0% completed

All LessonsFree Lessons (4)

Introduction

Overview of Image Classification Image Classification Techniques Image Classification Metrics PyTorch Image Model Framework

Basic Concepts

Create Model List and Search Supported Models Dataset Format Load and Preprocess Images Prediction Using Pre-trained Resnet50 Prediction Using Pre-trained EfficientNet Quiz (Basic)Exercise (Basic)

Augmentation

Training a Neural Network with Augmentation Mixup and Cutmix RandAugment Random Erase AutoAugment Random Resized Crop and Interpolation Quiz (Augmentation)

Loss

Loss Functions Asymmetric Loss Jensen-Shannon Divergence and Cross-Entropy Loss Quiz (Loss)

Training

Training Workflow ResNet50 EfficientNet Fine-tuning Custom Model Training with an EMA (Exponential Moving Average)Quiz (Training)Exercise (Training)

Model Conversion

Serving a Pytorch Model

Convert PyTorch Model into an ONNX Model

Serving an ONNX Model

Convert ONNX into a Tensorflow Model

Serving a TensorFlow Model

Convert a TensorFlow Model into a TFLite Model

Serving a TFLite Model

Quiz (Model Conversion)

Exercise (Model Conversion)

Project

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

Deployment

Overview of FastAPI HTTP Methods REST API Integration Quiz (Deployment)Exercise (Deployment)

Appendix

Virtual Environment Python Packages Package Installation Training Arguments Deployment Dependencies

Conclusion

Getting Started with Image Classification with PyTorch/

...

/

Serving an ONNX Model

Serving an ONNX Model

Learn to use an ONNX model for inference.

We'll cover the following...

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

We will use the onnxruntime package. It’s a cross-platform machine learning accelerator for inference and training.

Utility functions

Define the following utility functions:

softmax: This is

...