简体   繁体   中英

Interactive 3D visualization of word2vec model (gensim)

i have created a word2vec model with gensim and am now looking for a way to visualize this.

I have already created a 2D plot, but it is very confusing. Assuming one performs a dimensionality reduction to 3 dimensions, is there a possibility to visualize these data points "interactively" within a jupyter notebook? By interactive I mean that you might be able to navigate through the 3D plot and have a closer look at different points.

Thanks a lot.

TensorBoard a visualization tool for Google's TensorFlow can visualize embeddings in an interactive 3D plot .

If you want to use, you first need to convert the embeddings into the TensorFlow format. Gensim has a tool for that.

python -m gensim.scripts.word2vec2tensor -i you_w2v.txt -o /tmp/my_model_prefix

The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM