Last active
July 30, 2018 17:42
-
-
Save thomelane/2623e0bf79873bc901ca79dd89dc5fff to your computer and use it in GitHub Desktop.
Why Numpy, vs NDArray, vs Gluon NN
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| NDArray (vs Numpy): | |
| + Can use GPU | |
| + Can use with autograd. | |
| + More NN specific functions (convolutions, etc) | |
| + Contiguous memory, better use of the cache, more performant. | |
| - Less functions implemented (although can often make with NDArray) | |
| Gluon NN (vs NDArray) | |
| + Handles parameters for you (uses same functions under the hood) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment