A High-Quality Real Time Upscaler for Anime Video

Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!

XAI - An eXplainability toolbox for machine learning

Tensorflow implementation : U-net and FCN with global convolution

The Pytorch implementation of "Location-aware Upsampling for Semantic Segmentation" (LaU)

hq2x scaling algorithm updated to support RGBA

Checkerboard rendering with Magnum and OpenGL

DeepLearningで音楽をアップサンプリングします

Anime4K implemented in C# (with explanation)

A PyTorch implementation of CARAFE based on ICCV 2019 paper “CARAFE: Content-Aware ReAssembly of FEatures”

Implementation of Anime4K in Go.

An implementation of Anime4K in Python.

Native bindings to libsamplerate

Applied Statistics and Data Science: Computer vision course

Experimental port of Anime4K to metal

Drone using Fully Convolutional Network

This is an implementation of the CVPR 2017 paper - Deep Koalarization : Image Colorization using deep CNNs and Inception Resnet V2

Gaussian/Laplacian Pyramids OpenCV

Customer churn analysis for a telecommunication company

Upsampling Audio from 8khz to 16khz with a Resnet Architecture

Upsampling method for an input cloud using mls method of PCL 1.9.1

An implementation of a nodejs service that handles time-series data with downsampling and upsampling operations.

The given python code gives the data modeling and consists the following methods used: 1) Up sampling 2) Down sampling 3) Gridsearch for the selection of optimal combination of parameters 4) Application of Random Forest classifier 5) Dimensionality reduction using PCA

Implementation of FIR filter with time multiplexing and upsampling in Verilog.

Oversample 44.1kHz WAV file to 352.8kHz

Predicting truck sensor failure

Machine Learning Exercise: Exploring the concept of Upsampling / Oversampling and using KNN, Decision Tree and Random Forest to predict Class on Lymphography data from UCI.

This work predicts the buyers and non-buyers on an online shopping platform at a 92.4% accuracy, 89.8% precision and 95.3% recall performance.

Nearly complete submissions for Super Resolution Convolutional Neural Network (SRCNN) algorithm.