tf.image.resize_images has aliasing when downsampling and does not have gradients for bicubic mode. This implementation fixes those problems.

PyTorch implementation of the mixture distribution family with implicit reparametrisation gradients.

An automatic differentiation library written in Python with NumPy vectorization.

Software pipeline to identify lane boundaries from a video streaming from a front-facing camera on a car using color transform and gradient

Neural network visualization tool after an optional model compression with parameter pruning: (integrated) gradients, guided/visual backpropagation, activation maps for the cao model on the IndianPines dataset

Predicting wine quality using regression on the well-known UCI data set and more

Object detection and tracking in videos using HOG+SVM and Kalman Filter uses Filterpy,Numpy and Sci-kit learn

This tool can be used to find the most influential words on a document. We define most influential as the words that influence a trained classifier the most to give it a particular classification.

Avoiding the vanishing gradients problem by adding random noise and batch normalization

Gradient fills for Matplotlib charts

First assignment in ׳Deep Learning for Texts and Sequences' course (using NumPy only) by Prof. Yoav Goldberg at Bar-Ilan University

Take a list of rgb color values and insert a number of colors of your choice in between each given color pair in a smooth transition.

Python Library for creating and training CNNs. Implemented from scratch.

A pipeline to detect road lane lines in images from a monocular camera

Demonstrate how to do backpropagation using an example of BatchNorm-Sigmoid-MSELoss network with a detailed derivation of gradients and custom implementations.

This repository contains several algorithms that are covered in Computer Vision Lab.

Advanced Lane Finding (project 2 of 9 from Udacity Self-Driving Car Engineer Nanodegree)

Master thesis for the MSc. Artificial Intelligence at the Universiteit van Amsterdam, 2019