • 1
  • 3
0
votes
0 answers

How to implement attention for sequence to sequence model in keras. Please explain step by step

How to implement attention for a sequence to sequence model in keras. I understand this seq2seq model, but I want to do attention with Fig B (shown in the attached link seq2seq). Please explain step by step.
Mr.Beans
  • 1
  • 2
0
votes
1 answer

Saved tensorflow NLP model outputs nothing after restoring saved variables for training

I built a seq2seq model for a chatbot after getting inspired by a github repo. To train the chatbot I used my facebook chat history. Since most of my chat is like hindi words written in english language. I had to train word embedding from scratch. I…
Mohit Saini
  • 21
  • 1
  • 8
0
votes
1 answer

implement Attention mechanism in seq2seq Maluuba model

Hello, i'm trying to add an attention to simple Maluuba/qgen-workshop seq2seq model but i can not figure out what is the correct batch_size i should pass to the initial state i tried this: # Attention # attention_states: [batch_size, max_time,…
Mekasa
  • 1
0
votes
1 answer

tf.nn.rnn_cell.GRUCell were built on CPU device

I'm training a 2-layer seq2seq model now and gru_cell is used. def create_rnn_cell(): encoDecoCell = tf.contrib.rnn.GRUCell(emb_dim) encoDecoCell = tf.contrib.rnn.DropoutWrapper( …
Ming
  • 1
  • 1
0
votes
1 answer

Tensorflow: Attention output gets concatenated with the next decoder input causing dimension missmatch in seq2seq model

[TF 1.8] I'm trying to build a seq2seq model for a toy chatbot to learn about tensorflow and deep learning. I was able to train and run the model with sampled softmax and beam search but then I try to apply tf.contrib.seq2seq.LuongAttention using…
Sea Otter
  • 73
  • 1
  • 6
0
votes
0 answers

Pytorch Spell Check Character RNN not outputting end tokens

I’m trying to implement a character RNN for the purpose of spell correction and tokenization. The model is based on the practical pytorch GRU-RNN implementation of a seq2seq model - the loss function is masked cross entropy like they use here and…
E Holm
  • 1
0
votes
1 answer

Seq2seq for non-sentence, float data; stuck configuring the decoder

I am trying to apply sequence-to-sequence modelling to EEG data. The encoding works just fine, but getting the decoding to work is proving problematic. The input-data has the shape None-by-3000-by-31, where the second dimension is the…
MPKenning
  • 569
  • 1
  • 7
  • 22
0
votes
2 answers

why do we reverse input when feeding in seq2seq model in tensorflow( tf.reverse(inputs,[-1]))

Why do we reverse input when feeding in seq2seq model in tensorflow ( tf.reverse(inputs,[-1])) training_predictions,test_predictions=seq2seq_model(tf.reverse(inputs,[-1]), targets, …
music in air
  • 1
  • 2
0
votes
0 answers

Multi-step Time Series Prediction w/ seq2seq LSTM

I am trying to predict time series data using an encoder/decoder with LSTM layers. So far, I am using 20 points of past data to predict 20 future points. For each sample of 20 past data points, the 1st value in the predicted sequence is very close…
Kunal Singh
  • 1
0
votes
1 answer

pytorch seq2seq encoder forward method

I'm following Pytorch seq2seq tutorial and below is how they define the encoder function. class EncoderRNN(nn.Module): def __init__(self, input_size, hidden_size): super(EncoderRNN, self).__init__() self.hidden_size =…
aerin
  • 20,607
  • 28
  • 102
  • 140
0
votes
1 answer

Encoder returning same states for every input Keras seq2seq

I am using an Encoder Decoder seq2seq architecture in Keras, I'm passing a one-hot array of shape (num_samples, max_sentence_length, max_words) for training, and using teacher forcing. #Encoder latent_dim = 256 encoder_inputs = Input(shape=(None,…
Arth Dh
  • 11
  • 5
1 2 3
…
21 22