Gain insights into using PyTorch for image classification and detection, delve into model implementation, and explore deployment on edge devices with ONNX and OpenVINO.

Image Classification and Object Detection using CNNs-01.png

pytorch.tar.gz

Basics_Of_CNN-ex1

Basics_Of_CNN-ex2

Basics_Of_CNN-vgg16

Basics_Of_CNN-inceptionv1

Basics_Of_CNN-residuals

Basics_Of_CNN-depthwise

Train-data

Train-training

Train-trainingFT

Train-transfer

deploy-onnx

deploy-openvino

deploy-comparison

prepare_dataset_openimages

train_yolov7

inference_yolov7

onnx_yolov7

Image classification and object detection have gained widespread use in recent years. Content categorization and monitoring, disease diagnosis from medical images, identifying terrain in satellite images, and detecting road elements for self-driving cars are classification problems at their core. PyTorch is a popular framework for these tasks—offering a useful mix of user-friendliness, deep learning functionalities, customization, and optimization.

In this course, you will cover the fundamentals of classification and object detection models and apply them to actual datasets using PyTorch. You’ll learn popular architectures and how to implement and fine-tune them for better results. Finally, you’ll learn to convert models to ONNX and OpenVINO to deploy in edge devices.

By the end of this course, you will have acquired the necessary skills to be able to use PyTorch for image identification and object detection in real-world applications

Using PyTorch for Image Classification and Object Detection

# Underfitting & overfitting

**Underfitting** refers to the model's failure to learn. Somehow, the model can't improve itself, and we see that training and validation accuracy get stuck without getting any better with further iterations. A primary reason for this is to have vanishing or exploding gradients. As we mentioned, both problems are about having bad values to update weights, which causes the learning to stop.

> **Note:** The figures below show us what happens if we set `LEARNING_RATE = 1.0`.

The graphs seem awful, and the model can't learn anything.  When we check the gradients, they shrink significantly to 10–28. It's because even though we select an excellent activation function to fight the vanishing gradient problem, we multiply our gradients with a considerable value, which makes a significant impact when updating our weights and kills them (making them near zero). So we try to carry the input signal until the output layer gets closer to 0.


On the other hand, if we set `LEARNING_RATE = 0.0001`, we obtain the following results:

Learn fine-tuning techniques to improve a model’s performance.


Fine-Tune a Model

Fine-Tuning Models

Before We Start

Basics of Convolutional Neural Networks

Cats vs Dogs Classification with Convolutional Neural Networks

Popular Neural Network Architectures for Image Classification

Using PyTorch for Image Classification

Model Deployment

Using a PyTorch Model in JavaScript with ONNX

Basics of Object Detection

Two-Stage Object Detection Architectures

One-Stage Object Detection Architectures

YOLOv7 Model Train and Inference on Edge

Conclusion

Appendix

Building a System for Safety Helmet Detection Based on YOLOv5

Fine-Tuning Models

Underfitting & overfitting