njustkmg/OMML
A multi-modal learning toolkit supporting joint and cross-modal learning algorithms for processing image-text data.
Not currently ranked — collecting fresh signals.
star history
OMML is a multi-modal learning library based on PyTorch with PaddlePaddle compatibility, offering algorithm model implementations for multi-modal fusion, cross-modal retrieval, and image captioning tasks. The toolkit supports user-defined data and training pipelines, and has been applied to industrial use cases such as sneaker authenticity verification and rumor detection.
Frequently asked
- What is njustkmg/OMML?
- A multi-modal learning toolkit supporting joint and cross-modal learning algorithms for processing image-text data.
- Is OMML open source?
- Yes — njustkmg/OMML is open source, released under the Apache-2.0 license.
- What language is OMML written in?
- njustkmg/OMML is primarily written in Python.
- How popular is OMML?
- njustkmg/OMML has 477 stars on GitHub.
- Where can I find OMML?
- njustkmg/OMML is on GitHub at https://github.com/njustkmg/OMML.