https://github.com/m0saan/minima
a lightweight deep learning framework, lean yet effective tailor-made for educational exploration.
https://github.com/m0saan/minima
agi deep-learning deep-learning-framework ndarray neural-networks tensors
Last synced: about 13 hours ago
JSON representation
a lightweight deep learning framework, lean yet effective tailor-made for educational exploration.
- Host: GitHub
- URL: https://github.com/m0saan/minima
- Owner: m0saan
- License: apache-2.0
- Created: 2023-05-31T19:09:33.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2023-07-04T06:23:48.000Z (over 2 years ago)
- Last Synced: 2025-03-06T10:31:18.814Z (7 months ago)
- Topics: agi, deep-learning, deep-learning-framework, ndarray, neural-networks, tensors
- Language: Jupyter Notebook
- Homepage: https://m0saan.github.io/minima/
- Size: 30.1 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
Welcome to minima
================
[](https://pypi.org/project/minima/#description)
[](https://anaconda.org/m0saan/minima)
# minima: A Mini Deep Learning Framework
> minima is a lightweight deep learning framewor, lean yet effective
> tailor-made for educational exploration.
> Just like a delicate sapling inspired by the towering strength of an
> oak, Minima draws its inspiration from PyTorch.
> Yet, it carves its own identity with a straightforward interface and a
> curated set of features.
> This makes learning and using it a breeze, allowing you to
> effortlessly build and train neural networks.
> Indeed, Minima is your friendly companion on the journey to
> understanding deep learning, where less is often more.
## Installing
You can install minima on your own machines with conda
If you’re using
[miniconda](https://docs.conda.io/en/latest/miniconda.html)
(recommended) then run:
``` bash
conda install minima
```
…or if you’re using
[Anaconda](https://www.anaconda.com/products/individual) then run:
``` bash
conda install minima anaconda
```
To install with pip, use: `pip install minima`.
If you plan to develop Minima yourself, or want to be on the cutting
edge, you can use an editable install.
``` bash
git clone https://github.com/m0saan/minima
pip install .
```
## Features
- Easy to install and use
- Simple and intuitive API for defining and training neural networks
- Built-in support for common layers and activation functions
- Supports both CPU and GPU acceleration
- Compatible with NumPy arrays for easy data manipulation
## Usage
Here’s a simple example of how to define and train a neural network
using Minima:
``` python
import minima as mi
# Define the neural network architecture
model = mi.nn.Sequential(
mi.nn.Linear(784, 128),
mi.nn.ReLU(),
mi.nn.Linear(128, 10),
mi.nn.Softmax()
)
# Load the dataset
x_train, y_train, x_test, y_test = load_data()
# Train the model
loss_fn = mi.nn.CrossEntropyLoss()
optimizer = mi.optim.SGD(model.parameters(), lr=0.01)
for epoch in range(10):
for x_batch, y_batch in mi.nn.minibatch(x_train, y_train, batch_size=32):
y_pred = model(x_batch)
loss = loss_fn(y_pred, y_batch)
optimizer.zero_grad()
loss.backward()
optimizer.step()
# Evaluate the model
y_pred = model(x_test)
accuracy = compute_accuracy(y_pred, y_test)
print(f"Accuracy: {accuracy:.2f}")
```
This example defines a simple neural network with two linear layers and
two activation functions, trains it on a dataset using stochastic
gradient descent, and evaluates its accuracy on a test set.
## Documentation
For more information on how to use minima, please refer to the
documentation, which can be found in the website above.
## Contributing
coming soon!
## License
minima is released under the Apache License 2.0. See `LICENSE` for more
information.