PyTorch implementation of different types of autoencoders
-
Updated
Aug 22, 2018 - Python
PyTorch implementation of different types of autoencoders
Comparison between a linear and convolutional autoencoder.
Thesis work on Video Anomaly Detection
An initial phase segmentation using LinkNet on the skin lesion dataset managed by VISION AND IMAGE PROCESSING LAB, University of Waterloo. Public dataset on Kaggle at https://www.kaggle.com/datasets/mahmudulhasantasin/university-of-waterloo-skin-cancer-db-80-10-10/.
This repository explores the cutting-edge field of anomaly detection using deep learning, particularly through the implementation of autoencoders. Our approach revolves around the concept of reconstruction error, with a specific focus on leveraging the Mean Absolute Error (MAE) as the determining factor for anomalies within complex datasets.
A python package made to streamline the usage of Variational Autoencoders, understand the algorithm first before using this package
Deep k-means (Autoencoder + k-means clustering)
Exploring the importance of image resolution on self-supervised learning methods for multispectral imagery
Python autoencoder to remove blur from images
Project of Paraphrase Identification Based on Weighted URAE, Unit Similarity and Context Correlation Feature
My personal attempt to write well designed autoencoders-NNets.
Experiments with Variational Autoencoders in pytorch
Base space-time model with on top a classic autoencoder to perform video anomaly detection
Novel Pooling for anti-aliasing convolutional neural networks
A Recommender System that predicts ratings from 1 to 5 on MovieLens 1M Dataset
Linear Regression, Logistic Regression, Neural Networks, Convolutional Neural networks, Auto Encoders
Add a description, image, and links to the autoencoders topic page so that developers can more easily learn about it.
To associate your repository with the autoencoders topic, visit your repo's landing page and select "manage topics."