Thesis/pytorch-dnc
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

love thy neighbour

Browse Source
This commit is contained in:
ixaxaar 2017-12-20 03:05:01 +05:30
parent adbb195e27
commit 1abd4c4ba4
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@ -456,7 +456,7 @@ python ./tasks/argmax_task.py -cuda 0 -lr 0.0001 -rnn_type lstm -memory_type dnc
## General noteworthy stuff
1. SDNCs use the [FLANN approximate nearest library](https://www.cs.ubc.ca/research/flann/), with its python binding [pyflann3](https://github.com/primetang/pyflann).
1. SDNCs use the [FLANN approximate nearest neigbhour library](https://www.cs.ubc.ca/research/flann/), with its python binding [pyflann3](https://github.com/primetang/pyflann) and [FAISS](https://github.com/facebookresearch/faiss).
FLANN can be installed either from pip (automatically as a dependency), or from source (e.g. for multithreading via OpenMP):
@ -480,8 +480,7 @@ conda install faiss-gpu -c pytorch
FAISS is much faster, has a GPU implementation and is interoperable with pytorch tensors.
We try to use FAISS by default, in absence of which we fall back to FLANN.
2. An alternative to FLANN is [FAISS](https://github.com/facebookresearch/faiss), which is much faster and interoperable with torch cuda tensors (but is difficult to distribute, see [dnc/faiss_index.py](dnc/faiss_index.py)).
3. `nan`s in the gradients are common, try with different batch sizes
2. `nan`s in the gradients are common, try with different batch sizes
Repos referred to for creation of this repo: