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

From a high-level point of view, the entire training process consists of the following steps:


# Initialization
1. Initialize the parameters for distributed training. This step is only applicable if `args.distributed` is `True`.
2. Initialize a value as the seed. This ensures that the results are reproducible.
3. Create the desired model architecture with the `timm.create_model` function.
4. Initialize the configuration for datasets based on the default setting of the model. Each model has its own setting, which typically contains the following information:

```
{
  'url': '',
  'num_classes': 1000,
  'input_size': (3, 224, 224),
  'pool_size': (7, 7),
  'crop_pct': 0.875,
  'interpolation': 'bicubic',
  'mean': (0.485, 0.456, 0.406),
  'std': (0.229, 0.224, 0.225),
  'first_conv': 'conv1',
  'classifier': 'fc'
}
```

5. Determine the number of augmentation batch splits, then split the data into `N` groups. Half of the groups are without any augmentation, while the other half is. The training script uses `N` separate batch normalization layers for normalization. As a result, our training will now have separate batch normalization layers for each augmentation split.

> **Note**: If the split is 0, the script will apply all the relevant data augmentations to the complete batch. After that, it will use the batch to define batch normalization statistics, such as variance and mean.

Learn about the training workflow in the Pytorch Image Model.

Introduction

Basic Concepts

Augmentation

Loss

Training

Model Conversion

Deployment

Appendix

Conclusion

Training Workflow

Initialization