How yacine204/nyuraru works
ニューラル is a NumPy-based neural-network library for defining custom layers, training on .npy data, evaluating and predicting, with a Raylib visualizer for training progress and interactive tests. The main workflow is user configuration → training or loading a model → evaluation or interactive prediction. The graph includes the core computation, loss and activation modules, the Python-to-C visualization boundary, and the supplied datasets and weights. Edges are limited to relationships shown in excerpts or documented in the README; examples are omitted, and unsampled implementation details are not inferred.
Main entry points: nn.py Neural network · visualizer.py Python visualizer · dataset Example datasets · weights Pretrained weights
Components 12
Model computation
- Neural network
core/nn.py - Layer definitions
core/layer.py - Activation functions
core/activate.py
Training and evaluation
- Loss functions
core/cost.py - Training
core/nn.py - Evaluation
core/nn.py - Interactive prediction
core/nn.py
Interactive visualization
- Python visualizer
core/visualizer.py - Raylib visualizer UI
visualizor.c
Supplied model data
- Example datasets
dataset - Pretrained weights
weights
Other components
- Library user
Connections 13
- Library user → Neural network: configures
README.md - Neural network → Layer definitions: uses layers
core/nn.py - Neural network → Activation functions: uses activations
core/nn.py - Neural network → Loss functions: executes loss
core/nn.py - Library user → Training: trains on data
README.md - Example datasets → Training: provides .npy data
README.md - Library user → Evaluation: evaluates model
README.md - Pretrained weights → Neural network: loads pretrained model
README.md - Library user → Interactive prediction: starts prediction
README.md - Training → Python visualizer: updates visualization
core/nn.py - Interactive prediction → Python visualizer: drives interactive UI
core/nn.py - Python visualizer → Raylib visualizer UI: calls UI functions
core/visualizer.py - Library user → Python visualizer: interacts in real time
README.md