Code Monkey home page Code Monkey logo

Comments (7)

orhanf avatar orhanf commented on May 20, 2024

We were getting comparable scores for cs-en when the initial pr was made, around august so the issues in NMT repo might be outdated. iirc the there were fixes at beam-search which uses the generate computational graph (same one we generate samples).

Have you checked whether the cost computational graphs are generating the same cost or not (using the same batch and initial parameters)?

from blocks-examples.

critias avatar critias commented on May 20, 2024

Thanks for your fast response,
we didn't try that yet. It's next on the list of things to try. Right now we are looking into something else, I let you know if we find something.

from blocks-examples.

orhanf avatar orhanf commented on May 20, 2024

Thanks, keep us posted

from blocks-examples.

rizar avatar rizar commented on May 20, 2024

Henry Choi told me that he was able to reproduce English to French results
with this implementation.

On 8 January 2016 at 15:32, Orhan Firat [email protected] wrote:

Thanks, keep us posted


Reply to this email directly or view it on GitHub
#71 (comment)
.

from blocks-examples.

YilunLiu avatar YilunLiu commented on May 20, 2024

@critias Hi, I am wondering did you reach the Groudhog performance. If you did, how did you reach that? I am trying the example as well and I cannot reach the performance.

from blocks-examples.

critias avatar critias commented on May 20, 2024

Hi,
yes and no. We got roughly equal results on the validation set during training, but not after reloading the saved model. Since we changed the code base a little to reload and translate the model I guess the error is on our side. It's still kinda unclear and we have to look into this in more detail, but were busy with other things last week.
Beside that we also try using orhanfs fork to see if his code to translate works better for us.

from blocks-examples.

critias avatar critias commented on May 20, 2024

It turned out the problem was on our side. We changed some minor parts of the code that caused a mismatch between the encoding used to create the vocabulary (just bytes) and the encoding used during training/translation (unicode).
We are now able to reproduce the GroundHog results and even slightly surpassed it (0.4% Bleu).
I'll close the issue. Thanks for your help and keep up the good work.

from blocks-examples.

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.