pytorch-adapt
pykale
Our great sponsors
pytorch-adapt | pykale | |
---|---|---|
3 | 2 | |
323 | 427 | |
- | 1.6% | |
0.0 | 9.4 | |
about 1 year ago | about 1 month ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
pytorch-adapt
- PyTorch-adapt re-purposes existing ML models to work in new domains
-
[P] A domain adaptation library that I wrote: PyTorch Adapt
For more details, you might be interested in the jupyter notebooks here: https://github.com/KevinMusgrave/pytorch-adapt/blob/main/examples/README.md
I wrote [a library](https://github.com/KevinMusgrave/pytorch-adapt) for domain adaptation, which is a type of machine learning that repurposes existing models to work in new domains. A toy example is adapting a model trained on MNIST for use on colored digits:
pykale
-
PyKale Preprint: Knowledge-Aware Machine Learning from Multiple Sources in Python [P][R]
A 10-page preprint is on arXiv to describe the green machine learning design principles behind our pipeline-based API below as well as features and examples in our PyKale library for multimodal learning and transfer learning with deep learning and dimensionality reduction on graphs, images, texts, and videos to enable and accelerate interdisciplinary research: [2106.09756] PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python (arxiv.org)
-
[P] An introduction to PyKale https://github.com/pykale/pykale, a PyTorch library that provides a unified pipeline-based API for knowledge-aware multimodal learning and transfer learning on graphs, images, texts, and videos to accelerate interdisciplinary research. Welcome feedback/contribution!
Thank you LargeYellowBus for your valuable feedback! That's really helpful. It is weird to hear that the GitHub link was broken when you tried. It is here https://github.com/pykale/pykale and there have been 100+ unique visitors today. So it might be temporary on your side and you may try again.
What are some alternatives?
hierarchical-domain-adaptation - Code of NAACL 2022 "Efficient Hierarchical Domain Adaptation for Pretrained Language Models" paper.
EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Transfer-Learning-Library - Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
AdaTime - [TKDD 2023] AdaTime: A Benchmarking Suite for Domain Adaptation on Time Series Data
CEPC - A domain adaptation model
Multimodal-Toolkit - Multimodal model for text and tabular data with HuggingFace transformers as building block for text data
autogluon - AutoGluon: AutoML for Image, Text, Time Series, and Tabular Data [Moved to: https://github.com/autogluon/autogluon]
Meta-SelfLearning - Meta Self-learning for Multi-Source Domain Adaptation: A Benchmark
social-balance - A library-agnostic project for calculating exactly and efficiently social balance, based on the Aref, Mason and Wilson paper (https://arxiv.org/abs/1611.09030)
open_flamingo - An open-source framework for training large multimodal models.
jina - ☁️ Build multimodal AI applications with cloud-native stack
valhalla-nmt - Code repository for CVPR 2022 paper "VALHALLA: Visual Hallucination for Machine Translation"