Question about the running speed of Pyflann and Faiss for the SAM model

ixaxaar / pytorch-dnc

Differentiable Neural Computers, Sparse Access Memory and Sparse Differentiable Neural Computers, for Pytorch

MIT License

335 stars 56 forks source link

Question about the running speed of Pyflann and Faiss for the SAM model #40

Closed zoharli closed 5 years ago

zoharli commented 5 years ago

I can't normally install Faiss environment because of certain force majeure, so I wonder how using Faiss-gpu or Pyflann will influence the actual training speed of the SAM model. Let's say for example, in the copy task, how are the actual epoch times when using these two methods? Can you give me a rough reference?

ixaxaar commented 5 years ago

Oh it was significant enough that I had to literally shove FAISS in this project.

I mean the first version I had implemented was using flann, but FAISS was just way faster. In fact I ended up keeping flann just in case (as some kind of a fallback).

zoharli commented 5 years ago

Ok, I get it now, thanks！

ixaxaar commented 5 years ago

Cool! Closing this issue then 😬