GLIP VS spaCy

noun_chunks: The noun phrase (extracted by spaCy) that have associated bounding boxes (predicted by GLIP). The items in the children list respectively represent 'Start of the noun chunk in caption', 'End of the noun chunk in caption', 'normalized x_min', 'normalized y_min', 'normalized x_max', 'normalized y_max', 'confidence score'.

GLIP (https://github.com/microsoft/GLIP), which i feel has flown under the radar, is capable of zero-shot object detection. i threw together a notebook that pairs it with the recently released Segment Anything Model (https://github.com/facebookresearch/segment-anything) to do zero-shot instance segmentation: https://colab.research.google.com/drive/1kfdizAJiD5_t-M6yFBB6t2vzGrYg8SJc

Continue reading | Checkout the paper and github

Code for https://arxiv.org/abs/2112.03857 found: https://github.com/microsoft/GLIP

Hi Community, In this article, I will demonstrate below steps to create your own chatbot by using spaCy (spaCy is an open-source software library for advanced natural language processing, written in the programming languages Python and Cython):

SpaCy: An open-source library providing tools for advanced NLP tasks like tokenization, entity recognition, and part-of-speech tagging.

spaCy https://spacy.io/

In this article, I'm going to walk through a sentiment analysis project from start to finish, using open-source Amazon product reviews. However, using the same approach, you can easily implement mass sentiment analysis on your own products. We'll explore an approach to sentiment analysis with one of the most popular Python NLP packages: spaCy.

Spacy [0] is a state-of-art / easy-to-use NLP library from the pre-LLM era. This post is the Spacy founder's thoughts on how to integrate LLMs with the kind of problems that "traditional" NLP is used for right now. It's an advertisement for Prodigy [1], their paid tool for using LLMs to assist data labeling. That said, I think I largely agree with the premise, and it's worth reading the entire post.

The steps described in "LLM pragmatism" are basically what I see my data science friends doing — it's hard to justify the cost (money and latency) in using LLMs directly for all tasks, and even if you want to you'll need a baseline model to compare against, so why not use LLMs for dataset creation or augmentation in order to train a classic supervised model?

[0] https://spacy.io/

[1] https://prodi.gy/

spaCy

I chose spacy. Although it's not state of the art, it's very well established and stable.