zshot
FSL-Mate
| zshot | FSL-Mate | |
|---|---|---|
| 2 | 1 | |
| 320 | 1,645 | |
| 2.5% | - | |
| 6.6 | 4.8 | |
| 2 months ago | about 2 months 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.
zshot
FSL-Mate
-
Anyone knows a good online material to understand and implement few shot learning?
In regards to understanding, I'm not entirely sure which part you need help with. A few shots learning simply means that instead of a lot of data per class (e.g. 1k+), you only have a few (e.g 8). You can take any ML algorithm that works and just train it with less examples to make it a few shot learning algorithm. Not all will work well, but it will still be a few shot learning algorithm. Try starting with a survey rather than a specific paper. Maybe this, or this
What are some alternatives?
transferlearning - Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
NCRFpp - NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.
deep-kernel-transfer - Official pytorch implementation of the paper "Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels" (NeurIPS 2020)
bllip-parser - BLLIP reranking parser (also known as Charniak-Johnson parser, Charniak parser, Brown reranking parser) See http://pypi.python.org/pypi/bllipparser/ for Python module.
learn2learn - A PyTorch Library for Meta-learning Research
GoLLIE - Guideline following Large Language Model for Information Extraction
DeepKE - [EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction
Papers-in-100-Lines-of-Code - Implementation of papers in 100 lines of code.
ARElight - Granular Viewer of Sentiments Between Entities in Massively Large Documents and Collections of Texts, powered by AREkit
PaddleViT - :robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+