Skip to content

Instantly share code, notes, and snippets.

@victorkohler

victorkohler/bpr-opt-02.py

Created March 14, 2019 21:35
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save victorkohler/eb96199c08102a85c5cae186813757ce to your computer and use it in GitHub Desktop.
Save victorkohler/eb96199c08102a85c5cae186813757ce to your computer and use it in GitHub Desktop.
Download ZIP
Raw
bpr-opt-02.py
#-------------
# HYPERPARAMS
#-------------
epochs = 50
batches = 30
num_factors = 64 # Number of latent features
# Independent lambda regularization values
# for user, items and bias.
lambda_user = 0.0000001
lambda_item = 0.0000001
lambda_bias = 0.0000001
# Our learning rate
lr = 0.005
# How many (u,i,j) triplets we sample for each batch
samples = 15000
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment