tensorflow/fold
TensorFlow Fold is a library for deep learning with dynamic computation graphs that depend on input data structure.
Not currently ranked — collecting fresh signals.
star history
TensorFlow Fold enables creation of TensorFlow models that consume structured data, where the computation graph structure adapts to input structure. It implements dynamic batching, transforming arbitrarily shaped computation graphs into static graphs for efficient execution. The library is particularly suited for recursive neural networks like TreeLSTMs applied to tasks such as sentiment analysis on parse trees of varying shapes and depths.
Frequently asked
- What is tensorflow/fold?
- TensorFlow Fold is a library for deep learning with dynamic computation graphs that depend on input data structure.
- Is fold open source?
- Yes — tensorflow/fold is open source, released under the Apache-2.0 license.
- What language is fold written in?
- tensorflow/fold is primarily written in Python.
- How popular is fold?
- tensorflow/fold has 1.8k stars on GitHub.
- Where can I find fold?
- tensorflow/fold is on GitHub at https://github.com/tensorflow/fold.