D

deep-learning

BIL635 - Modified Version of "Finding a Target with Zero-shot Invariant and Efficient Visual Search"

BIL635 - Modified Version of "Finding a Target with Zero-shot Invariant and Efficient Visual Search" v2

PyTorch reimplementation of CheXNet: multi-label classification and CAM/Grad-CAM localization of 14 thoracic diseases on ChestX-ray14, with full-resolution (1024px) ResNet50 training.

Introduction to classification using machine learning and deep learning (PyTorch, TensorFlow, Keras)

GPU-accelerated embedding server for RAG systems - CUDA, FastAPI, sentence-transformers | Serveur d'embeddings GPU ultra-rapide

https://ayinedjimi-consultants.fr

CS 7643 — Spring 2019 Project

Goal: learn more about the underlying deep learning model of GPT2: the Transformer model and, more broadly, the attention mechanism.

LLM quantization & benchmarking on GPU - GGUF, GPTQ, AWQ, bitsandbytes | Quantification et benchmark de modeles LLM sur GPU

https://ayinedjimi-consultants.fr

An OpenAI Gym for Shopping Cart Reinforcement Learning.

A simplified version of "Cliffworld" in an OpenAI Gym Environment

IF-Net fork + complete preprocessed ShapeNet archive (tar.xz bundles via git LFS). ShapeNet derivatives: non-commercial research use only.

Projet pédagogique en algorithmie et intelligence artificielle consistant à créer un agent (Kevin) capable de résoudre un labyrinthe.

Le projet explore plusieurs approches :

Génération de labyrinthes (DFS, Prim) Algorithmes de recherche de chemin (A*, Dijkstra) Apprentissage supervisé (Imitation Learning avec CNN) Apprentissage par renforcement (Deep Q-Network)

Des outils de visualisation permettent de générer des images et des GIFs montrant Kevin se déplacer dans le labyrinthe.

Projet réalisé dans le cadre de la formation Développeur en Intelligence Artificielle (Simplon).

Fine tunning of a deep neural network (using convolutionnal layers) to reconize a digit from a picture of an handwritten one.

✭ MAGNETRON ™ ✭: Detectron2 is a platform for PROXIA that can do POSE ESTIMATION, object detection, segmentation and other visual recognition tasks.

Automated LLM Benchmarking on GPU - tokens/sec, latency percentiles, VRAM profiling, multi-format support (HuggingFace, GGUF, GPTQ)

https://ayinedjimi-consultants.fr

3D Hand Pose Estimation using Multi-View CNNs

Academic NLP project focused on multilingual text summarization using Transformer-based deep learning models and natural language processing techniques.

Classifier to assign label to particle

A clean, modular implementation of Physics-Informed Neural Networks (PINNs) for solving the 1D and 2D wave equation using PyTorch.