TensorNets
High-level TensorFlow network definitions with pre-trained weights for easy integration into existing ML workflows.
What is TensorNets?
TensorNets is a Python library that provides high-level implementations of popular deep learning architectures with pre-trained weights for TensorFlow. It solves the problem of quickly integrating state-of-the-art models into existing machine learning workflows without dealing with complex custom classes or implementation details. The library includes models for image classification and object detection with utilities for pre-processing, weight loading, and intermediate layer access.
Machine learning practitioners and researchers who use TensorFlow and want to quickly benchmark or deploy pre-trained models like ResNet, MobileNet, or YOLO without writing boilerplate code. It's particularly useful for those with existing ML workflows who need plug-and-play model integration.
Developers choose TensorNets because it offers simple functional interfaces that return standard TensorFlow tensors, making models easily composable with existing code. Unlike other implementations, it provides consistent APIs across many architectures, pre-trained weights with reproduction utilities, and compatibility with multiple TensorFlow versions.
Overview
High level network definitions with pre-trained weights in TensorFlow
Use Cases
Best For
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.
