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 **loss function** evaluates how well our algorithm models our datasets. It calculates the difference between the predicted output and the ground truth of a single training example. It’s also known as the error function.
 
It represents how far off the predicted output is from the expected output. We can think of the loss function as the penalty for failing to get the expected output.

Most optimization problems use loss functions. The main goal is to minimize the loss, which will maximize the accuracy. The lower the loss, the better our model is.

Given the following synthetic data, we can calculate the total loss for price predictions for metals ($/troy ounce) by:


* Subtracting between predictions and actual value.
* Getting the absolute value of the number.

|Metals|Predictions|Actual value|Total Loss|
|-|-|-|-|
|Gold Platinum|1995.80 998.32|1998.30 999.34|3.52 (2.50 for Gold, 1.02 for Platinum)|
|Gold Platinum|2003.12 999.34|1998.30 999.34|4.82 (4.82 for Gold, 0 for Platinum)|
|Gold Platinum|1998.05 995.81|1998.30 999.34|3.78 (0.25 for Gold, 3.53 for Platinum)|

> **Note**: A loss function is direction-agnostic. 

The Pytorch Image Model provides the following standard loss functions:
* `LabelSmoothingCrossEntropy`
* `SoftTargetCrossEntropy`

## The `LabelSmoothingCrossEntropy` function
The `LabelSmoothingCrossEntropy` function works the same way as negative log-likelihood loss (NLL loss) with an extra `smoothing` argument. The formula for NLL loss is:

$$
L(y) = -log(y)
$$

The following graph shows the range of negative log-likelihood:

The **loss function** evaluates how well our algorithm models our datasets. It calculates the difference between the predicted output and the ground truth of a single training example. It’s also known as the error function.
 
It represents how far off the predicted output is from the expected output. We can think of the loss function as the penalty for failing to get the expected output.

Most optimization problems use loss functions. The main goal is to minimize the loss, which will maximize the accuracy. The lower the loss, the better our model is.

Given the following synthetic data, we can calculate the total loss for price predictions for metals ($/troy ounce) by:


* Subtracting between predictions and actual value.
* Getting the absolute value of the number.

|Metals|Predictions|Actual value|Total Loss|
|-|-|-|-|
|Gold Platinum|1995.80 998.32|1998.30 999.34|3.52 (2.50 for Gold, 1.02 for Platinum)|
|Gold Platinum|2003.12 999.34|1998.30 999.34|4.82 (4.82 for Gold, 0 for Platinum)|
|Gold Platinum|1998.05 995.81|1998.30 999.34|3.78 (0.25 for Gold, 3.53 for Platinum)|

> **Note**: A loss function is direction-agnostic. 

The Pytorch Image Model provides the following standard loss functions:
* `LabelSmoothingCrossEntropy`
* `SoftTargetCrossEntropy`

# The `LabelSmoothingCrossEntropy` function
The `LabelSmoothingCrossEntropy` function works the same way as negative log-likelihood loss (NLL loss) with an extra `smoothing` argument. The formula for NLL loss is:

$$
L(y) = -log(y)
$$

The following graph shows the range of negative log-likelihood:

Learn the basic concepts of loss functions.

Introduction

Basic Concepts

Augmentation

Loss

Training

Model Conversion

Anomaly Detection in Medical Images: Python, TF, and PyTorch

Deployment

Appendix

Conclusion

Loss Functions

Metals	Predictions	Actual value	Total Loss
Gold Platinum	1995.80 998.32	1998.30 999.34	3.52 (2.50 for Gold, 1.02 for Platinum)
Gold Platinum	2003.12 999.34	1998.30 999.34	4.82 (4.82 for Gold, 0 for Platinum)
Gold Platinum	1998.05 995.81	1998.30