TensorFlow : How and where to specify save path in word2vec?

Question

I am trying to implementing word2vec model of tensorflow and went through the tutorial of tensorflows Vector representation of words.

After that I compiled the word2vec code in my system and I am getting this output.

--train_data --eval_data and --save_path must be specified.

I am new to TensorFlow and I don't know where and how should I specify train_data, eval_data and save_path.

Also is there a more detailed tutorial available on TensorFlow vector representation of words to understand the word2vec model better.

Answer 1

When you run the script, you need to provide these as flags. Try running it like this,

python word2vec.py --train_data <path to training data> --eval_data <path to eval> --save_path <save directory>