Stack Overflow
Stack Overflow

Questions tagged [encoder-decoder]

184 questions
2
votes
0 answers

Keras Looping LSTM layers

I am trying to build a model which is basically sequence to sequence model but i have a special encoder namely "Secondary Encoder". Timesteps in Secondary Encoder = 300 this encoder has a special property, in essence it is a GRU, but at each…
Harsh
  • 21
  • 2
2
votes
0 answers

How to generate sequence correctly with encoder-decoder lstm?

I am implementing some code to generate labeled data for Natural Language Understanding (NLU) from the article "Labeled Data Generation with Encoder-decoder LSTM for Semantic Slot Filling"…
Daniel Martin Arteaga Melendez
  • 21
  • 1
2
votes
0 answers

inference model predicts same words repeatedly in encoder-decoder

I'm training encoder-decoder with LSTM, for generating abstractive review summaries on Amazon Kindle dataset. For every input the output summaries are slightly different but they generate a couple of words repeatedly. I have tried a random…
neha tamore
  • 181
  • 1
  • 1
  • 8
2
votes
1 answer

Transformer based decoding

Can the decoder in a transformer model be parallelized like the encoder? As far as I understand the encoder has all the tokens in the sequence to compute the self-attention scores. But for a decoder this is not possible (in both training and…
shiredude95
  • 560
  • 3
  • 7
2
votes
1 answer

Some parameters are not getting saved when saving a model in pytorch

I have built an encoder-decoder model with attention for morph inflection generation. I am able to train the model and predict on test data but I am getting wrong predicting after loading a saved model I am not getting any error during saving or…
Umang Jain
  • 21
  • 5
2
votes
1 answer

Inputs to Encoder-Decoder LSTMCell/RNN Network

I'm creating an LSTM Encoder-Decoder Network, using Keras, following the code provided here: https://github.com/LukeTonin/keras-seq-2-seq-signal-prediction. The only change I made is to replace the GRUCell with an LSTMCell. Basically both the…
Brindha Kanniah
  • 119
  • 1
  • 1
  • 7
2
votes
0 answers

Graph disconnect in inference in Keras RNN + Encoder/Decoder + Attention

I've successfully trained a model in Keras using an encoder/decoder structure + attention + glove following several examples, most notably this one and this one. It's based on a modification of machine translation. This is a chatbot, so the input is…
a1orona
  • 21
  • 2
2
votes
3 answers

How to save Tensorflow encoder decoder model?

I followed this tutorial about building an encoder-decoder language translation model and built one for my native language. Now I want to save it, deploy on cloud ML engine and make predictions with HTTP request. I couldn't find a clear example on…
UpaJah
  • 6,954
  • 4
  • 24
  • 30
2
votes
1 answer

How is the decoder conditioned in seq2seq learning?

I am trying to understand sequence-to-sequence learning with a RNN. What I understand so far, is that the output of the encoder is used to condition the decoder. Yet, I have two sources which, in my opinion, do the conditioning differently and I…
lwi
  • 1,682
  • 12
  • 21
2
votes
1 answer

Output of DecoderRNN contains extra dimensions

I have developed an Encoder(CNN)-Decoder (RNN) network for image captioning in pytorch. The decoder network takes in two inputs- Context feature vector from the Encoder and the word embeddings of the caption for training. The context feature vector…
Vineet Pandey
  • 1,386
  • 2
  • 9
  • 12
2
votes
0 answers

An error was encountered when setting batch_size to 1 in sequence_to_sequence_implementation.ipynb（when batch_size > 1,it 's ok）

reference: https://github.com/udacity/deep-learning/blob/master/seq2seq/sequence_to_sequence_implementation.ipynb setting: encoding_embedding_size=decoding_embedding_size = 200 error info: Traceback (most recent call last): File…
melody
  • 59
  • 4
2
votes
1 answer

How to use Tensorflow v1.1 seq2seq.dynamic_decode?

I am trying to use seq2seq.dynamic_decode from Tensorflow to build a sequence to sequence model. I have already finished the encoder part. I am confused about the decoder as decoder_outputs seems to return [batch_size x sequence_length x…
dparted
  • 395
  • 1
  • 2
  • 15
2
votes
1 answer

Adding multiple convolutional layers reduces accuracy in encoder-decoder model

I'm working on an implementation of SegNet in TensorFlow, that I am using to segment aerial images into two classes: "Building" and "Not building". I have a small version of the network, which gives accuracy up to 82% mIoU. However, I wanted to…
Mathilde O
  • 41
  • 3
1
vote
0 answers

Huggingface Translate Pipe with custom BeamScorer

I want to generate a sentence from a machine translation model with constrained decoding that requires a custom BeamScorer. Is there a way how to replace the standard BeamSearchScorer while using the high-level API such as the Translate pipeline or…
Jindřich
  • 10,270
  • 2
  • 23
  • 44
1
vote
0 answers

Output of extracted Huggingface decoder does not have attribute logits

I am trying to build a video-to-text model using a Huggingface VisionEncoderDecoderModel. For the encoder, I'm using VideoMAE. Because the sequence length for videos is long, I want to use the decoder from Longformer Encoder-Decoder (LED). Because…
jeg
  • 51
  • 6
1 2
3
…
12 13