An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019).

An example of visualization of weights and output of convolutional layers

Rede Neural Convolucional para reconhecimento de gestos em LIBRAS (Alfabeto) Projeto 01/2019 - Ciência da Computação (Universidade Anhembi Morumbi)

Multi class audio classification using Deep Learning (MLP, CNN): The objective of this project is to build a multi class classifier to identify sound of a bee, cricket or noise.

A look at some simple autoencoders for the Cifar10 dataset, including a denoising autoencoder. Python code included.

Implementation of the generalized 2D convolution with dilation from scratch in Python and NumPy

Using Tensorflow to classify the NIST Dataset 19 (Handwriting)

A 1D implementation of a deformable convolutional layer in PyTorch with a few tricks.

Tensorflow implementation for 'LCNN: Lookup-based Convolutional Neural Network'. Predict Faster using Models Trained Fast with Multi-GPUs

Octave convolution

Pytorch Implementations of Common modules, blocks and losses for CNNs specifically for segmentation models

A Python implementation of the InverSynth method (Barkan, Tsiris, Koenigstein, Katz)

Sub-Pixel Convolutional Layer with Tensorflow/Keras

In this project we have explored the use of imaging time series to enhance forecasting results with Neural Networks. The approach has revealed itself to be extremely promising as, both in combination with an LSTM architecture and without, it has out-performed the pure LSTM architecture by a solid margin within our test datasets.

Code for Spectral Norm of Convolutional Layers with Circular and Zero Paddings and Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration

Implementation of SoundtStream from the paper: "SoundStream: An End-to-End Neural Audio Codec"

A simple single object detection using Convolutional Neural Network, (CNN).

Multi-scale version of ROCKET: a random convolutional kernel machine learning method

Visualization of the filters of VGG16, via gradient ascent in input space.

GPU-accelerated Neural Network layers using Approximate Multiplications for PyTorch