samils7
Follow
Stars
🦜🔗 Build context-aware reasoning applications
21 Lessons, Get Started Building with Generative AI đź”— https://microsoft.github.io/generative-ai-for-beginners/
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
High-Resolution Image Synthesis with Latent Diffusion Models
CoTracker is a model for tracking any point (pixel) on a video.
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
We are building an open database of COVID-19 cases with chest X-ray or CT images.
MARS5 speech model (TTS) from CAMB.AI
COVID-Net Open Source Initiative
A Chrome extension that adds a 3d photo effect to instagram pages.
Literature survey, paper reviews, experimental setups and a collection of implementations for baselines methods for predictive uncertainty estimation in deep learning models.
Public release of the Image Matching Benchmark: https://image-matching-challenge.github.io
Place where folks can contribute to 🤗 community events
Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.
Baselines for the Image Matching Benchmark and Challenge
Using efficientnet to provide embeddings for retrieval
RAGs: Simple implementations of Retrieval Augmented Generation (RAG) Systems
implement Domain-Adversarial Training of Neural Networks
Barabási–Albert Network. A Step-by-Step Model with Visualizations created in Python 3.
the re-implementation of Score CAM with pytorch
Conversions between kornia and other computer vision libraries formats
Using unet and wgan to enhance resolution and remove watermark
Stitch images using SuperGlue features instead of mouse-clicked points. Compute the homography through RANSAC or MSAC. Stitch more than two images using mouse-clicked points. Handle the seams. {Sup…
Starter notebook and utilities for the Clevr-4 dataset