Tim Sainburg

Visualizing features, receptive fields, and classes in neural networks from "scratch" with Tensorflow 2. Part 4: DeepDream and style transfer

Posted on Tue 19 May 2020 in Neural networks • Tagged with VGG16, tensorflow, neural networks, convolutional neural networks, receptive fields

A few examples of feature visualization in convolutional neural networks with Tensorflow 2.0. In this part, we look at filtering images using different layers of a deep neural network. We also perform style transfer, by modifying an image to have similar layer activations as a second source image.

Visualizing features, receptive fields, and classes in neural networks from "scratch" with Tensorflow 2. Part 3: Reconstructing images from layer activations

Posted on Tue 19 May 2020 in Neural networks • Tagged with VGG16, tensorflow, neural networks, convolutional neural networks, receptive fields

A few examples of feature visualization in convolutional neural networks with Tensorflow 2.0. In this part, we look at how much information is contained about the original image by trying to reconstruct the image based upon layer activations.

Visualizing features, receptive fields, and classes in neural networks from "scratch" with Tensorflow 2. Part 2: Visualizing features and receptive fields

Posted on Tue 19 May 2020 in Neural networks • Tagged with VGG16, tensorflow, neural networks, convolutional neural networks, receptive fields

A few examples of feature visualization in convolutional neural networks with Tensorflow 2.0. In this part, we look at visualizing classes.

Visualizing features, receptive fields, and classes in neural networks from "scratch" with Tensorflow 2. Part 1: Visualizing classes

Posted on Tue 19 May 2020 in Neural networks • Tagged with VGG16, tensorflow, neural networks, convolutional neural networks, receptive fields

A few examples of feature visualization in convolutional neural networks with Tensorflow 2.0. In this part, we look at visualizing classes.