aodhneine/pygrad
1
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

Compare commits

base: aodhneine:0ad8ac2fcde1ffbc8ef4b418897100fcee1332ed
Branches Tags
aodhneine:trunk
..
compare: aodhneine:a75365a1ab13e22a3e6a465b74139ee023bcef70
Branches Tags
aodhneine:trunk

No commits in common. "0ad8ac2fcde1ffbc8ef4b418897100fcee1332ed" and "a75365a1ab13e22a3e6a465b74139ee023bcef70" have entirely different histories.
0ad8ac2fcd ... a75365a1ab

2 changed files with 3 additions and 9 deletions
Show stats Expand all files Collapse all files

1
.gitignore vendored
View file

@ -3,4 +3,3 @@ include/
lib/ lib/
lib64 lib64
pyvenv.cfg pyvenv.cfg
__pycache__/

11
README.md
View file

@ -9,20 +9,15 @@ Neural network library written in Python completely from scratch, using only num
## Usage ## Usage
``` ```
from pygrad.tensor import Tensor import nn
a, b = Tensor(np.random.randn(3, 1)), Tensor(np.random.randn(1, 3)) a, b = Tensor(2), Tensor(3)
c = a.mul(b) c = a.mul(b)
d = c.exp() d = c.exp()
d.backward() d.backward()
print(a.grad, b.grad, c.grad) print(a.grad, b.grad, c.grad)
# should output something like # should output (1210.2863804782053, 806.8575869854702, 403.4287934927351)
# [[-16.51232262 -16.51232262 -16.51232262]]
# [[-53.88103349 -53.88103349 -53.88103349]]
# [[ 3.50417648 3.50417648 3.50417648]
# [15.67424587 15.67424587 15.67424587]
# [16.0131011 16.0131011 16.0131011 ]]
``` ```
## References ## References