AlexNet: Implementation from Scratch

A PyTorch series for people starting with Deep Learning. Following an implementation-based approach of various well-known architectures.

Introduction

The Alexnet architecture was a breakthrough at the time of its publication, achieving minimal loss on the ImageNet classification task. It uses sequential convolutional blocks with some fully connected layers for the classification task. In this article, we understand the architecture and code it in PyTorch.

Architecture

The flowchart shows the basic outline of the process.

alexnet architecture architectures article classification convolutional-network deep learning image image-captioning imagenet implementation loss machine learning people publication pytorch series