Archive | Deep Learning for Computer Vision

Plot of the First Nine Photos of Cats in the Dogs vs Cats Dataset

How to Classify Photos of Dogs and Cats (with 97% accuracy)

Develop a Deep Convolutional Neural Network Step-by-Step to Classify Photographs of Dogs and Cats The Dogs vs. Cats dataset is a standard computer vision dataset that involves classifying photos as either containing a dog or cat. Although the problem sounds simple, it was only effectively addressed in the last few years using deep learning convolutional […]

Continue Reading 40
How to Use Transfer Learning when Developing Convolutional Neural Network Models

How to Reuse Models for Computer Vision with Transfer Learning in Keras

Deep convolutional neural network models may take days or even weeks to train on very large datasets. A way to short-cut this process is to re-use the model weights from pre-trained models that were developed for standard computer vision benchmark datasets, such as the ImageNet image recognition tasks. Top performing models can be downloaded and […]

Continue Reading 10
Line Plots of Learning Curves for Baseline Model With Increasing Dropout, Data Augmentation, and Batch Normalization on the CIFAR-10 Dataset

How to Develop a CNN From Scratch for CIFAR-10 Photo Classification

Discover how to develop a deep convolutional neural network model from scratch for the CIFAR-10 object classification dataset. The CIFAR-10 small photo classification problem is a standard dataset used in computer vision and deep learning. Although the dataset is effectively solved, it can be used as the basis for learning and practicing how to develop, […]

Continue Reading 28
Loss-and-Accuracy-Learning-Curves-for-the-Baseline-Model-on-the-Fashion-MNIST-Dataset-During-k-Fold-Cross-Validation

How to Develop a Deep CNN for Fashion-MNIST Clothing Classification

The Fashion-MNIST clothing classification problem is a new standard dataset used in computer vision and deep learning. Although the dataset is relatively simple, it can be used as the basis for learning and practicing how to develop, evaluate, and use deep convolutional neural networks for image classification from scratch. This includes how to develop a […]

Continue Reading 8
Plot of a Subset of Images From the MNIST Dataset

How to Develop a CNN for MNIST Handwritten Digit Classification

How to Develop a Convolutional Neural Network From Scratch for MNIST Handwritten Digit Classification. The MNIST handwritten digit classification problem is a standard dataset used in computer vision and deep learning. Although the dataset is effectively solved, it can be used as the basis for learning and practicing how to develop, evaluate, and use convolutional […]

Continue Reading 6
Visualization of the Feature Maps Extracted From the First Convolutional Layer in the VGG16 Model

How to Visualize Filters and Feature Maps in Convolutional Neural Networks

Deep learning neural networks are generally opaque, meaning that although they can make useful and skillful predictions, it is not clear how or why a given prediction was made. Convolutional neural networks, have internal structures that are designed to operate upon two-dimensional image data, and as such preserve the spatial relationships for what was learned […]

Continue Reading 43
A Gentle Introduction to ImageNet and the Large Scale Visual Recognition Challenge (ILSVRC)

A Gentle Introduction to the ImageNet Challenge (ILSVRC)

The rise in popularity and use of deep learning neural network techniques can be traced back to the innovations in the application of convolutional neural networks to image classification tasks. Some of the most important innovations have sprung from submissions by academics and industry leaders to the ImageNet Large Scale Visual Recognition Challenge, or ILSVRC. […]

Continue Reading 0
A Gentle Introduction to 1x1 Convolutions to Reduce the Complexity of Convolutional Neural Networks

A Gentle Introduction to 1×1 Convolutions to Manage Model Complexity

Pooling can be used to down sample the content of feature maps, reducing their width and height whilst maintaining their salient features. A problem with deep convolutional neural networks is that the number of feature maps often increases with the depth of the network. This problem can result in a dramatic increase in the number […]

Continue Reading 20
Plot of Convolutional Neural Network Architecture With a Efficient Inception Module

How to Develop VGG, Inception and ResNet Modules from Scratch in Keras

There are discrete architectural elements from milestone models that you can use in the design of your own convolutional neural networks. Specifically, models that have achieved state-of-the-art results for tasks like image classification use discrete architecture elements repeated multiple times, such as the VGG block in the VGG models, the inception module in the GoogLeNet, […]

Continue Reading 25