tensornetwork

We have hosted the application tensornetwork in order to run this application in our online workstations with Wine or directly.

Quick description about tensornetwork:

TensorNetwork is a high-level library for building and contracting tensor networks—graphical factorizations of large tensors that underpin many algorithms in physics and machine learning. It abstracts networks as nodes and edges, then compiles efficient contraction orders across multiple numeric backends so users can focus on model structure rather than index bookkeeping. Common network families (MPS/TT, PEPS, MERA, tree networks) are expressed with concise APIs that encourage experimentation and comparison. The library provides automatic path finding and cost estimation, exposing when contractions will explode in memory and suggesting better orders. Because it supports backends such as NumPy, TensorFlow, PyTorch, and JAX, the same model can run on CPUs, GPUs, or TPUs with minimal code changes. Tutorials and visualization helpers make it easier to understand how network topology affects expressive power and computational cost.

Features:

• Graph-based API for nodes, edges, and contractions
• Automatic path finding and contraction-cost estimation
• Ready-made builders for MPS/TT, PEPS, MERA, and tree networks
• Pluggable backends: NumPy, TensorFlow, PyTorch, JAX
• Visualization utilities for network structure and flows
• GPU/TPU acceleration with identical high-level code

Programming Language: Python.
Categories: