Metadata-Version: 2.4
Name: energizer
Version: 0.1.8a1
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/energizer-ml/energizer
Project-URL: Repository, https://github.com/energizer-ml/energizer
Project-URL: Issues, https://github.com/energizer-ml/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: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: <3.13,>=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: mlx
Requires-Dist: mlx-metal
Requires-Dist: coremltools>=8.0
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"
Provides-Extra: coreml
Requires-Dist: coremltools>=8.0; extra == "coreml"
Dynamic: license-file

# Energizer

> A lightweight PyTorch-like deep learning library for Apple's Neural Engine.

[![PyPI version](https://img.shields.io/pypi/v/energizer)](https://pypi.org/project/energizer/)
[![Python](https://img.shields.io/pypi/pyversions/energizer)](https://pypi.org/project/energizer/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
[![Lint](https://github.com/energizer-ml/energizer/actions/workflows/lint.yml/badge.svg)](https://github.com/energizer-ml/energizer/actions/workflows/lint.yml)

Energizer provides a familiar, PyTorch-style API for building and training neural networks with **first-class support for Apple Silicon** via the [MLX](https://github.com/ml-explore/mlx) backend. It falls back to NumPy on CPU, making it suitable for prototyping on any platform.

---

## Features

- **Autograd** — Automatic differentiation through a `Function` graph, with `.backward()` on any `Tensor`.
- **Dual backend** — CPU via NumPy, GPU via Apple MLX. Switch with `.to("gpu")`.
- **PyTorch-like API** — `Module`, `Parameter`, `Sequential`, `Optimizer` — familiar patterns, zero friction.
- **Full layer library** — Linear, Conv1d/2d, Transformer, Embedding, Normalization, Pooling, and more.
- **Model serialization** — `model.save()` / `Model.load()` out of the box.
- **Lightweight** — Pure Python, minimal dependencies (`numpy`, `mlx`).

---

## Installation

```bash
pip install energizer
```

For GPU acceleration on Apple Silicon:

```bash
pip install "energizer[gpu]"
```

For development:

```bash
pip install "energizer[dev]"
```

**Requirements:** Python 3.10, 3.11, or 3.12 (Maximum 3.12 required for `coremltools` support)

---

## Quickstart

```python
import energizer

# Build a model
model = energizer.Sequential(
    energizer.Linear(784, 256),
    energizer.ReLU(),
    energizer.Dropout(p=0.3),
    energizer.Linear(256, 10),
)

# Move to Apple Neural Engine
model.to("gpu")

# Forward pass
x = energizer.Tensor.randn(32, 784, device="gpu")
output = model(x)

# Loss + backward
loss_fn = energizer.CrossEntropyLoss()
target  = energizer.Tensor.zeros((32,), device="gpu")
loss    = loss_fn(output, target)
loss.backward()

# Optimizer step
optimizer = energizer.Adam(model.parameters(), lr=1e-3)
optimizer.step()
optimizer.zero_grad()
```

---

## API Reference

### Tensor

The core data structure. Wraps NumPy arrays on CPU and MLX arrays on GPU.

```python
t = energizer.Tensor([[1.0, 2.0], [3.0, 4.0]], requires_grad=True)

# Creation helpers
energizer.Tensor.randn(3, 4)
energizer.Tensor.zeros((3, 4))
energizer.Tensor.ones((3, 4))

# Device transfer
t.to("gpu")   # → Apple Neural Engine (MLX)
t.to("cpu")   # → NumPy

# Supported operators
t + t  |  t - t  |  t * t  |  t / t
t @ t  |  t ** 2 |  -t
t.sum()  |  t.mean()  |  t.T
t.reshape((4, 2))  |  t.view((4, 2))
t.transpose(0, 1)

# Autograd
loss = (model(x) - target).mean()
loss.backward()
```

---

### Module

Base class for all layers. Subclass it to define custom layers.

```python
class MyLayer(energizer.Module):
    def __init__(self):
        super().__init__()
        self.w = energizer.Parameter(energizer.Tensor.randn(4, 4))

    def forward(self, x):
        return x @ self.w

model.parameters()        # list of trainable Parameters
model.to("gpu")           # move all parameters to device
model.train() / .eval()   # toggle training mode (affects Dropout, BatchNorm)
model.save("model.npz")   # serialize to disk
model.load("model.npz")   # restore from disk
```

---

### Layers

#### Linear

```python
energizer.Linear(in_features=128, out_features=64, bias=True)
```

#### Convolutional

```python
energizer.Conv1d(in_channels, out_channels, kernel_size, stride=1, padding=0)
energizer.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0)
energizer.ConvTranspose2d(in_channels, out_channels, kernel_size, stride=1, padding=0)
```

#### Activation Functions

```python
energizer.ReLU()
energizer.LeakyReLU(negative_slope=0.01)
energizer.Sigmoid()
energizer.GELU()
```

#### Normalization

```python
energizer.BatchNorm1d(num_features)
energizer.BatchNorm2d(num_features)
energizer.LayerNorm(normalized_shape)
```

#### Pooling

```python
energizer.MaxPool2d(kernel_size, stride=None, padding=0)
energizer.AvgPool2d(kernel_size, stride=None, padding=0)
```

#### Regularization

```python
energizer.Dropout(p=0.5)
```

#### Shape Manipulation

```python
energizer.Flatten(start_dim=1, end_dim=-1)
energizer.Reshape(shape)
energizer.Trim(start, end)
```

#### Containers

```python
energizer.Sequential(*layers)          # forward through layers in order
energizer.ModuleList([layer1, layer2]) # list of modules, no auto-forward
```

#### Residual Blocks

```python
energizer.ResidualBlock(channels)
energizer.BottleneckBlock(in_channels, out_channels)
```

#### Transformer

```python
energizer.TransformerEncoderLayer(d_model, nhead, dim_feedforward=2048, dropout=0.1)
energizer.TransformerEncoder(encoder_layer, num_layers)
```

#### Embedding

```python
energizer.Embedding(num_embeddings, embedding_dim)
```

#### AutoEncoder

```python
energizer.AutoEncoder(device="cpu")   # pre-configured convolutional autoencoder
```

---

### Loss Functions

```python
energizer.MSELoss(reduction="mean")
energizer.CrossEntropyLoss(reduction="mean")
```

---

### Optimizers

#### SGD

```python
energizer.SGD(
    model.parameters(),
    lr=0.01,
    momentum=0.9,
    weight_decay=1e-4,
    nesterov=False,
)
```

#### Adam

```python
energizer.Adam(
    model.parameters(),
    lr=1e-3,
    betas=(0.9, 0.999),
    eps=1e-8,
    weight_decay=0,
    amsgrad=False,
)
```

---

### Functional API

```python
from energizer import functionnal as F

F.max(tensor, floor=0.0)                     # element-wise max with a floor
F.as_strided(tensor, shape, strides)         # strided view of a tensor
F.trace(tensor)                              # trace of a 2D matrix
```

---

## Training Loop Example

```python
import energizer

model     = energizer.Sequential(energizer.Linear(4, 8), energizer.ReLU(), energizer.Linear(8, 1))
optimizer = energizer.Adam(model.parameters(), lr=1e-3)
loss_fn   = energizer.MSELoss()

model.train()
for epoch in range(100):
    optimizer.zero_grad()

    x      = energizer.Tensor.randn(16, 4)
    target = energizer.Tensor.zeros((16, 1))

    output = model(x)
    loss   = loss_fn(output, target)
    loss.backward()
    optimizer.step()

    if epoch % 10 == 0:
        print(f"Epoch {epoch:3d} | Loss: {loss.item():.4f}")
```

---

## Roadmap

### Layers
- [ ] Softmax activation
- [ ] Huber Loss

### Infrastructure
- [ ] GPU autograd pass (MLX-native backward)
- [ ] Mixed precision training
- [ ] `DataLoader` / `Dataset` abstractions

---

## Contributing

Pull requests are welcome. Please make sure your code is formatted with [Black](https://black.readthedocs.io/) before submitting — the CI will enforce it:

```bash
black energizer/ tests/ src/
```

---

## License

MIT — see [LICENSE](LICENSE).

---

## Author

**Florian GRIMA** — [florian.grima@epitech.eu](mailto:florian.grima@epitech.eu)  
[GitHub](https://github.com/fgrimaepitech) · [PyPI](https://pypi.org/project/energizer/) · [Issues](https://github.com/energizer-ml/energizer/issues)
