profile
viewpoint
If you are wondering where the data of this site comes from, please visit https://api.github.com/users/ilya-shenbin/events. GitMemory does not store any data, but only uses NGINX to cache data for a period of time. The idea behind GitMemory is simply to give users a better reading experience.
Ilya Shenbin ilya-shenbin Saint Petersburg

ilya-shenbin/RecVAE 51

The official PyTorch implementation of the paper "RecVAE: A New Variational Autoencoder for Top-N Recommendations with Implicit Feedback"

ilya-shenbin/hpcourse 0

Project is aimed to store student's practical works on high performance computing course

ilya-shenbin/inverted-index-pm2 0

Automatically exported from code.google.com/p/inverted-index-pm2

startedilya-shenbin/RecVAE

started time in 4 days

startedilya-shenbin/RecVAE

started time in 15 days

issue commentilya-shenbin/RecVAE

epoch result: nan for ndcg

Try running it python2. That worked for me.

mir-boz

comment created time in 23 days

startedilya-shenbin/RecVAE

started time in 24 days

startedilya-shenbin/RecVAE

started time in a month

startedilya-shenbin/RecVAE

started time in a month

fork crystal22/RecVAE

The official PyTorch implementation of the paper "RecVAE: A New Variational Autoencoder for Top-N Recommendations with Implicit Feedback"

fork in 2 months

fork Microstrong0305/RecVAE

The official PyTorch implementation of the paper "RecVAE: A New Variational Autoencoder for Top-N Recommendations with Implicit Feedback"

fork in 2 months

fork mir-boz/RecVAE

The official PyTorch implementation of the paper "RecVAE: A New Variational Autoencoder for Top-N Recommendations with Implicit Feedback"

fork in 3 months

startedilya-shenbin/RecVAE

started time in 3 months

issue openedilya-shenbin/RecVAE

epoch result: nan for ndcg

Greetings to the team! Your code is beautiful, but I'm lost in the implementation of it.

I have the last version of PyTorch: https://pytorch.org/get-started/locally/ & Python

  • Stable (1.8.1)
  • OS: Windows
  • Package: PiP
  • Computer Platform: CUDA 11.1
  • Python: 3.8.7

When I train the model I receive the outputs:

  • test_te.csv
  • test_tr.csv
  • validation_tr.csv
  • validation_te.csv
  • train
  • unique_sid
  • unique_uid (For k = 100 in utils.py)

image

If I change the utils.py in the return of ndcg function for: return DCG/IDCG to: return np.divide(DCG,IDCG, where=IDCG!=0) it solve it, but still giving 'low' values. The latter in comparison with other VAE-CF results.

Can you help me, please?

Congratulations. I reiterate, your code is beautiful in comparison to tensorflow-keras implementation.

Best regards, Mirko.

created time in 3 months

startedilya-shenbin/RecVAE

started time in 3 months