Stack Overflow
Stack Overflow

Questions tagged [seq2seq]

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

318 questions
2
votes
1 answer

InvalidArgumentError: Received a label value of 8825 which is outside the valid range of [0, 8825) SEQ2SEQ model

I have been trying to build RNN with Seq2Seq model from Udemy course called DeepLearning_NLP_Chatbot, and I followed him step by step, but I face when training an error: InvalidArgumentError: Received a label value of 8825 which is outside the valid…
Mohamad Alsharbaji
  • 23
  • 7
2
votes
1 answer

Confused about multi-layered Bidirectional RNN in Tensorflow

I'm building a multilayered bidirectional RNN using Tensorflow .I'm a bit confused about the implementation though . I have built two functions that creates multilayered bidirectional RNN the first one works fine , but I'm not sure about the…
mousa alsulaimi
  • 316
  • 1
  • 14
2
votes
2 answers

Install seq2seq on google colaboratory

I have installed seq2seq on google colab but when I want to import it I get the error: **no module named "seq2seq"** When I run: !python3 drive/app/seq2seq-master/setup.py build !python3 drive/app/seq2seq-master/setup.py install import…
hadeer
  • 19
  • 7
2
votes
0 answers

alternative for tf.contrib.seq2seq.prepare_attention() in tensorflow version 1.8

AttributeError: module 'tensorflow.contrib.seq2seq' has no attribute 'prepare_attention' I know that the prepare_attention() has been deprecated. What is the alternative for this? And also please specify the syntax also. the function I'm using…
SUMANTH DODDAPANENI
  • 21
  • 3
2
votes
0 answers

Subfunction variables not saving in tensorflow

I have a decoder function which contains a subfunction that runs an iterative summation across an input 2D Tensor and an 2xn shaped variable. This summation function works properly during training, however the variables that are used in the function…
Arya Vohra
  • 71
  • 1
1
vote
0 answers

Avoid printing 'Generate config GenerationConfig { ... }'

I am facing an issue while training a t5 model. After each evaluation step, the following message is printed, which makes it impossible to maintain an overview. Do you have any ideas, on how I can avoid such behavior? ***** Running Evaluation *****…
good_guy_from_ozzi
  • 11
  • 2
1
vote
0 answers

what should be the value of the "input_lenghts" in "forward function" in encoder rnn in seq2seq model

i'm training an encoder rnn for sequence to sequence model with batches of 10 sentences . every batches have 10 sentences. and every sentences have 60 words. in the encoder network of the seq2seq model what should be the value of the…
mahdi
  • 13
  • 2
1
vote
1 answer

loss is drastically decreasing whereas BLEU score stays at zero during training of the seq2seq RNN for machine translation

I'm trying to train an RNN for machine translation, using LSTM. However,the BLEU at the first batch decreases to zero and stay at this level during all the training. At the same time loss is drastically decreasing. What may be the problem? **the…
Haski
  • 11
  • 1
1
vote
0 answers

ROUGE-1.5.1.pl problem when train seq2seq model

It is a problem about seq2seq-summarizer. ( more details see)I run these codes on Google colab. I just train it one epoch,and it returns an error. the imformation about the error and I download ROUGE-1.5.5.pl from network and I just put this file…
taro
  • 11
  • 3
1
vote
0 answers

What is “Ensemble of 5 reversed LSTMs” in seq2seq

While reading the seq2seq paper (Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. Advances in neural information processing systems, 27.), the authors said they used a 4-layer LSTMs in section 3.4…
dd123
  • 11
  • 1
1
vote
1 answer

Keras seq2seq model Output Shapes

I am working on keras seq2seq example here:https://blog.keras.io/a-ten-minute-introduction-to-sequence-to-sequence-learning-in-keras.html What I have understood from the text is in decoder model each cell's output is input to the next cell. However…
samatra
  • 15
  • 4
1
vote
1 answer

TypeError: from_pretrained() got an unexpected keyword argument 'file_name'

I'm trying to quantize a seq2seq model (M2M100) using optimum library provided by Huggingface. As per this guide, I'm trying to quantize the encoder and decoder one by one but that requires me to overwrite the model name. Following the documentation…
Arnav Saxena
  • 21
  • 1
  • 5
1
vote
0 answers

ValueError: Shapes (None, 16) and (None, 16, 16) are incompatible (LSTMs)

I am building a English to Hindi translation model and I keep getting this error. I am still new to this so I couldn't figure out my error. I used the encoder-decoder model and i still have to build the inference model for decoder. I referred my…
Akshat Mittu
  • 11
  • 1
  • 1
1
vote
0 answers

Calculate F-score for GEC

I am working on Sequence to Sequence encoder-decoder model with bidirectional GRU for the task of grammar error detection and correction for Arabic language. I want to calculate the F0.5 score for my model. This is how my data divided: train_data,…
Moodhi
  • 45
  • 3
1
vote
0 answers

Getting shape dimension error during Concatenation while employing Attention to my seq2seq model?

I'm trying to implement my own seq2seq model and employ the widely recommended attention layer on it. Oddly getting an error during the concatenation like below. You can reach the whole Python code from here. (I could not share it here as it was too…
talha06
  • 6,206
  • 21
  • 92
  • 147
1 2 3
…
21 22