clementapa

APAVOU Clément's repositories

CelebFaces_Attributes_Classification

This repository is related to a project of the Introduction to Numerical Imaging (i.e, Introduction à l'Imagerie Numérique in French), given by the MVA Masters program at ENS-Paris Saclay. It was entirely build from scratch and contains code in PyTorch Lightning to train and then use a neural network for image classification. We used it to create a classifier allowing semantic attributes classification of faces with the dataset CelebA-HQ.

Language:Jupyter NotebookMIT25 2 3

COTS_detection

Building an object detector to protect the Great Barrier Reef: Kaggle challenge TensorFlow - Help Protect the Great Barrier Reef.

Language:Jupyter NotebookMIT500

orangutan-image-video-detection

This is repository containing a full pipeline (from annotation to training) for building an orangutans detector.

Language:Python400

Prostate-Cancer-Image-Classification

Deep Learning for medical imaging kaggle challenge for the MVA master 2021-2022. Classification of ISUP grades from Whole Slide Images.

Language:Jupyter Notebook400

English_Language_Learning_NLP_Transformers

For me, the goal of this project was to handle transformers fine tuning by implementing and applying optimization training techniques using limited computational resources.

Language:Python1 10

Projet_Maillage_et_Elements_Finis

Language:Python100

RecvisProject

In this project, we propose to study Vision Transformers trained using the Barlow Twins self-supervised method, and compare the results with DINO. We demonstrate the effectiveness of the Barlow Twins method by showing that networks pretrained on the small PASCAL VOC 2012 dataset are able to generalize well. Authors: Apavou Clément & Zucker Arthur

Language:PythonGPL-3.0100