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

**HTTP GET** is a request method to retrieve data from the server. An HTTP GET method should have the following characteristics:
* **Safe**: It doesn't change or modify the state of the server.
* **Idempotent**: It doesn’t result in any side effects for the server.
* **Cacheable**: It allows caching of the HTTP response.

> **Note:** All safe methods are also idempotent.

We can easily build a simple HTTP GET API with the FastAPI framework.

# Import
Start by adding the following import statements:

from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware

app = FastAPI(
    title="Image Classification API",
    description="Working demo for building HTTP GET API server.",
    version="0.0.1"
)

print('The title of the application is:', app.title)

# Cross-origin resource sharing (CORS)
CORS allows a frontend to load resources from a backend with a different origin. The implementation for CORS in FastAPI is as follows:
1. Import the `CORSMiddleware`.
2. Define the list of origins.
3. Call the `add_middleware` function and pass in the corresponding arguments.

Learn to build GET and POST APIs using the FastAPI framework.

Introduction

Basic Concepts

Augmentation

Loss

Training

Model Conversion

Deployment

Appendix

Conclusion

HTTP Methods

Import

Cross-origin resource sharing (CORS)