Saghir Alfasly's Projects
This is a PyTorch implementation of the paper: "Processing Megapixel Images with Deep Attention-Sampling Models".
An experimental open-source attempt to make GPT-4 fully autonomous.
A self-supervised learning framework for audio-visual speech
Data-efficient and weakly supervised computational pathology on whole slide images - Nature Biomedical Engineering
Classification models trained on ImageNet. Keras.
Contrastive Language-Image Pretraining
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
A project demonstrating use of Python for DeepStream sample apps given as a part of SDK (that are currently in C,C++).
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
PyTorch code and models for the DINOv2 self-supervised learning method.
A library for efficient similarity search and clustering of dense vectors.
Fast and memory-efficient exact attention
Ressources of histopathology datasets
A project template to simplify building and training deep learning models using Keras.
High-Resolution Image Synthesis with Latent Diffusion Models
Caffe prototext file of the lightweight baseline for pedestrian detection proposed in the paper: Auto-Zooming CNN-Based Framework for Real-Time Pedestrian Detection in Outdoor Surveillance Videos
Inference code for LLaMA models
Examples and recipes for Llama 2 model
Code Repository for Machine Learning with PyTorch and Scikit-Learn
medigan - A Python Library of Pretrained Generative Models for Enriched Data Access in Medical Imaging.
Segment Anything in Medical Images
The official repository for [CVPR2022] MOVER: Human-Aware Object Placement for Visual Environment Reconstruction.
Plug and play modules to boost the performances of your AI systems 🚀
NeMo: a toolkit for conversational AI
Code implementation of the paper: OSRE: Object-to-Spot Rotation Estimation for Bike Parking Assessment (IEEE Transactions on Intelligent Transportation Systems)
Prov-GigaPath: A whole-slide foundation model for digital pathology from real-world data
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more