nn_builder
A Python library that builds neural networks with minimal boilerplate code for PyTorch and TensorFlow.
What is nn_builder?
nn_builder is a Python library that automatically generates neural network architectures for PyTorch and TensorFlow with minimal code. It solves the problem of writing repetitive boilerplate code when creating neural networks by allowing developers to specify network configurations in a concise format. The library supports multiple network types including fully connected networks, convolutional networks, and recurrent networks.
Machine learning practitioners and researchers who work with PyTorch or TensorFlow and want to accelerate neural network prototyping. It's particularly useful for those who frequently experiment with different architectures and want to reduce implementation overhead.
Developers choose nn_builder because it dramatically reduces the amount of code needed to create neural networks while maintaining full customization capabilities. Unlike manually writing network layers, it provides a standardized interface that works across both major deep learning frameworks with consistent configuration options.
Overview
Build neural networks with less boilerplate code
Use Cases
Best For
- Rapid prototyping of neural network architectures
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
