Stack Overflow
Stack Overflow

Questions tagged [textsum]

31 questions
7
votes
1 answer

How to use textsum?

I've been following this link to use textsum. I've trained the model using the command provided. But I don't see any folder 'train' in 'textsum/log_root/' directory. Since training is made on a sample file, will the model be able to work on real…
Selva Saravana Er
  • 199
  • 1
  • 1
  • 6
5
votes
1 answer

Tensorflow text summarization setup : What is a workspace file?

Reading the Tensorflow text summarization documentation setup : https://github.com/tensorflow/models/tree/master/textsum it states clone the code to your workspace and create empty WORKSPACE file. I've created a new folder and cloned…
blue-sky
  • 51,962
  • 152
  • 427
  • 752
4
votes
1 answer

textsum beam search decoder gives all results

I have been testing textsum with both the binary data and gigaword data, trained models and tested. The beam search decoder gives me all 'UNK' results with both set of data and models. I was using the default parameter settings. I first changed the…
Rui
  • 41
  • 2
3
votes
1 answer

Is this the correct guide for tensorflow text summarization?

Reading the tensorflow text summarization model it states "The results described below are based on model trained on multi-gpu and multi-machine settings. It has been simplified to run on only one machine for open source purpose." Further in the…
blue-sky
  • 51,962
  • 152
  • 427
  • 752
2
votes
0 answers

How to implement pretrained tensorflow textsum model in android?

I have seen many examples of image Classification using tensorflow in android but didn't find any example to implement TEXTSUM model of tensorflow in android.
dhrumit patel
  • 21
  • 5
2
votes
0 answers

Tensorflow -Textsum error when retraining the model

Whenever I retrain the textsum model, it gives the following error: InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [35313] rhs shape= [35314]" exist. I am using the same command line for training as provided on…
user7795805
  • 21
  • 2
2
votes
2 answers

How much time it will take to train with sample data(toy sample data) for tensorflow textsum?

I am working on tensorflow's textsum (text summarization model). I have put it on run to train the model with the sample data i.e. toy dataset provided with the model while cloning from git. I wanted to know that how much time it will take to train…
Kajal Kodrani
  • 21
  • 1
  • 3
2
votes
0 answers

TensorFlow TextSum decode error: Could not flatten dictionary

I try to run TensorFlow textsum model Training went well, but when I try to run "decode" mode using toy data provided by authors of the model, I get this error: Traceback (most recent call last): File…
Pavel Surmenok
  • 4,584
  • 4
  • 30
  • 33
2
votes
0 answers

Running tensorflow summarisation service with docker instance

Can the tensorflow summarisation model be invoked using the tensorflow docker instance? The documentation for the model refers to using bazel build as part of the steps for building the model. But running the tensorflow docker container does not…
blue-sky
  • 51,962
  • 152
  • 427
  • 752
1
vote
0 answers

ValueError: Exception encountered when calling layer "lstm_2" (type LSTM)

I made model for text summarization with BLSTM architecture and global Attention, I have x_vocab_size = 36782 and y_vocab_size = 19749 For the full model i've made : latent_dim = 300 # Encoder encoder_inputs = Input(shape=(None,), dtype='int32',…
Ronald Ferdinand
  • 37
  • 8
1
vote
2 answers

Tensorflow textsum error of Versioning

I am trying to convert the training text file to bin file for training the textsum of tensorflow. But I encountered the following error: $ python textsum/data_convert_example.py --command text_to_binary --in_file data/tt.txt --out_file…
Jaffer Wilson
  • 7,029
  • 10
  • 62
  • 139
1
vote
1 answer

Interpreting textsum decode files (more output than input?)

I'm running textsum decoding on a small test set (5 examples), but both the reference and decode files are already thousands of lines long. Is there a reason decoding runs seemingly indefinitely? Is it processing the same set of examples repeatedly?…
hate5six
  • 11
  • 3
1
vote
1 answer

Which file to be used for eval step in TEXTSUM?

Am working on the texsum model of tensorflow which is text summarization. I was following commands specified in readme at github/textsum. It said that file named validation, present in data folder, is to be used in eval step, but there was no…
Ayushya
  • 9,599
  • 6
  • 41
  • 57
1
vote
1 answer

How to detect if textsum training is overfitting?

I am using Tensorflow 0.9 and training with the Textsum model. I have about 1.3 million articles that I scraped and have been training against them for about a week now. The average loss was about 1.75 - 2.1. I decided to stop and run eval as it is…
xtr33me
  • 936
  • 1
  • 13
  • 39
1
vote
1 answer

Textsum - Incorrect decode results compared to ref file

This issue is seen when performing training against my own dataset which was converted to binary via data_convert_example.py. After a week of training I get decode results that don't make sense when comparing the decode and ref files. If anyone has…
xtr33me
  • 936
  • 1
  • 13
  • 39
1
2 3