We start by defining the variable normalize with the mean and standard deviations of each of the channel (red, green, and blue) in the dataset.We define a function data_loader that returns either train/validation data or test data depending on the arguments.Torchvision is a library that provides easy access to tons of computer vision datasets and methods to pre-process these datasets in an easy and intuitive manner We will also be defining a variable device so that the program can use GPU if available import numpy as npįrom import SubsetRandomSamplerĭevice = vice('cuda' if _available() else 'cpu') We'll be working mainly with torch (used for building the model and training), torchvision (for data loading/processing, contains datasets and methods for processing those datasets in computer vision), and numpy (for mathematical manipulation). Here's the list of classes in the CIFAR-100: Class List for the CIFAR-100 dataset Importing the libraries Each image comes with a "fine" label (the class to which it belongs) and a "coarse" label (the superclass to which it belongs). The 100 classes in the CIFAR-100 are grouped into 20 superclasses. There are 500 training images and 100 testing images per class. This dataset is just like the CIFAR-10, except it has 100 classes containing 600 images each. In this article, we'll be using the CIFAR-100 dataset. Sourceīefore building the model, one of the most important things in any Machine Learning project is to load, analyze, and pre-process the dataset. You can read more about the network in the official paper here VGG16 architecture. All the convolutional layers consists of 3x3 filters. It normally consists of 16 convolutional layers but can be extended to 19 layers as well (hence the two versions, VGG-16 and VGG-19). It was developed by Simonyan and Zisserman. Then, we will implement VGG16 (number refers to the number of layers, there are two versions basically VGG16 and VGG19) from scratch using PyTorch and then train it our dataset along with evaluating it on our test set to see how it performs on unseen dataīuilding on the work of AlexNet, VGG focuses on another crucial aspect of Convolutional Neural Networks (CNNs), depth. We will then explore our dataset, CIFAR100, and load into our program using memory-efficient code.
#Nn sequential use series
You can see the previous articles in the series on my profile, mainly LeNet5 and AlexNet.Īs before, we will be looking into the architecture and intuition behind VGG and how the results were at that time. Continuing my series on building classical convolutional neural networks that revolutionized the field of computer vision in the last 1-2 decades, we next will build VGG, a very deep convolutional neural network, from scratch using PyTorch.
0 kommentar(er)
