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

This lesson contains a step-by-step guide to integrate our image classification model into the FastAPI framework. We’ll serve it as an HTTP POST API.

We’ll reuse some of the code from our previous lesson to perform the following operations:
* Create the FastAPI instance.
* Add the CORS middleware.


from fastapi import FastAPI, File, UploadFile
from fastapi.middleware.cors import CORSMiddleware

import torch
from PIL import Image
import torchvision.transforms as transforms
import timm
import io

app = FastAPI(
    title="Image Classification API",
    description="Working demo for weather classification.",
    version="0.0.1"
)

app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

print('The title of the application is:', app.title)
print('The application contains the following middleware:', app.user_middleware)

# Startup event
The startup event handler is the ideal place to load our model. Implement it as follows:


Learn to integrate inference code as a REST API.

Introduction

Basic Concepts

Augmentation

Loss

Training

Model Conversion

Deployment

Appendix

Conclusion

REST API Integration

Startup event