Shypd.aiThe largest open index of AI toolstf_geometric is an efficient and friendly Graph Neural Network (GNN) library for TensorFlow 1.x and 2.x. It provides easy and elegant APIs for complex GNN operations and supports various GNN architectures.
About
tf_geometric is a Graph Neural Network (GNN) library designed for TensorFlow 1.x and 2.x, offering an efficient and user-friendly approach to deep learning on graphs. Inspired by PyTorch Geometric, it implements GNNs using a Message Passing mechanism, which is noted for being more efficient than dense matrix-based implementations and more accessible than sparse matrix-based ones. The library provides intuitive APIs for constructing graphs, applying various GNN layers like GAT and GCN, and handling batch processing of graphs. It also includes built-in datasets such as Cora, PPI, and TU Datasets, and supports both OOP and Functional API styles for flexibility in model development. Users can install it with specific TensorFlow CPU or GPU versions.
Capabilities
Pricing & Plans
Open Source
Free
FAQs