syna 0.2.0

Syna is a lightweight machine learning framework inspired by DeZero.

Syna

Syna is a lightweight machine learning framework inspired by DeZero. Built from scratch using only NumPy, it follows a define-by-run (dynamic computation graph) approach and includes a basic reinforcement learning framework.

Unlike most frameworks that implement reinforcement learning as a separate library, Syna provides everything in a single library.

Designed for beginners and researchers, Syna helps you learn the fundamentals of machine learning and the inner workings of frameworks like PyTorch. Performance is not the focus, and GPU support is intentionally omitted to keep the code simple and easy to understand.

Installation

Get the Syna Source

git clone https://github.com/sql-hkr/syna.git
cd syna
uv venv
source .venv/bin/activate
uv sync

Or, from PyPI:

uv add syna

[!IMPORTANT] To visualize the computation graph, you need to install Graphviz.

brew install graphviz # macOS
sudo apt install graphviz # Linux

Getting started

Computation Graph

Visualize the computation graph for the fifth derivative of tanh(x) with respect to x.

import syna
import syna.functions as F
from syna.utils import plot_dot_graph

x = syna.tensor(1.0)
y = F.tanh(x)
x.name = "x"
y.name = "y"
y.backward(create_graph=True)

iters = 4

for i in range(iters):
    gx = x.grad
    x.cleargrad()
    gx.backward(create_graph=True)

gx = x.grad
gx.name = "gx" + str(iters + 1)
plot_dot_graph(gx, verbose=False, to_file="tanh.svg")

The output graph is shown below.

RL (Deep Q-Network; DQN)

Solve CartPole-v1 using the DQN algorithm.

from syna.algo.dqn import DQNAgent
from syna.rl import Trainer

trainer = Trainer(
    env_name="CartPole-v1",
    num_episodes=300,
    agent=DQNAgent(
        lr=3e-4,
    ),
)
trainer.train()

API Reference

• syna package

License

Syna is licensed under the MIT License. See LICENSE for details.