Explore projects

Encoder decoder architecture for semantic segmentation .Encoder consists of a pretrained resnet18 and the decoder is composed of multiple layers of transposed convolution.

This is mmdetection library that implements deformable convolution neural networks. With this library I can use attention layers with mmdetection implemented in pytorch

Code, information, ideas and other shenanigans concerning 2018s RecSys challenge.

Machine Learning models for classifying text according to the 17 Sustainable Development Goals

fully-connected autoencoder in Pytorch for the CIFAR 10

Sentiment Analysis on Amazon review data

This is the test task for the project Self-Supervised Autoencoder

The CNN model with cifar10 dataset for 2 versions: 1. normalize data with mean-0 and standard deviation-1 2. samples that lie in the unit cube