2020-11-14 23:01:51 +00:00
|
|
|
<p align="center">
|
|
|
|
|
<img src="./assets/logo.png" style="max-width: 50%;"/>
|
|
|
|
|
</p>
|
|
|
|
|
|
|
|
|
|
---
|
2020-11-14 19:27:42 +00:00
|
|
|
|
|
|
|
|
Neural network library written in Python completely from scratch, using only numpy.
|
|
|
|
|
|
|
|
|
|
## Usage
|
|
|
|
|
|
|
|
|
|
```
|
|
|
|
|
import nn
|
|
|
|
|
|
2020-11-14 20:58:11 +00:00
|
|
|
a, b = Tensor(2), Tensor(3)
|
2020-11-14 19:27:42 +00:00
|
|
|
c = a.mul(b)
|
2020-11-14 20:58:11 +00:00
|
|
|
d = c.exp()
|
|
|
|
|
d.backward()
|
2020-11-14 19:27:42 +00:00
|
|
|
|
2020-11-14 20:58:11 +00:00
|
|
|
print(a.grad, b.grad, c.grad)
|
|
|
|
|
# should output (1210.2863804782053, 806.8575869854702, 403.4287934927351)
|
2020-11-14 19:27:42 +00:00
|
|
|
```
|
|
|
|
|
|
|
|
|
|
## References
|
|
|
|
|
|
|
|
|
|
- <https://github.com/geohot/tinygrad/>
|
|
|
|
|
- <https://github.com/karpathy/micrograd/>
|
|
|
|
|
|
|
|
|
|
## Copying
|
|
|
|
|
|
|
|
|
|
This is free and unencumbered software released into the public domain.
|
