Tag Archives: neural networks

Compressing VGG for Style Transfer

32-bit float (no quantization) 8-bit 7-bit 6-bit 5-bit 4-bit 3-bit 2-bit 1-bit I recently implemented pastiche—discussed in a prior post—for applying neural style transfer. I encountered a size limit when uploading the library to PyPI, as a package cannot exceed … Continue reading

Tagged , , , , | Leave a comment

Style Transfer Medley

I used the pastiche style transfer program—discussed in a prior post—to create the video shown above. The content image is a photo I took in Boston in 2015, and the style images were randomly sampled from the test images of … Continue reading

Tagged , , , | Leave a comment

🎨 pastiche

pastiche A literary, artistic, musical, or architectural work that imitates the style of previous work. ―Merriam-Webster dictionary I recently implemented pastiche, a PyTorch-based Python program for applying neural style transfer [1]. Given a content image C and a style image … Continue reading

Tagged , , , , | Leave a comment

More Bézier Walks in Neural Networks

The videos above were generated using the same script described in an earlier post.

Tagged , , | Leave a comment

Random Bézier Walk in a Random Neural Network

The video above was generated using neuralart.

Tagged , , | Leave a comment

Neural Art

neuralart is a Python library and utility for rendering generative art from a randomly initialized neural network. It’s based on the following blog posts and pages from studio otoro. Neural Network Generative Art in Javascript Generating Abstract Patterns with TensorFlow Neurogram … Continue reading

Tagged , | Leave a comment