search

notAI-tech / deepsegment

A sentence segmenter that actually works!
http://bpraneeth.com/projects
GNU General Public License v3.0
302 stars 56 forks source link

Add the ability to change the dimension #21

Open nagadit opened 4 years ago

nagadit commented 4 years ago

I have glove 300d vectors only. Change pls code here and here to this: def train(x, y, vx, vy, epochs, batch_size, save_folder, glove_path, dim_glove=100) and model = seqtag_keras.Sequence(embeddings=embeddings, word_embedding_dim=dim_glove, word_lstm_size = dim_glove) tnx

bedapudi6788 commented 4 years ago

@good-mouse 300d vectors are mostly a overkill and will result in at least 4x performance degradation.

If you really need support for 300d vectors inside the library, please consider making a PR. I will be more than happy to help if you need any guidance for that.

bedapudi6788 commented 4 years ago
  1. Fork the repo.
  2. create a new branch
  3. Make your changes and push to your forked repo.
  4. Create a pull request.

https://yangsu.github.io/pull-request-tutorial/

nagadit commented 4 years ago

@bedapudi6788 I thought you mean PR as an advertisement 😄