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

# Detecting objects at one step

Extracting the regions from an image using the feature maps, then predicting the probability of these regions, whether they have an object inside or not, and finally sending the chosen high-probability regions to the classifier head seems to work quite accurately but slowly on the other hand.

Depending on the project we work on, we might need different expectations from our model regarding its speed. If we work on live videos, we will need a model able to process the frames at 30 FPS (the most common video setting, but it might be more or less than that) to catch the next frame coming from our live stream.


We might need more time to process a video that is not live but offline. Anyway, it wouldn't be the best option to process a one-minute video in 10 minutes.

In many other cases—live or offline videos and single or batch images—we usually prefer the fastest model, preferably without trading off the accuracy.

At this point, one-stage object detectors are lifesavers, removing the multiple steps and generating the region proposals with their class scores simultaneously.









Learn about the one-stage object detection architecture.

Introduction to One-Stage Object Detection Architectures

Before We Start

Basics of Convolutional Neural Networks

Popular Neural Network Architectures for Image Classification

Using PyTorch for Image Classification

Model Deployment

Basics of Object Detection

Two-Stage Object Detection Architectures

One-Stage Object Detection Architectures

YOLOv7 Model Train and Inference on Edge

Conclusion

Appendix

Introduction to One-Stage Object Detection Architectures

Detecting objects at one step