jiant
YOLOP
| jiant | YOLOP | |
|---|---|---|
| 2 | 5 | |
| 1,608 | 1,823 | |
| 0.5% | 1.5% | |
| 0.0 | 3.2 | |
| 10 months ago | 7 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.
jiant
-
Any recommendation for the replacement of the toolkit jiant? [Research] [Discussion]
I am doing research in NLP with the toolkit jiant (https://github.com/nyu-mll/jiant). It is a quite nice and easy-to-use tool. Unfortunately, it stopped being maintained. I wonder is there any other recommendation that I can use to replace it?
-
Looking for a code base to implement multi-task learning in NLP
Jiant should fulfill 1, 2, 4 and 5.
YOLOP
- Appending YOLO repo
- YOLO ML project
-
Lane detection
https://github.com/hustvl/YOLOP this perhaps?
- You Only Look Once for panopitic driving perception
What are some alternatives?
kiri - Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
PaddleSeg - Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.
SGDepth - [ECCV 2020] Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance
Ultra-Fast-Lane-Detection - Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)
allennlp - An open-source NLP research library, built on PyTorch.
HybridNets - HybridNets: End-to-End Perception Network
bertviz - BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
PaddleNLP - π Easy-to-use and powerful NLP and LLM library with π€ Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including πText Classification, π Neural Search, β Question Answering, βΉοΈ Information Extraction, π Document Intelligence, π Sentiment Analysis etc.