October 2018
Intermediate to advanced
472 pages
10h 57m
English
Now that we have our model binaries stored in the /runs/ folder, we just need to write a restful API, for which you can use Flask, and then call the sentiment_engine() defined in the model_inference.py code.
Always make sure that you use the checkpoints of the best model and the correct embedding file, which is defined as the following:
checkpoint_dir = "./runs/1508847544/"embedding = np.load('fasttext_embedding.npy')
Read now
Unlock full access