Mohamed Ali Souibgui

opik. Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

docling. Get your documents ready for gen AI

easymcp. TypeScript

SVGCraft. [WACV 2026 Round 1] Beyond Single Object Text-to-SVG Synthesis with Comprehensive Canvas Layout

next-level-bert. Python

awesome-comics-understanding. The official repo of the Comics Survey: "A missing piece in Vision and Language: A Survey on Comics Understanding"

awesome-diffusion-categorized. collection of diffusion model papers categorized by their subareas

einops. Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

VAR. [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

annotation. annotation system for labelling bounding boxes using openCV

GraphKD. [ICDAR 2024] (Best Student Paper🏆) Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation

Hyper-Modulation. Official Implementation for "Transferring Unconditional to Conditional GANs with Hyper-Modulation" CVPRW 22 https://arxiv.org/abs/2112.02219

table-transformer. Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.

fiftyone. Refine high-quality datasets and visual AI models

transformer-inertial-poser. Python implementation accompanying the Transformer Inertial Poser paper at SIGGRAPH Asia 2022

EgoLocate. A real-time system that simultaneously captures human pose, reconstructs the scene in sparse 3D points, and localizes the human in the scene with 6 IMUs and a body-worn phone camera

LabelAdaptiveMixup-SER. Python

PFL-DocVQA-Competition. Python

AvatarPoser. Official Code for ECCV 2022 paper "AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing"

ControlNet. Let us control diffusion models!

docile. DocILE: Document Information Localization and Extraction Benchmark

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

stable-diffusion. A latent text-to-image diffusion model

Structured-Diffusion-Guidance. Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis

latent-diffusion. High-Resolution Image Synthesis with Latent Diffusion Models

handwriting-synthesis. Handwriting Synthesis with RNNs ✏️

doc2graph. Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.

idl_data. OCR Annotations from Amazon Textract for Industry Documents Library

ivy. Convert Machine Learning Code Between Frameworks

GACNN. Generative Adverserial Convolutional Neural Network

jNMF. Discovering De-similarities of Modular Structure Between Tumor Cells and Normal Cells by Integrating Multiple Data Sources Through Joint Non-Negative Matrix Factorization

dct-dft-fft-craft. DCT-DFT-FFT Based Method for Text Detection in Underwater Images

HAGNN. Gene Selection of Microarray Data using Heatmap Analysis and Graph Neural Network

Machine-Learning. In the summer 2020, I have get a chance to learn machine learning from Andrew Ng, coursework organised by Stanford University. Here, I am going to upload all the assignment done by me during the coursework.

HandsonML. The Machine Learning Tsunami

DCN-DQN-TDF-IDF. A Comprehensive Scheme for Tattoo Text Detection

Assignment_AIforManufacturing_Quality_Assurance_OpGAN. This repository contains the assignments related to Pix2Pix image translation with GAN

Deep_Learning_with_Python. The deep in deep learning isn’t a reference to any kind of deeper understanding achieved by the approach; rather, it stands for this idea of successive layers of representations......

SegIris. a procedure of iris segmentation is presented which was designed on the basis of the natural properties of the iris.

DocSegTr. A Bottom-Up Instance Segmentation Strategy for segmenting document instances using Transformers

Sim-GAN. Missing Value Estimation of Microarray Data using Sim-GAN

ContrastiveSupervisedDistillation. This repo contains the code of "Contrastive Supervised Distillation for Continual Representation Learning", Tommaso Barletti, Niccolò Biondi, Federico Pernici, Matteo Bruni, and Alberto Del Bimbo, ICIAP2021

MAE-pytorch. Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

ncs_metric. Is an image worth five sentences? A new look into semantics of image-text matching - WACV 2022

GoodNews. Good News Everyone! - CVPR 2019

SelectiveTextStyleTransfer. ICDAR 2019

DocSegTr. A Bottom-Up Instance Segmentation Strategy for segmenting document instances using Transformers

TextRecognitionDataGenerator. A synthetic data generator for text recognition

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

semantic_adaptive_margin. WACV 2022 Paper - Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

object-bias. Let there be clock in the beach - WACV 2022

vissl. VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

Swin-Transformer. This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

the-gan-zoo. A list of all named GANs!

Fractals. Matlab project

DIGITS. Deep Learning GPU Training System

caffe. Caffe: a fast open framework for deep learning.

tensorflow. Computation using data flow graphs for scalable machine learning

DeepRosetta. An universal deep learning models conversor

LBP-for-word-spotting. Local Binary Pattern for historical handwritten documents

nmp_qc. Neural Message Passing for Computer Vision

tiny-dnn. header only, dependency-free deep learning framework in C++11

DeepSketchHashing. Deep Sketch Hashing source code

Lenet_nicicon. LeNet applied to NicIcon dataset

Hallucination.

sem-pcyc. PyTorch implementation of the paper "Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval", CVPR 2019.

GoodNews. Good News Everyone! - CVPR 2019

kornia. Open Source Differentiable Computer Vision Library for PyTorch

doodle2search. Doodle to Search: Practical Zero Shot Sketch Based Image Retrieval

online-cv. A minimal Jekyll Theme to host your resume (CV)

GCN_classification. Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval

swav. PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

allanlab. Allan Lab website

doodle2search.github.io. Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval

SigNet. SigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification

Multilabel-Fashion-MNIST. Multilabel-Fashion-MNIST

Naive_text_dataset. A naive approach that generates images and labels of text in simple colored background.

phoc_clf. Python

Pytorch-yolo-phoc. Implementation on pytorch of the code from the ECCV 2018 paper - Single Shot Scene Text Retrieval

Fine_Grained_Clf. Based on the WACV 2020 paper - Fine Grained Classification and Retrieval by Combining Visual and Locally Pooled Textual Features

GCN_classification. Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval

synth_doc_generation. Official PyTorch Implementation of DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis - ICDAR 2021

snake. Code for "Deep Snake for Real-Time Instance Segmentation" CVPR 2020 oral

StacMR. Scene Text Aware Cross Modal Retrieval (StacMR)

pix2pixHD. Synthesizing and manipulating 2048x1024 images with conditional GANs