Gain insights into Hugging Face’s AI models for NLP and computer vision. Explore transformer-based pipelines, apply them for tasks like classification and object detection, using Python and PyTorch.

Applying Hugging Face Machine Learning Pipelines in Python.png

dox.tar.gz

NormalCode

JuPyter

JuPy-Translation

JuPy-QA

JuPy-Text-Classification

JuPy-Summarization

JuPy-Text-Generation

JuPy-Similarity

JuPy-Fill-Mask

JuPy-Image-Classification

JuPy-Object-Detection

JuPy-Segmentation

JuPy-Image-to-Text

Hugging Face is a community-driven effort to develop and promote artificial intelligence for a wide array of applications. The organization’s pre-trained, state-of-the-art deep learning models can be deployed to various machine learning tasks.

In this course, you’ll explore the Hugging Face artificial intelligence library with particular attention to natural language processing (NLP) and computer vision. You’ll first explore Hugging Face’s approach to deep learning with specific attention to transformers. You’ll then learn Hugging Face’s pipeline API model and apply various pipelines to unique NLP tasks such as classification, summarization, question answering, and more. You’ll continue with a new set of Hugging Face pipelines for computer vision tasks including object detection and segmentation.

By the end of this course, you’ll be familiar with a wide array of Hugging Face’s pipelines for common machine learning tasks and their implementation in Python using pytorch.

Applying Hugging Face Machine Learning Pipelines in Python

# Overview


**Object detection** is similar to image classification, but we're interested in particular object(s) instances. It can be used for object tracking and image annotation as well.


 

In classical computer vision, techniques like Histogram of Gradients (**HoG**), Shift-Invariant Features Transform (**SIFT**), or Haar features were used. \
With the popularity of deep learning models, they were replaced with models like **YOLO** (You Only Look Once), **R-CNN** (Region-based Convolutional Neural Networks), or RetinaNet.

# Transformers for object detection

The third wave of object detection models should be attributed to transformers. Transformers can be applied to images directly (using vision transformers) or indirectly.

We've already seen the direct use of vision transformers in the previous lesson. On the other hand, there are some indirect usages of transformers in computer vision tasks, including object detection.

In 2020, Facebook AI introduced a transformer-based model called [DEtection TRansformers (**DETR**)](https://arxiv.org/abs/2005.12872). DETR was trained on the state-of-the-art COCO dataset. It's used as the default model for object detection tasks on Hugging Face.

# Inference

To initialize the model, we call the **`object-detection`** pipeline:


Get an overview of how to use object detection using Hugging Face models.

Introduction

NLP

Computer Vision

Conclusion

Appendix

Object Detection

Overview