Latest Posts

Accelerating deep neural networks with tensor decompositions
My PyTorch implementation for tensor decomposition methods on convolutional layers.

Pruning deep neural networks to make them fast and small
My PyTorch implementation of [1611.06440 Pruning Convolutional Neural Networks for Resource Efficient Inference].

Visualizations for regressing wheel steering angles in self driving cars

Class activation maps in Keras for visualizing where deep learning networks pay attention

A few notes on using the Tensorflow C++ API
If you are unfamiliar with bazel, then there are some quirks in getting TensorFlow to work with OpenCV, optimizations turned on, and with building shared libraries.

Visualizing CNN filters with keras
Here is a utility I made for visualizing filters with Keras, using a few regularizations for more natural outputs.
You can use it to visualize filters, and inspect... 
Smoothing images with the Mumford Shah functional
Try out my python implementation for minimizing the Mumford Shah functional.

Simple Image saliency detection from histogram backprojection

Image Fisher Vectors In Python
Although the state of the art in image classification (while writing this post) is deep learning, Bag of words approaches still perform well on many image datasets.

Bag of visual words for image classification

Refining the Hough Transform with CAMSHIFT
The Circular Hough Transform result is often not very accurate due to noise\details\occlusions.