You can master Computer Vision, Deep Learning, and OpenCV - PyImageSearch
Keras and TensorFlowLearn how to successfully apply Deep Learning to Computer Vision with Keras and TensorFlow using my free Keras tutorials and guides.
The LeNet architecture is a seminal work in the deep learning community, first introduced by LeCun et al. in their 1998 paper, Gradient-Based Learning Applied to Document Recognition. As the name of the paper suggests, the authors’ motivation behind implementing…
Read More of LeNet: Recognizing Handwritten Digits
In our previous tutorial, we discussed LeNet, a seminal Convolutional Neural Network in the deep learning and computer vision literature. VGGNet, (sometimes referred to as simply VGG), was first introduced by Simonyan and Zisserman in their 2014 paper, Very Deep…
Read More of MiniVGGNet: Going Deeper with CNNs
One concept we have not discussed yet is architecture visualization, the process of constructing a graph of nodes and associated connections in a network and saving the graph to disk as an image (i.e., PNG, JPG, etc.). Nodes in the…
Read More of Visualizing network architectures using Keras and TensorFlow
In this tutorial, you will implement a CNN using Python and Keras. We’ll start with a quick review of Keras configurations you should keep in mind when constructing and training your own CNNs. We’ll then implement ShallowNet, which as the…
Read More of A gentle guide to training your first CNN with Keras and TensorFlow
In our previous tutorial, you learned how to train your first Convolutional Neural Network using the Keras library. However, you might have noticed that each time you wanted to evaluate your network or test it on a set of images,…
Read More of Save your Keras and TensorFlow model to disk
Now that we have implemented neural networks in pure Python, let’s move on to the preferred implementation method — using a dedicated (highly optimized) neural network library such as Keras. Today, I will discuss how to implement feedforward, multi-layer networks…
Read More of Implementing feedforward neural networks with Keras and TensorFlow
In this tutorial, you will learn how to generate image batches of (1) normal images and (2) adversarial images during the training process. Doing so improves your model’s ability to generalize and defend against adversarial attacks. Last week we learned…
Read More of Mixing normal images and adversarial images when training CNNs
In this tutorial, you will learn how to defend against adversarial image attacks using Keras and TensorFlow. So far, you have learned how to generate adversarial images using three different methods: Adversarial images and attacks with Keras and TensorFlow Targeted…
Read More of Defending against adversarial image attacks with Keras and TensorFlow
In this tutorial, you will learn how to perform adversarial attacks using the Fast Gradient Sign Method (FGSM). We will implement FGSM using Keras and TensorFlow. A dataset of images and their labels is critical for understanding adversarial attacksusing FGSM.…
Read More of Adversarial attacks with FGSM (Fast Gradient Sign Method)
