NVIDIA/DeepRecommender

Add MovieLens example

開放

#2 建立於 2017年10月3日

 (0 則留言) (2 個反應) (0 位負責人)Python (340 個分叉)auto 404
enhancementgood first issuehelp wanted

倉庫指標

星標
 (1,702 顆星)
PR 合併指標
 (PR 指標待抓取)

描述

Provide a recepie for training a model on MovieLens data (20M and 1M).

This should include the following:

  1. Data converter. Consider fixing/adjusting this script
  • Train/Eval/Test split. Training test ratings should come before any Eval and Test ratings. See section 3.1 (Experiment setup) of this paper for details and Netflix converter for example.
  1. An example train.sh, and test.sh for 20M and 1M MovieLens data sets which will train/eval and test the model correspondingly.

  2. Choose model architecture and hyper parameters that give best eval RMSE you can get.

貢獻者指南