numancelik34

AdaptSegNet

Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)

anomaly-detection

Anomaly detection is a common problem that is applied to machine learning/deep learning research. Here we will apply an LSTM autoencoder (AE) to identify ECG anomaly detections. In our experiments, anomaly detection problem is a rare-event classification problem. Therefore we will train our LSTM AE with major class, then we would have a higher mean squared error when model sees a minor class in the dataset.

Awesome-Self-Supervised-Papers

Paper bank for Self-Supervised Learning

cell-segmentation

In this work, cell segmentation was carried out through U-net. Segmented microscopic images were introduced to the neural network model with an annotation tool using OpenCV.

Deep-Channel

To follow

GAN_TimeSeries_Classification

TEST1:This is the test repo for time series classification using GAN.

ML-Oxford-2020

mvts_transformer

Multivariate Time Series Transformer, public version

TimeSeries-GAN

Generation of Time Series data using generatuve adversarial networks (GANs) for biological purposes.

vision-transformer-pytorch

Pytorch version of Vision Transformer (ViT) with pretrained models. This is part of CASL (https://casl-project.github.io/) and ASYML project.

numancelik34/TimeSeries-GAN

Generation of Time Series data using generatuve adversarial networks (GANs) for biological purposes.

numancelik34/anomaly-detection

Anomaly detection is a common problem that is applied to machine learning/deep learning research. Here we will apply an LSTM autoencoder (AE) to identify ECG anomaly detections. In our experiments, anomaly detection problem is a rare-event classification problem. Therefore we will train our LSTM AE with major class, then we would have a higher mean squared error when model sees a minor class in the dataset.

numancelik34/vision-transformer-pytorch

Pytorch version of Vision Transformer (ViT) with pretrained models. This is part of CASL (https://casl-project.github.io/) and ASYML project.

numancelik34/AdaptSegNet

Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)

numancelik34/Awesome-Self-Supervised-Papers

Paper bank for Self-Supervised Learning

numancelik34/cell-segmentation

In this work, cell segmentation was carried out through U-net. Segmented microscopic images were introduced to the neural network model with an annotation tool using OpenCV.

numancelik34/Deep-Channel

To follow

numancelik34/GAN_TimeSeries_Classification

TEST1:This is the test repo for time series classification using GAN.

numancelik34/ML-Oxford-2020

numancelik34/mvts_transformer

Multivariate Time Series Transformer, public version

numancelik34/pretrained-models.pytorch

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

numancelik34/pytorch-fcn

PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

numancelik34/pytorch-segmentation-toolbox

PyTorch Implementations for DeeplabV3 and PSPNet

numancelik34/semantic-segmentation-pytorch

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

numancelik34/torchcv

A PyTorch-Based Framework for Deep Learning in Computer Vision

numancelik34/vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch