D

deep-learning

Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

GitHub: https://github.com/ultralytics/ultralytics

https://platform.ultralytics.com

Enterprise-Grade Real-Time Movie Recommendation Engine & Platform with Lakehouse Architecture, Multi-Stage Reranking, and Rust Core.

PyTorch model profiler for computing MACs and parameter counts to measure deep learning model complexity.

GitHub: https://github.com/ultralytics/thop

https://pypi.org/project/ultralytics-thop/

OpenAI CLIP for zero-shot image-text classification and embeddings with ResNet and Vision Transformer models.

GitHub: https://github.com/ultralytics/CLIP

https://www.ultralytics.com

Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

GitHub: https://github.com/ultralytics/yolov5

https://docs.ultralytics.com/yolov5/

PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.

GitHub: https://github.com/ultralytics/yolov3

https://docs.ultralytics.com/models/yolov3/

PyTorch sandbox for testing convolutional networks, ResNets, and other architectures on MNIST digits.

GitHub: https://github.com/ultralytics/mnist

https://ultralytics.com

WAVE deep learning for signal readout and reconstruction in full-waveform time-of-flight particle detectors.

GitHub: https://github.com/ultralytics/wave

https://ultralytics.com

Code accompanying the Bitbrain Open Access Sleep (BOAS) dataset: preprocessing, deep learning sleep staging, and technical validation.

Ce projet porte sur la conception d'une application de Computer Vision capable d'estimer l'âge d'une personne à partir d'une photographie.

L'objectif est d'explorer l'utilisation du Deep Learning appliqué aux images et de construire une chaîne allant du prétraitement des images jusqu'à l'inférence du modèle dans une application.

Travaux réalisés :

Préparation et organisation du dataset d'images. Prétraitement et normalisation des images. Mise en place du pipeline de préparation des données. Expérimentation d'une architecture de Deep Learning pour la prédiction de l'âge. Entraînement du modèle sur les données préparées. Évaluation des performances du modèle. Intégration du modèle dans une application permettant de réaliser une prédiction à partir d'une photographie.

Bu proje, kapalı ve siyah hazneli bir geri dönüşüm kutusunda atıkları otomatik sınıflandıran bir derin öğrenme modeli geliştirmek için hazırlanmıştır. Hedef sınıflar: plastik, cam, kağıt, metal, karton ve çöp.

Photo-realistic single-image super-resolution (SRGAN, x4) in TensorFlow/TensorLayer — refactored OO training/evaluation pipeline with research experiment branches.

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

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.

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

Intelligent VRAM/RAM swapping for LLM inference - Extension of KVortex | Offloading intelligent VRAM/RAM pour l'inference

https://ayinedjimi-consultants.fr

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

https://ayinedjimi-consultants.fr

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

https://ayinedjimi-consultants.fr

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

https://ayinedjimi-consultants.fr