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
0 answers

How can I get the word2vec.bin file

I want to build a chatbot using python and deeplearning methodology.Iam referring the below link chatbot code But I troubled in the word2vec.bin file as describing in the code.Where should I get the bin file?
Pradeep
  • 21
  • 5
0
votes
1 answer

NMT, tensorflow, error with NotFoundError

I'm using tensorflow to implement nmt https://www.tensorflow.org/versions/master/tutorials/seq2seq#sequence-to-sequence-models I am going to create NMT for Korean and English. I created my data similar to that provided by Tensorflow. Corresponds to…
Jiwon Kim
  • 139
  • 3
  • 12
0
votes
1 answer

Tensoflow seq2seq decoder does not work

I'm trying to follow the seq2seq example in https://www.tensorflow.org/tutorials/seq2seq but with the difference being is that my inputs and outputs are real continuous values as opposed to words in the example. I have two tensors X and Y which are…
vmontazeri
  • 393
  • 2
  • 20
0
votes
1 answer

Which kind of regularization use L2 regularization or dropout in multiRNNCell?

I have been working on a project related with sequence to sequence autoencoder for time series forecasting. So, I have used tf.contrib.rnn.MultiRNNCell in encoder and decoder. I am confused in which strategy used in order to regularize my seq2seq…
dnovai
  • 137
  • 1
  • 8
0
votes
1 answer

Is it valid to use if else condition in the tensorflow graph?

I have been recently working on tensorflow. I am coding seq2seq model. I am in the process of writing a condition to select the helper provided by the API. When i am using following code i am facing the error. Training Helper helper1 =…
lifeisshubh
  • 513
  • 1
  • 5
  • 27
0
votes
1 answer

Reusing Embedding Variable For Inference in the Tf.Estimator API

In NMT using seq2seq architecture, during inference, we need the embedding variable trained during the training phase as an input to the GreedyEmbeddingHelper or the BeamSearchDecoder. The question is, within the context of training and inferring…
cad86
  • 125
  • 8
0
votes
1 answer

Use tf.contrib.legacy_seq2seq.embedding_rnn_seq2seq with tensorflow 1.5 case 'TypeError: can't pickle _thread.lock objects'

Use tf.contrib.legacy_seq2seq.embedding_rnn_seq2seq with tensorflow 1.5 case 'TypeError: can't pickle _thread.lock objects', this issue is the same as https://github.com/suriyadeepan/practical_seq2seq/issues/31 I use the way someone post: change the…
eagle A
  • 107
  • 8
0
votes
3 answers

Tying weights in neural machine translation

I want to tie weights of the embedding layer and the next_word prediction layer of the decoder. The embedding dimension is set to 300 and the hidden size of the decoder is set to 600. Vocabulary size of the target language in NMT is 50000, so…
Wasi Ahmad
  • 35,739
  • 32
  • 114
  • 161
-1
votes
0 answers

How to fine tune GODEL-v1_1-base-seq2seq?

I can't find enough information on how to fine tune model microsoft/GODEL-v1_1-base-seq2seq on certain dialogs. Maybe someone can tell me more? What should the training data look like? How do the instruction, knowledge, dialog fields work? How to…
Artem M
  • 1
-1
votes
1 answer

Tensorflow ValueError: No gradients provided for any variable:

I was trying to do a custom loss function but I get the error. This is supposed to be cyclegan for text This is the loss function: def sloss(ytrue, ypred): nump = 0 print(nump) for i in range(len(ypred[0])): if int(round(ypred[0][i])) !=…
Spock 360
  • 9
-1
votes
1 answer

How can I use legacy_seq2seq.embedding_rnn_seq2seq in tensorflow?

The problem is i am unable to find seq2seq in new tensorflow library Here's the code- decoderOutputs, states = tf.legacy_seq2seq.embedding_rnn_seq2seq( self.encoderInputs, # List<[batch=?, inputDim=1]>, list of size…
Kritharth Singh
  • 1
-1
votes
1 answer

ValueError: Dimensions must be equal, but are 13 and 3076 for 'loss/dense_1_loss/mul' (op: 'Mul') with input shapes: [?,13], [?,13,3076]

I am building a chatbot on top of seq2seq model. There's an error with dimensions. Please help. This is the .py file :https://drive.google.com/drive/u/0/folders/1ljeLb_LYO6qd9azqly31T3luv0oACXfO import re lines = open('movie_lines.txt', encoding =…
PUSHKAR KUDLIKAR
  • 1
-1
votes
1 answer

Is this a valid seq2seq lstm model?

Hello I am trying to build a seq2seq model to generate some music. I really dont know much about it though. On the internet I have found this model: def createSeq2Seq(): #seq2seq model #encoder model = Sequential() …
Daniel Casasampera
  • 351
  • 7
  • 20
-1
votes
1 answer

How to pad sequences during training for an encoder decoder model

I've got an encoder-decoder model for character level English language spelling correction, it is pretty basic stuff with a two LSTM encoder and another LSTM decoder. However, up until now, I have been pre-padding the encoder input sequences, like…
hhaefliger
  • 521
  • 3
  • 18
-1
votes
1 answer

How to evaluate inference accuracy for seq2seq video captionnig model?

I've built a video captionnig model. It consists of a Seq2seq model, taking video as input and outputting natural language I obtain really good test results but horrible inference results: Epoch 1 ; Batch loss: 5.181570 ; Batch accuracy: 60.28% ;…
wakobu
  • 318
  • 1
  • 11
1 2 3
…
21
22