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

We can use the TFLite model for inference on our datasets.

The `tensorflow` package supports TFLite and comes with built-in functions for inference.


# Utility functions
We’ll need the `softmax` utility function to convert the tensor output to probabilities. Implement it by entering the following code:


import numpy as np
import tensorflow as tf
import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

def softmax(vec):
    exponential = np.exp(vec)
    probabilities = exponential / np.sum(exponential)
    return probabilities


# test softmax function
dummy_vec = np.array([1.5630065, -0.24305986, -0.08382231, -0.4424621])
print('The output probabilities after softmax is:', softmax(dummy_vec))

> **Note:** The `softmax` utility function will convert the model prediction into probabilities that sum to 1.

# Load checkpoint
Create a new instance of `tf.lite.Interpreter` and load the TFLite model. After that, call the `allocate_tensors` function to allocate tensors.

Learn to use a TFLite model for inference.

Introduction

Basic Concepts

Augmentation

Loss

Training

Model Conversion

Deployment

Appendix

Conclusion

Serving a TFLite Model

Utility functions