Can't find the "checkpoint" folder

Sshanu / Relation-Classification-using-Bidirectional-LSTM-Tree

TensorFlow Implementation of the paper "End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures" and "Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths" for classifying relations

MIT License

185 stars 41 forks source link

Can't find the "checkpoint" folder #19

Closed Emily-zcy closed 4 years ago

Emily-zcy commented 4 years ago

Hello, Shannu I am trying to run the models in the LCA Shortest Path folder. But I didn't find the "checkpoint" folder and its files. Like that, word_embd_dir = '../checkpoint/word_embd_wiki' pos_embd_dir = '../checkpoint/pos_embd' dep_embd_dir = '../checkpoint/dep_embd' model_dir = '../checkpoint/modelv8' So I couldn't run it successfully. Do these files need to be generated by myself? Or did you not upload it to GitHub? If it's the latter, can you share them with me? Best wishes.

Sshanu commented 4 years ago

uncomment these commands in the file: https://github.com/Sshanu/Relation-Classification-using-Bidirectional-LSTM-Tree/blob/master/LSTM%20Seq%20and%20Tree/model3v1.ipynb

f = open('data/word_embedding', 'rb') word_embedding = pickle.load(f) f.close() sess.run(embedding_init, feed_dict={embedding_placeholder:word_embedding}) word_embedding_saver.save(sess, word_embd_dir + '/word_embd')