search

zalandoresearch / pytorch-ts

PyTorch based Probabilistic Time Series forecasting framework based on GluonTS backend
MIT License
1.24k stars 191 forks source link

Difference between the paper and the implementation #116

Open ken-take-it-so-so opened 2 years ago

ken-take-it-so-so commented 2 years ago

Hello.
I'm taking notice of the paper "Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting". I also read #50. I have three questions.

  1. The paper says batch size is 64, but according to #50, it seems to be 32. Why ?
  2. The paper says the RNN consists of 2 layers of an LSTM, but according to #50, it seems that GRU is used. Why ?
  3. Where is the experiment notebooks ?
    Does anyone know about these questions ? I would appreciate your help.