Giter Site home page Giter Site logo

Cannot replicate about deep-text-corrector HOT 15 OPEN

atpaino avatar atpaino commented on August 22, 2024
Cannot replicate

from deep-text-corrector.

Comments (15)

qinbill avatar qinbill commented on August 22, 2024 1

Problem fixed. Please see my fork.

from deep-text-corrector.

essamgoda avatar essamgoda commented on August 22, 2024

hi @braindead i have problem in training
it show error

batched_corrective_tokens = tf.pack(
AttributeError: 'module' object has no attribute 'pack'

in file

text_corrector_models.py line 91

tensorflow V 1.0.0

from deep-text-corrector.

xushenkun avatar xushenkun commented on August 22, 2024

@braindead I also get this kind of results. Have you solved it?
@essamgoda You should use stack instead of pack.

from deep-text-corrector.

essamgoda avatar essamgoda commented on August 22, 2024

another error show

@xushenkun

TypeError: Input 'y' of 'Mul' Op has type float32 that does not match type int32 of argument 'x'.

from deep-text-corrector.

derofim avatar derofim commented on August 22, 2024

@essamgoda Maybe change labels and inputs, as in in API https://www.tensorflow.org/versions/r1.1/api_docs/python/tf/nn/sampled_softmax_loss
def sampled_loss(labels, inputs): labels = tf.reshape(labels, [-1, 1]) return tf.nn.sampled_softmax_loss(w_t, b, labels, inputs, num_samples, self.target_vocab_size)

another error "Ran out of memory"

File "correct_text.py", line 434, in main
   train(data_reader, FLAGS.train_path, FLAGS.val_path, FLAGS.model_path)
 File "correct_text.py", line 181, in train
   target_weights, bucket_id, False)
 File "text_corrector_models.py", line 297, in step
   outputs = session.run(output_feed, input_feed)

Command used:
python correct_text.py --train_path "./data/movie_dialog_train.txt" --val_path "./data/movie_dialog_val.txt" --config DefaultMovieDialogConfig --data_reader_type MovieDialogReader --model_path "./movie_dialog_model"

Used data and source code:
https://www.dropbox.com/s/oo7e9vg5hcrnjke/deep-text-corrector-master.rar?dl=0

from deep-text-corrector.

essamgoda avatar essamgoda commented on August 22, 2024

@derofim thanks alot it's worked

your code worked (take a long time)

try to reduce number of layer and size if your resource is limited i use gpu ( Nvidia 940 mx 4 gb)

from deep-text-corrector.

essamgoda avatar essamgoda commented on August 22, 2024

@braindead @xushenkun the same error did you solve it ?

from deep-text-corrector.

liuyichaosoftware avatar liuyichaosoftware commented on August 22, 2024

@essamgoda hi, how much steps have you trained? when I run 20000 times in half an hour, it showed....

Input: you must have girlfriend
Output: girlfriend girlfriend girlfriend girlfriend girlfriend girlfriend girlfriend girlfriend girlfriend girlfriend

from deep-text-corrector.

essamgoda avatar essamgoda commented on August 22, 2024

@liuyichaosoftware I also run 20000 times

from deep-text-corrector.

bittlingmayer avatar bittlingmayer commented on August 22, 2024

Same here.

from deep-text-corrector.

HarshdeepGupta avatar HarshdeepGupta commented on August 22, 2024

@braindead @essamgoda
I am having the same issues with the model. Did you eventually solve it? Or is it unsolvable?

from deep-text-corrector.

arianpasquali avatar arianpasquali commented on August 22, 2024

@braindead @essamgoda @HarshdeepGupta
I have the same kind of output here:

na na na na na na na na na na
what what what what what what what what what what
gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim gim
... ... ... ... ... ... ... ... ... ...
up up up up up up up up up up
ya ya ya ya ya ya ya ya ya ya ya ya ya ya ya

I didnt change parameters. I also run 20000 times.
Did anyone eventually manage to get expected results?

from deep-text-corrector.

arianpasquali avatar arianpasquali commented on August 22, 2024

@qinbill what exactly did you fixed? did you get expected results?

from deep-text-corrector.

shibing624 avatar shibing624 commented on August 22, 2024

how to get expected results, and which parameters should change?
output: what what what what what what what what what

from deep-text-corrector.

Baidi96 avatar Baidi96 commented on August 22, 2024

Problem fixed. Please see my fork.

Hi, which problem did you fix? problem 'cannot replicate the results'? I tried your fork with my pertained model but still get the same kind of results.

from deep-text-corrector.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.