Kiwigrad
Despite lacking the ability to fly through the skies like PyTorch and TensorFlow, the Kiwigrad is still a formidable bird that is teeming with untapped potential waiting to be uncovered. :wink:
Kiwigrad? yes, it is another version of micrograd that was created just for fun and experimentation.
Install
To install the current release,
pip install kiwigrad
Functionalities
Kiwigrad is a modified version of the micrograd and the minigrad packages with additional features. The main features added to Kiwigrad are:
- Training is faster due to the C implementation of the Value object.
- Tracing functionalities like the original micrograd package were added. An example of this can be seen in the ops notebook.
- Methods for saving and loading the weights of a trained model.
- Support for RNN(1) feedforward neural networks.
Examples
- In the examples folder, you can find examples of models trained using the Kiwigrad library.
- A declaration example of an MLP net using Kiwigrad:
from kiwigrad import MLP, Layer
class PotNet(MLP):
def __init__(self):
layers = [
Layer(nin=2, nout=16, bias=True, activation="relu"),
Layer(nin=16, nout=16, bias=True, activation="relu"),
Layer(nin=16, nout=1, bias=True, activation="linear")
]
super().__init__(layers=layers)
model = PotNet()
from kiwigrad import Value, draw_dot
a = Value(-4.0)
b = Value(2.0)
c = a + b
d = a * b + b**3
c += c + Value(1.)
c += Value(1.) + c + (-a)
d += d * Value(2) + (b + a).relu()
d += Value(3.) * d + (b - a).relu()
e = c - d
f = e**2
g = f / Value(2.0)
g += Value(10.0) / f
print(f'{g.data:.4f}') # prints 24.7041, the outcome of this forward pass
g.backward()
print(f'{a.grad:.4f}') # prints 138.8338, i.e. the numerical value of dg/da
print(f'{b.grad:.4f}') # prints 645.5773, i.e. the numerical value of dg/db
draw_dot(g)
Running test
cd test
pytest .
1 maintainer
Release files for kiwigrad 0.28
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| kiwigrad-0.28.tar.gz | 10.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| kiwigrad-0.28-cp39-cp39-macosx_10_9_universal2.whl | CPython 3.9 | CPython 3.9 | macOS 10.9+ universal2 (ARM64, x86-64) | Details |
Total release size: 27.9 kB
Release files / kiwigrad-0.28.tar.gz
| Download URL | kiwigrad-0.28.tar.gz |
|---|---|
| Size | 10.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
fe118ec44b0a7f2b3573f8807481a182b7b390a9cc51284e8404523ee60d0332
|
|
BLAKE2b-256 checksum How to use checksums |
70cc26f79c4d09886377fda0ff4a1fd845b8013b168b0c0b9f1eceeb639155c2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.9.12
|
Release files / kiwigrad-0.28-cp39-cp39-macosx_10_9_universal2.whl
| Download URL | kiwigrad-0.28-cp39-cp39-macosx_10_9_universal2.whl |
|---|---|
| Size | 17.5 kB |
| Tags | CPython 3.9 macOS 10.9+ universal2 (ARM64, x86-64) |
|
SHA-256 checksum How to use checksums |
73cca6c4fcc751bfa0ca7564159818ef62cea3951144be64a57d4a2bf77031fb
|
|
BLAKE2b-256 checksum How to use checksums |
5db4c6db648eeace5c080288102f92b765537d719a7ab5a4298457000506bc5c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.9.12
|
