Self-supervised vIsion Transformer (SiT)

An ongoing list of pandas quirks

Cool Python features for machine learning that I used to be too afraid to use. Will be updated as I have more time / learn more.

SC-CAM: Weakly-Supervised Semantic Segmentation via Sub-category Exploration (CVPR 2020)

This project aims to use the instance colorization model and apply it to video in a time consistent manner

This is my solution for the RecVis Challenge where i ended 1st on fine-grained classification on bird dataset

relevant Lab sessions & Homeworks in Machine Learning/Deep learning

this repo contains some machine learning scripts for various applications

kaggle challenge (https://www.kaggle.com/c/gan-getting-started/overview) , using Gan to generate Monet-style images.

private kaggle challenge : https://www.kaggle.com/c/mva-recvis-2020/

Evaluation of the Layoutlm model on the CORD dataset

Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018

The fastai book, published as Jupyter Notebooks