Gain insights into image classification with PyTorch. Learn about data preprocessing, model training, fine-tuning, and deploying models using ONNX for real-world applications.

Introduction to PyTorch image classification-01.png

wfngenv.tar.gz

wfngenv

terminalenv

PyTorch is a machine learning framework used in a wide array of popular applications, including Tesla’s Autopilot and Pyro, Uber’s probabilistic modeling engine.

This course is an introduction to image classification using PyTorch’s computer vision models for training and tuning your own model. You’ll start with the fundamental concepts of applying machine learning and its applications to image classification before exploring the process of training your AI model. You’ll prepare data for intake by the computer vision model with image pre-processing, set up pipelines for training your model, and fine-tune the variables to improve predictive performance. You’ll finish by deploying the image classification model by converting to ONNX format and serving it via REST API.

By the end of this course, you’ll be able to build and deploy your own image classification models from scratch.

Getting Started with Image Classification with PyTorch

The **AutoAugment** is another standalone data augmentation technique that works similarly to `RandAugment`.

`AutoAugment` class complements other data augmentation techniques. Most of the top-performing models use `AutoAugment` in their training pipelines.

## The `AutoAugment` augmentation
The `AutoAugment` augmentation accepts a `PIL.Image` as input, which we can configure with the `config_str` variable.

However, the image transformations are bundled as policies and sub-policies instead. The `original` policy consists of 25 sub-policies. The `AutoAugment` module will iterate through each sub-policy and perform the corresponding image transformations.

Like before, we need to load the image with  `PIL` before data augmentation. Next, call the `auto_augment_transform` function from `timm.data.auto_augment` module:




The **AutoAugment** is another standalone data augmentation technique that works similarly to `RandAugment`.

`AutoAugment` class complements other data augmentation techniques. Most of the top-performing models use `AutoAugment` in their training pipelines.

# The `AutoAugment` augmentation
The `AutoAugment` augmentation accepts a `PIL.Image` as input, which we can configure with the `config_str` variable.

However, the image transformations are bundled as policies and sub-policies instead. The `original` policy consists of 25 sub-policies. The `AutoAugment` module will iterate through each sub-policy and perform the corresponding image transformations.

Like before, we need to load the image with  `PIL` before data augmentation. Next, call the `auto_augment_transform` function from `timm.data.auto_augment` module:




Learn to perform data augmentation with the AutoAugment technique.

Introduction

Basic Concepts

Augmentation

Loss

Training

Model Conversion

Deployment

Appendix

Conclusion

AutoAugment

The `AutoAugment` augmentation