Metadata-Version: 2.4
Name: energizer
Version: 0.1.4
Summary: A lightweight deep learning library for Apple's Neural Engine.
Author-email: Florian GRIMA <florian.grima@epitech.eu>
License-Expression: MIT
Project-URL: Homepage, https://github.com/fgrimaepitech/energizer
Project-URL: Repository, https://github.com/fgrimaepitech/energizer
Project-URL: Issues, https://github.com/fgrimaepitech/energizer/issues
Keywords: deep-learning,neural-engine,machine-learning,mlx,apple
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: mlx
Requires-Dist: mlx-metal
Provides-Extra: gpu
Requires-Dist: mlx; extra == "gpu"
Requires-Dist: mlx-metal; extra == "gpu"
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Requires-Dist: torch; extra == "dev"
Requires-Dist: torchvision; extra == "dev"
Dynamic: license-file

Energizer (formerly `energizer`) – custom PyTorch-like library for the Neural Engine

## Need to Implement:

### A. Essential Layers:

- [x] Batch Normalization - Critical for stable training (BatchNorm1d, BatchNorm2d)
- [x] Dropout - For regularization
- [x] Pooling layers (MaxPool2d, AvgPool2d)
- [x] Flatten layer - To convert conv outputs to linear inputs
- [x] Residual blocks - For deeper networks

### B. Activation Functions:

- [x] Sigmoid - For binary classification
- [x] Tanh - For value estimation (-1 to 1)
- [x] LeakyReLU - Better than ReLU in some cases
- [ ] Softmax - For move probability distribution

### C. Loss Functions:

- [x] MSE Loss - For value prediction
- [x] CrossEntropy Loss - For move prediction
- [ ] Huber Loss - More robust than MSE
- [ ] Custom chess loss - Combine policy and value loss
