Thesis/dnc_pytorch
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
PyTorch Port of DeepMind's Differentiable Neural Computer
2 Commits 2 Branches 0 Tags 54 KiB
Python 100%
1a581b8aff
Go to file
moto 1a581b8aff Initial commit
2022-08-23 21:58:43 +09:00
dnc Initial commit 2022-08-23 21:58:43 +09:00
tests Initial commit 2022-08-23 21:58:43 +09:00
.gitignore Initial commit 2022-08-23 05:33:24 -04:00
LICENSE Initial commit 2022-08-23 05:33:24 -04:00
README.md Initial commit 2022-08-23 21:58:43 +09:00
requirements.txt Initial commit 2022-08-23 21:58:43 +09:00
train.py Initial commit 2022-08-23 21:58:43 +09:00

README.md

Differential Neural Computer in PyTorch

This is PyTorch port of DeepMind's Differentiable Neural Computer (DNC).

The original code was written with TensorFlow v1, which is not straightforward to set up in modern tech stack, such as Apple Scilicon and Python 3.8+.

This code requires only PyTorch >= 1.10.

The code structure and interfaces are kept almost same.

You can run repeat-copy task with python train.py.