mmg63 Goto Github PK

albumentations

Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

autoencoder-cifar10

back-propagation-for-xor-representation-using-hidden-layer-net

Training using binary input is relatively slow; any unit that receives an input of zero for a particular pattern cannot learn that pattern. For the binary case, training took at most 3,000 epocs.

brew

🍺 The missing package manager for macOS (or Linux)

comp_8740

coordinate-attack

implementing coordinate attack at distributed systems

covid-19-prediction-project

This is a code for testing classification program for Covid-19 prediction and classification

darknet

Convolutional Neural Networks

data-science-ml-full-stack-2022

Everything you need to know for data science.

efficient_python_tricks_and_tools_for_data_scientists

Efficient Python Tricks and Tools for Data Scientists

fcnalexnet

FCN with AlexNet

forex_pairs_full_training_predicting_rnn

forex full train and prediction on pairs

graph-attention-networks-research

Graph attention networks research

hypergraph-convolution-and-attention-networks

Hypergraph convolution and attention networks research

hypergraph-project

Implementation and evaluation some idead in Hypergraph Convolutional networks

index_select

Return an index select of the torch tensors based on samples and labels matrix

install-whl-file-with-conda-commands

This is a tutorial for installing WHL files by anaconda environment.

introduction-to-different-classifiers

SIX diffenret Classifiers for six sample dataset

jumpflooding-taichi

2D & 3D Jump Flooding Algorithm and 2D Centroidal Voronoi Tessellation based on taichi

kmeans-neural-network-implemetation

Illustration of the K-means algorithm using the re-scaled Old Faithful data set. (a) Green points denote the data set in a two-dimensional Euclidean space. The initial choices for centers ?1 and ?2 are shown by the red and blue crosses, respectively. (b) In the initial E step, each data point is assigned either to the red cluster or to the blue cluster, according to which cluster centre is nearer. This is equivalent to classifying the points according to which side of the perpendicular bisector of the two cluster centred, shown by the magenta line, they lie on. (c) In the subsequent M step, each cluster centre is re-computed to be the mean of the points assigned to the corresponding cluster. (d)?(i) show successive E and M steps through to final convergence of the algorithm.

lightgcn-pytorch

The PyTorch implementation of LightGCN

lloyd

Constrained Lloyd Iteration for distributing 2D points

matrix-multiplication-using-spark

Matrix-Vector multiplication using MapReduce technique in python spark

maximumsubsequencearray

Finding the maximum contiguous subarray sum using a more sophisticated algorithm that runs in O ( n ) O(n) time.

mnist-superpixel

MWP for superpixel GNN classification

mscg-net

Multi-view Self-Constructing Graph Convolutional Networks with Adaptive Class Weighting Loss for Semantic Segmentation

object-detection-by-yolo-algorithm-using-pytorch

Object Detection by YOLO algorithm Using PyTorch

pgl

Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on PaddlePaddle

pygcn

Graph Convolutional Networks in PyTorch

pysnic

Python implementation of the SNIC superpixels algorithm