Giter Site home page Giter Site logo

aditya-malte / colab-xlnet-finetuning Goto Github PK

View Code? Open in Web Editor NEW

This project forked from zihangdai/xlnet

12.0 12.0 8.0 201 KB

Colab TPU - Compatible XLNet model code

License: Apache License 2.0

Python 88.13% Shell 1.12% Jupyter Notebook 10.75%

colab-xlnet-finetuning's Issues

How to get the predictions from the XLNet

I have trained the model by doing some modifications in the yelp5processor. The model has been trained. Now I want to get the predictions of the test sentences for which I don't have the actual Y, I just want to retrieve the predicted Y values from the trained model.
If someone could give an example in the colab file that would be a lot helpful.
Any Help will be appreciated.

typo in data dir

Hi,
Thanks a lot for the notebook for TPU, I've tried and it is really fast!
BTW, there is a little typo in the notebook:
--data_dir=../"+TASK_DATA_DIR+"
there should be 2 "." :)

issue of Dir when eval

Hi, it's me again. Thanks for your notebook!

I just find that the init Weight should be in a different directory from the saved ckpt. Or there will be error when doing eval.
in the notebook, you put init weight in MODEL_DIR
I think in training:
--output_dir="+OUTPUT_DIR+"
--model_dir="+MODEL_DIR+"
should be:
--output_dir="+OUTPUT_DIR+"
--model_dir="+OUTPUT_DIR+"
to separate init weight from save ckpt.

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.